{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T03:57:57Z","timestamp":1780545477694,"version":"3.54.1"},"reference-count":395,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FT210100097"],"award-info":[{"award-number":["FT210100097"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP240101547"],"award-info":[{"award-number":["DP240101547"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CSIRO\u2014National Science Foundation (U.S.) AI Research Collaboration Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/jproc.2024.3369017","type":"journal-article","created":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T18:29:14Z","timestamp":1711045754000},"page":"97-139","source":"Crossref","is-referenced-by-count":95,"title":["Trustworthy Graph Neural Networks: Aspects, Methods, and Trends"],"prefix":"10.1109","volume":"112","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5796-7891","authenticated-orcid":false,"given":"He","family":"Zhang","sequence":"first","affiliation":[{"name":"Faculty of Information Technology (IT), Monash University, Clayton, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bang","family":"Wu","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology (IT), Monash University, Clayton, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3701-4946","authenticated-orcid":false,"given":"Xingliang","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, The University of Melbourne, Parkville, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-527X","authenticated-orcid":false,"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Southport, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanghang","family":"Tong","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Urbana--Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2200-8711","authenticated-orcid":false,"given":"Jian","family":"Pei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Trinity College of Arts & Sciences, Department of Biostatistics and Bioinformatics, School of Medicine, Department of Electric and Computer Engineering, Pratt School of Engineering, Duke University, Durham, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Wild and Interesting Facebook Statistics and Facts","author":"Osman","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3055400"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352127"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403280"},{"key":"ref6","first-page":"8459","article-title":"Learning to simulate complex physics with graph networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Sanchez-Gonzalez"},{"key":"ref7","first-page":"323","article-title":"Study of mass composition of cosmic rays with IceTop and IceCube","volume-title":"Proc. Int. Cosmic Ray Conf.","author":"Abbasi"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2021.113633"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2105070118"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3546872"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3555803"},{"key":"ref12","volume-title":"Trustworthy Machine Learning","author":"Varshney","year":"2021"},{"key":"ref13","article-title":"Toward trustworthy AI development: Mechanisms for supporting verifiable claims","author":"Brundage","year":"2020","journal-title":"arXiv:2004.07213"},{"key":"ref14","volume-title":"Governance Principles for the New Generation Artificial Intelligence\u2013Developing Responsible Artificial Intelligence","year":"2019"},{"key":"ref15","volume-title":"The Montreal Declaration of Responsible AI","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599410"},{"key":"ref17","first-page":"42492","article-title":"Finding the missing-half: Graph complementary learning for homophily-prone and heterophily-prone graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Zheng"},{"key":"ref18","first-page":"1","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref20","first-page":"6437","article-title":"Training graph neural networks with 1000 layers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441752"},{"key":"ref24","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. NIPS","author":"Ying"},{"key":"ref25","volume-title":"Definition of Trustworthy","author":"Dictionaries","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/2578601"},{"key":"ref27","first-page":"1651","article-title":"GAZELLE: A low latency framework for secure neural network inference","volume-title":"Proc. 27th USENIX Secur. Symp. (USENIX Security)","author":"Juvekar"},{"key":"ref28","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447566"},{"key":"ref31","article-title":"Explainability in graph neural networks: A taxonomic survey","author":"Yuan","year":"2020","journal-title":"arXiv:2012.15445"},{"key":"ref32","article-title":"Probing GNN explainers: A rigorous theoretical and empirical analysis of GNN explanation methods","author":"Agarwal","year":"2021","journal-title":"arXiv:2106.09078"},{"key":"ref33","article-title":"FedGraphNN: A federated learning system and benchmark for graph neural networks","author":"He","year":"2021","journal-title":"arXiv:2104.07145"},{"key":"ref34","first-page":"1","article-title":"On dyadic fairness: Exploring and mitigating bias in graph connections","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403080"},{"key":"ref36","article-title":"A pipeline for fair comparison of graph neural networks in node classification tasks","author":"Zhao","year":"2020","journal-title":"arXiv:2012.10619"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218751"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586181"},{"key":"ref39","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Goodfellow"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref41","first-page":"1","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372833"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/872"},{"key":"ref47","first-page":"2669","article-title":"Stealing links from graph neural networks","volume-title":"Proc. USENIX Secur.","author":"He"},{"key":"ref48","article-title":"Node-level membership inference attacks against graph neural networks","author":"He","year":"2021","journal-title":"arXiv:2102.05429"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00182"},{"key":"ref50","first-page":"1","article-title":"GraphSAINT: Graph sampling based inductive learning method","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zeng"},{"key":"ref51","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/205"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3071274"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1017\/9781108924184"},{"key":"ref55","first-page":"1123","article-title":"Adversarial attack on graph structured data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref56","first-page":"695","article-title":"Adversarial attacks on node embeddings via graph poisoning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bojchevski"},{"key":"ref57","first-page":"305","article-title":"Attacking similarity-based link prediction in social networks","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Zhou"},{"key":"ref58","first-page":"321","article-title":"Manipulating node similarity measures in networks","volume-title":"Proc. Int. Conf. Auto. Agents MultiAgent Syst.","author":"Dey"},{"key":"ref59","first-page":"1","article-title":"Parameterized explainer for graph neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref60","first-page":"1","article-title":"Evaluating attribution for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"S\u00e1nchez-Lengeling"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01103"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00801"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3488932.3497753"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467273"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3087515"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78478-4_9"},{"key":"ref67","first-page":"2114","article-title":"Towards a unified framework for fair and stable graph representation learning","volume-title":"Proc. 37th Conf. Uncertainty Artif. Intell.","author":"Agarwal"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3133818"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498391"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3064761"},{"key":"ref71","article-title":"Accountable algorithms","author":"Kroll","year":"2015"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3477141"},{"key":"ref74","article-title":"A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability","author":"Dai","year":"2022","journal-title":"arXiv:2204.08570"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414831"},{"key":"ref76","first-page":"13556","article-title":"Graph normalizing flows","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref77","article-title":"Out-of-distribution generalization on graphs: A survey","author":"Li","year":"2202","journal-title":"arXiv:2202.07987"},{"key":"ref78","first-page":"1","article-title":"Discovering invariant rationales for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3141260"},{"key":"ref80","article-title":"Generalizing graph neural networks on out-of-distribution graphs","author":"Fan","year":"2111","journal-title":"arXiv:2111.10657"},{"key":"ref81","first-page":"1","article-title":"How neural networks extrapolate: From feedforward to graph neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref82","volume-title":"Fighting Computer Crime\u2014A New Framework for Protecting Information","author":"Parker","year":"1998"},{"key":"ref83","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Gilmer"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932096"},{"key":"ref85","first-page":"6316","article-title":"Contrastive graph Poisson networks: Semi-supervised learning with extremely limited labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wan"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3104155"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-6054-2_3"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467314"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482161"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00201"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3485387"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3163672"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2009.11.037"},{"key":"ref94","first-page":"1","article-title":"Adversarial attacks on graph neural networks via meta learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Z\u00fcgner"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75768-7_9"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380149"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00138"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71590-8_8"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3450569.3463560"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00696-7"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467416"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3468218.3469046"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/458"},{"key":"ref104","first-page":"1","article-title":"Understanding and improving graph injection attack by promoting unnoticeability","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2020.3031058"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/550"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/669"},{"key":"ref108","article-title":"Fast gradient attack on network embedding","author":"Chen","year":"2018","journal-title":"arXiv:1809.02797"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.693"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447566"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484796"},{"key":"ref112","article-title":"Graph robustness benchmark: Benchmarking the adversarial robustness of graph machine learning","author":"Zheng","year":"2021","journal-title":"arXiv:2111.04314"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371789"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403049"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512180"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330851"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371851"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054325"},{"key":"ref119","first-page":"9263","article-title":"GNNguard: Defending graph neural networks against adversarial attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2957786"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67664-3_24"},{"key":"ref122","first-page":"8317","article-title":"Certifiable robustness to graph perturbations","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Bojchevski"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330905"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441782"},{"key":"ref125","first-page":"1","article-title":"Comparing and detecting adversarial attacks for graph deep learning","volume-title":"Proc. Represent. Learn. Graphs Manifolds Workshop","author":"Zhang"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3188583"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1145\/3544968"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3153844"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3468791.3468814"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140451"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449989"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411903"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPCT.2017.8074262"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2020.113303"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/310"},{"key":"ref136","first-page":"1","article-title":"Evaluating the robustness of neural networks: An extreme value theory approach","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Weng"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/583"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20357"},{"key":"ref139","first-page":"1","article-title":"Robustness of graph neural networks at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Geisler"},{"key":"ref140","article-title":"GraphSAC: Detecting anomalies in large-scale graphs","author":"Ioannidis","year":"2019","journal-title":"arXiv:1910.09589"},{"key":"ref141","first-page":"1","article-title":"Reliable graph neural networks via robust aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Geisler"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467323"},{"key":"ref144","first-page":"1","article-title":"GStarX: Explaining graph neural networks with structure-aware cooperative games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref145","first-page":"6199","article-title":"Distill n\u2019 explain: Explaining graph neural networks using simple surrogates","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"206","author":"Pereira"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20615"},{"key":"ref147","article-title":"PSICHIC: Physicochemical graph neural network for learning protein-ligand interaction fingerprints from sequence data","author":"Koh","year":"2023","journal-title":"BioRxiv"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467154"},{"key":"ref149","article-title":"Jointly attacking graph neural network and its explanations","author":"Fan","year":"2021","journal-title":"arXiv:2108.03388"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-6054-2_7"},{"key":"ref151","volume-title":"Interpretable Machine Learning","author":"Molnar","year":"2020"},{"key":"ref152","first-page":"15524","article-title":"Interpretable and generalizable graph learning via stochastic attention mechanism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Miao"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1126\/science.298.5594.824"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11742"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220063"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3187455"},{"key":"ref158","first-page":"5644","article-title":"Robust counterfactual explanations on graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bajaj"},{"key":"ref159","author":"Olah","year":"2017","journal-title":"Feature Visualization"},{"key":"ref160","first-page":"882","article-title":"Learning to explain: An information-theoretic perspective on model interpretation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Chen"},{"key":"ref161","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Duvenaud"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358155"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482306"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20898"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i18.17986"},{"key":"ref166","first-page":"1","article-title":"Graph information bottleneck for subgraph recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref167","first-page":"1","article-title":"Explainability techniques for graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baldassarre"},{"key":"ref168","first-page":"4203","article-title":"Improving molecular graph neural network explainability with orthonormalization and induced sparsity","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henderson"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357910"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358044"},{"key":"ref171","volume-title":"Causal Screening To Interpret Graph Neural Networks","author":"Wang","year":"2021"},{"key":"ref172","first-page":"12225","article-title":"PGM-explainer: Probabilistic graphical model explanations for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vu"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115452"},{"key":"ref174","first-page":"22523","article-title":"Reinforcement learning enhanced explainer for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shan"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01336"},{"key":"ref176","first-page":"1","article-title":"DEGREE: Decomposition based explanation for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Feng"},{"key":"ref177","first-page":"6666","article-title":"Generative causal explanations for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref178","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Sundararajan"},{"key":"ref179","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Shrikumar"},{"key":"ref180","first-page":"10220","article-title":"CXPlain: Causal explanations for model interpretation under uncertainty","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Schwab"},{"key":"ref181","volume-title":"Hard Masking for Explaining Graph Neural Networks","author":"Funke","year":"2021"},{"key":"ref182","first-page":"1","article-title":"Interpreting graph neural networks for NLP with differentiable edge masking","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schlichtkrull"},{"key":"ref183","first-page":"12241","article-title":"On explainability of graph neural networks via subgraph explorations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yuan"},{"key":"ref184","first-page":"4499","article-title":"CF-GNNexplainer: Counterfactual explanations for graph neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Lucic"},{"key":"ref185","first-page":"18446","article-title":"Towards multi-grained explainability for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511948"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462562"},{"key":"ref188","first-page":"1018","article-title":"Sanity checks for saliency maps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Adebayo"},{"key":"ref189","first-page":"6967","article-title":"Real time image saliency for black box classifiers","volume-title":"Proc. NIPS","author":"Dabkowski"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3178211"},{"issue":"12","key":"ref191","first-page":"47","article-title":"Generative explanation for graph neural network: Methods and evaluation","volume":"54","author":"Chen","year":"2023","journal-title":"Extraction"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/490"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1117\/12.2550114"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60365-6_20"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac478"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.156"},{"key":"ref197","first-page":"117","article-title":"Histocartography: A toolkit for graph analytics in digital pathology","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent Workshop Comput. Pathol.","volume":"156","author":"Jaume"},{"key":"ref198","article-title":"Towards the explanation of graph neural networks in digital pathology with information flows","author":"Yu","year":"2021","journal-title":"arXiv:2112.09895"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86970-0_5"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.48"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75762-5_56"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/DSN53405.2022.00028"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS54753.2022.9798287"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2023.100747"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_36"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI52829.2022.9761449"},{"key":"ref207","article-title":"APRILE: Exploring the molecular mechanisms of drug side effects with explainable graph neural networks","author":"Xu","year":"2021","journal-title":"BioRxiv"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c01344"},{"key":"ref209","first-page":"4849","article-title":"Multi-objective molecule generation using interpretable substructures","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"119","author":"Jin"},{"key":"ref210","first-page":"1","article-title":"Molecule optimization by explainable evolution","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103955"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403393"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412734"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/825"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73200-4_31"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1145\/3448891.3448939"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560662"},{"key":"ref218","first-page":"1972","article-title":"Learning discrete structures for graph neural networks","volume-title":"Proc. 36th Conf. Mach. Learn.","author":"Franceschi"},{"key":"ref219","article-title":"Membership inference attacks on knowledge graphs","author":"Wang","year":"2021","journal-title":"arXiv:2104.08273"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/516"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833806"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref223","article-title":"Federated graph learning\u2014A position paper","author":"Zhang","year":"2021","journal-title":"arXiv:2105.11099"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00435-6"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3360429"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref227","article-title":"GraphFL: A federated learning framework for semi-supervised node classification on graphs","author":"Wang","year":"2020","journal-title":"arXiv:2012.04187"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1007\/s12083-021-01074-w"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/643"},{"key":"ref230","volume-title":"Banca Online Webank: Conto Corrente Online E Mobile Banking","year":"2022"},{"key":"ref231","volume-title":"National Vat Invoice Verification Platform","year":"2022"},{"key":"ref232","volume-title":"Tencent\u2019s Webank Applying in AI. Digital Finance","author":"Ku","year":"2019"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1145\/3501808"},{"key":"ref234","article-title":"SpreadGNN: Serverless multi-task federated learning for graph neural networks","author":"He","year":"2021","journal-title":"arXiv:2106.02743"},{"key":"ref235","article-title":"Federated graph classification over non-IID graphs","author":"Xie","year":"2021","journal-title":"arXiv:2106.13423"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89847-2_4"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100521"},{"key":"ref238","article-title":"STFL: A temporal-spatial federated learning framework for graph neural networks","author":"Lou","year":"2021","journal-title":"arXiv:2111. 06750"},{"key":"ref239","article-title":"FedGNN: Federated graph neural network for privacy-preserving recommendation","author":"Wu","year":"2021","journal-title":"arXiv:2102.04925"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1145\/3501815"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.11593"},{"key":"ref242","article-title":"Vertically federated graph neural network for privacy-preserving node classification","author":"Chen","year":"2020","journal-title":"arXiv:2005.11903"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119976"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467371"},{"key":"ref245","article-title":"Subgraph federated learning with missing neighbor generation","author":"Zhang","year":"2021","journal-title":"arXiv:2106.13430"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3125565"},{"key":"ref247","article-title":"Towards representation identical privacy-preserving graph neural network via split learning","author":"Shan","year":"2021","journal-title":"arXiv:2107.05917"},{"key":"ref248","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018","journal-title":"arXiv:1806.00582"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.48"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484565"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93037-4_19"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449813"},{"key":"ref253","first-page":"6600","article-title":"Information obfuscation of graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Liao"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3036583"},{"key":"ref255","first-page":"1","article-title":"Slalom: Fast, verifiable and private execution of neural networks in trusted hardware","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tram\u00e8r"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1145\/3386901.3388946"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58951-6_20"},{"key":"ref258","first-page":"1","article-title":"Glyph: Fast and accurately training deep neural networks on encrypted data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lou"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.12"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3138611"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3146448"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58951-6_21"},{"key":"ref264","article-title":"FedGCN: Convergence-communication tradeoffs in federated training of graph convolutional networks","author":"Yao","year":"2022","journal-title":"arXiv:2201.12433"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3241615"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.14778\/3587136.3587138"},{"key":"ref267","first-page":"37676","article-title":"CryptoGCN: Fast and scalable homomorphically encrypted graph convolutional network inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ran"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/380"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-38314-3"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1393"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450015"},{"key":"ref273","first-page":"14747","article-title":"Deep leakage from gradients","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref275","first-page":"1","article-title":"R-GAP: Recursive gradient attack on privacy","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref276","first-page":"1","article-title":"Learning fair graph representations via automated data augmentations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ling"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314248"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/456"},{"key":"ref279","first-page":"4066","article-title":"Counterfactual fairness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kusner"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1145\/3194770.3194776"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"ref282","first-page":"18839","article-title":"Federated graph classification over non-IID graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482030"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467266"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30487-3_8"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287594"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/549"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21182"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585893"},{"key":"ref290","first-page":"715","article-title":"Compositional fairness constraints for graph embeddings","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML","author":"Bose"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512173"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020694"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1145\/3568022"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272027"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM55673.2022.10068703"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539346"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1145\/3547333"},{"key":"ref299","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101906","article-title":"A survey on fairness-aware recommender systems","volume":"100","author":"Jin","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531959"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1145\/3495163"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462875"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441824"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/807"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441743"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494128"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3124061"},{"key":"ref308","article-title":"Graph neural networks for graphs with heterophily: A survey","author":"Zheng","year":"2022","journal-title":"arXiv:2202.07082"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098095"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512169"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25905"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114850"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00117"},{"key":"ref314","first-page":"1","article-title":"Uncovering the structural fairness in graph contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref315","article-title":"Lightning: Striking the secure isolation on GPU clouds with transient hardware faults","author":"Sun","year":"2021","journal-title":"arXiv:2112.03662"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1561\/3300000002"},{"key":"ref317","volume-title":"Europe Fit for the Digital Age: Commission Proposes New Rules and Actions for Excellence and Trust in Artificial Intelligence","year":"2021"},{"key":"ref318","article-title":"A novel genetic algorithm with hierarchical evaluation strategy for hyperparameter optimisation of graph neural networks","author":"Yuan","year":"2021","journal-title":"arXiv:2101.09300"},{"key":"ref319","article-title":"Bag of tricks for node classification with graph neural networks","author":"Wang","year":"2021","journal-title":"arXiv:2103.13355"},{"key":"ref320","article-title":"Bag of tricks for training deeper graph neural networks: A comprehensive benchmark study","author":"Chen","year":"2021","journal-title":"arXiv:2108.10521"},{"key":"ref321","first-page":"1","article-title":"A fair comparison of graph neural networks for graph classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Errica"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643556"},{"key":"ref323","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00486"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00106"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i18.18013"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20338"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1109\/ICMTMA50254.2020.00108"},{"key":"ref328","volume-title":"Ai-powered Crime Prediction Draws Attention Amid Legal Battle","author":"KaburuGlory","year":"2023"},{"key":"ref329","article-title":"A needle in the haystack: Inspecting circuit layout to identify hardware trojans","volume":"2023\/610","author":"Meng","year":"2023","journal-title":"IACR Cryptol. ePrint Arch."},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1355"},{"key":"ref331","first-page":"1","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref332","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00089"},{"key":"ref333","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583498"},{"key":"ref334","first-page":"1","article-title":"DropEdge: Towards deep graph convolutional networks on node classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rong"},{"key":"ref335","article-title":"Learned low precision graph neural networks","author":"Zhao","year":"2020","journal-title":"arXiv:2009.09232"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403236"},{"key":"ref337","first-page":"1","article-title":"Degree-quant: Quantization-aware training for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tailor"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.14778\/3461535.3461547"},{"key":"ref339","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3065737"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"ref341","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS52030.2021.00048"},{"key":"ref343","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313508"},{"key":"ref344","first-page":"3294","article-title":"GNNAutoScale: Scalable and expressive graph neural networks via historical embeddings","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Fey"},{"key":"ref345","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481916"},{"key":"ref346","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/314"},{"key":"ref347","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/320"},{"key":"ref348","first-page":"1695","article-title":"A unified lottery ticket hypothesis for graph neural networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref349","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00937"},{"key":"ref350","first-page":"1","article-title":"Fast graph representation learning with PyTorch geometric","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fey"},{"key":"ref351","first-page":"1","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref352","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3014632"},{"key":"ref353","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2970395"},{"key":"ref354","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358318"},{"key":"ref355","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref356","first-page":"103","article-title":"BGL: GPU-efficient GNN training by optimizing graph data I\/O and preprocessing","volume-title":"Proc. USENIX Symp. Netw. Syst. Design Implement.","author":"Liu"},{"key":"ref357","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2023.3337442"},{"key":"ref358","article-title":"A survey on graph neural network acceleration: Algorithms, systems, and customized hardware","author":"Zhang","year":"2023","journal-title":"arXiv:2306.14052"},{"key":"ref359","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240796"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/637"},{"key":"ref361","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643549"},{"key":"ref362","first-page":"1523","article-title":"Graph backdoor","volume-title":"Proc. 30th USENIX Secur. Symp.","author":"Xi"},{"key":"ref363","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482252"},{"key":"ref364","first-page":"41737","article-title":"Demystifying uneven vulnerability of link stealing attacks against graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Zhang"},{"key":"ref365","article-title":"On the interaction between node fairness and edge privacy in graph neural networks","author":"Zhang","year":"2023","journal-title":"arXiv:2301.12951"},{"key":"ref366","first-page":"1","article-title":"Discrete-valued neural communication","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref367","article-title":"DefenseVGAE: Defending against adversarial attacks on graph data via a variational graph autoencoder","author":"Zhang","year":"2020","journal-title":"arXiv:2006.08900"},{"key":"ref368","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450068"},{"key":"ref369","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/367"},{"key":"ref370","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref371","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00056"},{"key":"ref372","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/195"},{"key":"ref373","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00710"},{"key":"ref374","first-page":"1048","article-title":"Subgroup generalization and fairness of graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ma"},{"key":"ref375","first-page":"3419","article-title":"Generalization and representational limits of graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Garg"},{"key":"ref376","first-page":"1","article-title":"BSQ: Exploring bit-level sparsity for mixed-precision neural network quantization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref377","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512186"},{"key":"ref378","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2022.3142719"},{"key":"ref379","article-title":"Holistic survey of privacy and fairness in machine learning","author":"Shaham","year":"2023","journal-title":"arXiv:2307.15838"},{"key":"ref380","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvkjb25m"},{"key":"ref381","volume-title":"Trusted AI","year":"2021"},{"key":"ref382","first-page":"1","article-title":"TUDataset: A collection of benchmark datasets for learning with graphs","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop Graph Represent. Learn. Beyond","author":"Morris"},{"key":"ref383","first-page":"23768","article-title":"Be confident! towards trustworthy graph neural networks via confidence calibration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref384","article-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","author":"Wang","year":"2019","journal-title":"arXiv:1909.01315"},{"key":"ref385","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion52605.2021.00024"},{"key":"ref386","doi-asserted-by":"publisher","DOI":"10.1145\/3545176"},{"key":"ref387","article-title":"Transformer for graphs: An overview from architecture perspective","author":"Min","year":"2022","journal-title":"arXiv:2202.08455"},{"key":"ref388","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/244"},{"key":"ref389","article-title":"Attending to graph transformers","author":"M\u00fcller","year":"2023","journal-title":"arXiv:2302.04181"},{"key":"ref390","first-page":"653","article-title":"Food knowledge representation learning with adversarial substitution","volume-title":"Proc. Conf. Asia\u2013Pacific Chapter Assoc. Comput. Linguistics Int. Joint Conf. Natural Lang. Process.","author":"Li"},{"key":"ref391","doi-asserted-by":"crossref","DOI":"10.1101\/2022.10.24.513465","article-title":"Adversarial attacks on protein language models","volume-title":"Proc. MLSB@NeurIP","author":"Carbone"},{"key":"ref392","article-title":"Structure-free graph condensation: From large-scale graphs to condensed graph-free data","author":"Zheng","year":"2023","journal-title":"arXiv:2306.02664"},{"key":"ref393","article-title":"Towards data-centric graph machine learning: Review and outlook","author":"Zheng","year":"2023","journal-title":"arXiv:2309.10979"},{"key":"ref394","article-title":"OGB-LSC: A large-scale challenge for machine learning on graphs","author":"Hu","year":"2021","journal-title":"arXiv:2103.09430"},{"key":"ref395","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5429"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5\/10496398\/10477407-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/10496398\/10477407.pdf?arnumber=10477407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T19:02:10Z","timestamp":1712862130000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10477407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":395,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2024.3369017","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}