{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:42:23Z","timestamp":1740109343316,"version":"3.37.3"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001230","name":"Macquarie University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001230","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>In heterogeneous graph analysis, existing self-supervised learning (SSL) methods face several key challenges. Primarily, these approaches are tailored for node-level tasks and fail to effectively capture global graph-level features, a crucial aspect for comprehensive graph understanding. Furthermore, they predominantly rely on meta-path-based techniques to unravel graph structures, a process that can be computationally intensive and often intractable for complex networks. Another significant limitation is their inability to account for nonpairwise relationships, a common characteristic in real-world networks like protein-protein interaction and collaboration networks, limiting their effectiveness in graph-level learning where high-order connectivity is essential. To address these issues, we propose an innovative SSL framework for heterogeneous hypergraph embedding, expressly designed to enhance graph-level classification. Our framework introduces multi-hop attention in hypergraph convolution, a significant leap from existing attention mechanisms specifically for hypergraphs that primarily focus on immediate neighborhoods. This multi-hop approach allows for an expansive capture of relational structures, both near and far, uncovering intricate patterns integral to accurate graph-level classification. Complementing this, we implement an informative graph-level attentive pooling mechanism that surpasses traditional aggregation methods. It intelligently synthesizes features, taking into account their structural and semantic importance within the hypergraph, thereby preserving critical contextual information. Furthermore, we refine our contrastive learning approach and introduce targeted negative sampling strategies, creating a more robust learning environment that excels at discerning nuanced graph-level features. Rigorous evaluation against established graph kernels, graph neural networks, and graph pooling methods on real-world datasets demonstrates our model\u2019s superior performance, validating its effectiveness in addressing the complexities inherent in heterogeneous graph-level classification.<\/jats:p>","DOI":"10.1007\/s10115-024-02259-4","type":"journal-article","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T02:52:51Z","timestamp":1731639171000},"page":"1945-1968","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-supervised multi-hop heterogeneous hypergraph embedding with informative pooling for graph-level classification"],"prefix":"10.1007","volume":"67","author":[{"given":"Malik Khizar","family":"Hayat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,15]]},"reference":[{"issue":"1","key":"2259_CR1","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2008) The graph neural network model. IEEE Trans. on Neural Netw 20(1):61\u201380","journal-title":"IEEE Trans. on Neural Netw"},{"key":"2259_CR2","unstructured":"Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. Advances in neural information processing systems 30"},{"issue":"5","key":"2259_CR3","doi-asserted-by":"publisher","first-page":"2661","DOI":"10.1007\/s11192-022-04340-7","volume":"127","author":"R Alharbey","year":"2022","unstructured":"Alharbey R, Kim JI, Daud A, Song M, Alshdadi AA, Hayat MK (2022) Indexing important drugs from medical literature. Scientometrics 127(5):2661\u20132681","journal-title":"Scientometrics"},{"issue":"14","key":"2259_CR4","doi-asserted-by":"publisher","first-page":"40489","DOI":"10.1007\/s11042-023-17126-7","volume":"83","author":"Malik Khizar Hayat","year":"2023","unstructured":"Hayat Malik Khizar, Daud Ali, Banjar Ameen, Alharbey Riad, Bukhari Amal (2023) A deep co-evolution architecture for anomaly detection in dynamic networks. Multimed Tools Appl 83(14):40489\u201340508. https:\/\/doi.org\/10.1007\/s11042-023-17126-7","journal-title":"Multimed Tools Appl"},{"issue":"6","key":"2259_CR5","doi-asserted-by":"publisher","first-page":"3536","DOI":"10.1109\/TCSS.2022.3206396","volume":"10","author":"Muhammad Sajid Qureshi","year":"2023","unstructured":"Qureshi Muhammad Sajid, Daud Ali, Hayat Malik Khizar, Song Min, Park Yejin (2023) Heading towards sub-discipline rankings for higher education institutions. IEEE Trans Comput Soc Syst 10(6):3536\u20133555","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"2259_CR6","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: Proceedings of the 6th international conference on learning representations"},{"key":"2259_CR7","doi-asserted-by":"crossref","unstructured":"Wang X, Ji H, Shi C, Wang B, Ye Y, Cui P, Yu PS (2019) Heterogeneous graph attention network. In: The World Wide Web Conference, pp. 2022\u20132032","DOI":"10.1145\/3308558.3313562"},{"key":"2259_CR8","doi-asserted-by":"crossref","unstructured":"Zhang M, Cui Z, Neumann M, Chen Y (2018) An end-to-end deep learning architecture for graph classification. In: Proceedings of the AAAI Conf. on Artificial Intelligence, vol.\u00a032, no.\u00a01","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"2259_CR9","doi-asserted-by":"crossref","unstructured":"Li J, Rong Y, Cheng H, Meng H, Huang W, Huang J (2019) Semi-supervised graph classification: a hierarchical graph perspective. In: The World Wide Web Conf., pp. 972\u2013982","DOI":"10.1145\/3308558.3313461"},{"issue":"9","key":"2259_CR10","first-page":"2539","volume":"12","author":"N Shervashidze","year":"2011","unstructured":"Shervashidze N, Schweitzer P, Van Leeuwen EJ, Mehlhorn K, Borgwardt KM (2011) Weisfeiler-lehman graph kernels. J Mach Learn Res 12(9):2539\u20132561","journal-title":"J Mach Learn Res"},{"key":"2259_CR11","doi-asserted-by":"crossref","unstructured":"Yanardag P, Vishwanathan S (2015) Deep graph kernels. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery<error l=\"300\" c=\"Unexpected ampersand\" \/> Data Mining, pp. 1365\u20131374","DOI":"10.1145\/2783258.2783417"},{"key":"2259_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107637","volume":"110","author":"S Bai","year":"2021","unstructured":"Bai S, Zhang F, Yu PS (2021) Hypergraph convolution and hypergraph attention. Pattern Recogn 110:107637","journal-title":"Pattern Recogn"},{"key":"2259_CR13","doi-asserted-by":"crossref","unstructured":"Sun X, Yin H, Liu B, Chen H, Cao J, Shao Y, Viet\u00a0Hung NQ (2021) \u201cHeterogeneous hypergraph embedding for graph classification. In: Proceedings of the 14th ACM international conference on web search and data mining, pp. 725\u2013733","DOI":"10.1145\/3437963.3441835"},{"key":"2259_CR14","doi-asserted-by":"crossref","unstructured":"Wu J, Li S, Li J, Pan Y, Xu K (2022) A simple yet effective method for graph classification. In: international joint conference on artificial intelligence (IJCAI), pp. 3580\u20133586","DOI":"10.24963\/ijcai.2022\/497"},{"key":"2259_CR15","doi-asserted-by":"crossref","unstructured":"Feng A, Li I, Jiang Y, Ying R (2023) Diffuser: efficient transformers with multi-hop attention diffusion for long sequences. In: Proceedings of the AAAI Conference on Artificial Intelligence 37(11):12 772-12 780","DOI":"10.1609\/aaai.v37i11.26502"},{"key":"2259_CR16","doi-asserted-by":"crossref","unstructured":"Hayat MK, Xue S, Yang J (2023) Self-supervised heterogeneous hypergraph learning with context-aware pooling for graph-level classification. In: Proceedings of the international conference on data mining (ICDM)","DOI":"10.1109\/ICDM58522.2023.00023"},{"key":"2259_CR17","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems, vol.\u00a030"},{"key":"2259_CR18","unstructured":"Rieck B, Bock C, Borgwardt K (2019) \u201cA persistent weisfeiler-lehman procedure for graph classification. In: International Conference on Machine Learning. PMLR, pp. 5448\u20135458"},{"key":"2259_CR19","doi-asserted-by":"crossref","unstructured":"Long Q, Jin Y, Wu Y, Song G (2021) Theoretically improving graph neural networks via anonymous walk graph kernels. In: Proceedings of the Web Conference, pp. 1204\u20131214","DOI":"10.1145\/3442381.3449951"},{"key":"2259_CR20","unstructured":"Baek J, Kang M, Hwang SJ (2021) Accurate learning of graph representations with graph multiset pooling. In: International Conference on Learning Representations (ICLR)"},{"key":"2259_CR21","unstructured":"Z.\u00a0Xinyi and L.\u00a0Chen (2019) Capsule graph neural network. In: International Conference on Learning Representations, 2019"},{"key":"2259_CR22","unstructured":"Xu K, Hu W, Leskovec J, and Jegelka S (2018) How powerful are graph neural networks?\u201d arXiv preprint arXiv:1810.00826, 2018"},{"key":"2259_CR23","first-page":"16 211","volume":"33","author":"G Nikolentzos","year":"2020","unstructured":"Nikolentzos G, Vazirgiannis M (2020) Random walk graph neural networks. Adv Neural Inf Process Syst 33:16 211-16 222","journal-title":"Adv Neural Inf Process Syst"},{"key":"2259_CR24","unstructured":"Wijesinghe A, Wang Q (2022) A new perspective on\" how graph neural networks go beyond weisfeiler-lehman?\". In: Internationl Conference on Learning Representations"},{"key":"2259_CR25","first-page":"2081","volume":"2021","author":"Q Sun","year":"2021","unstructured":"Sun Q, Li J, Peng H, Wu J, Ning Y, Yu PS, He L (2021) Sugar: Subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism. Proc of the Web Conf 2021:2081\u20132091","journal-title":"Proc of the Web Conf"},{"key":"2259_CR26","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3208063","author":"Kaixuan Chen","year":"2022","unstructured":"Chen Kaixuan, Song Jie, Liu Shunyu, Yu Na, Feng Zunlei, Han Gengshi, Song Mingli (2022) Distribution knowledge embedding for graph pooling. IEEE Trans Knowl Data Eng. https:\/\/doi.org\/10.1109\/TKDE.2022.3208063","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2259_CR27","doi-asserted-by":"crossref","unstructured":"Ma Y, Wang S, Aggarwal CC, Tang J (2019) Graph convolutional networks with eigenpooling. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery and data mining, pp. 723\u2013731","DOI":"10.1145\/3292500.3330982"},{"key":"2259_CR28","unstructured":"Lee J, Lee I, Kang J (2019) Self-attention graph pooling. In: International conference on machine learning. PMLR, pp. 3734\u20133743"},{"key":"2259_CR29","unstructured":"Yuan H, Ji S (2020) \u201cStructpool: Structured graph pooling via conditional random fields. In: Proceedings of the 8th international conference on learning representations"},{"key":"2259_CR30","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conf. Proceedings, pp. 249\u2013256"},{"key":"2259_CR31","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"},{"key":"2259_CR32","doi-asserted-by":"crossref","unstructured":"Dong Y, Chawla NV, Swami A (2017) \u201cmetapath2vec: Scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 135\u2013144","DOI":"10.1145\/3097983.3098036"},{"key":"2259_CR33","doi-asserted-by":"crossref","unstructured":"Fu T-y, Lee W-C, Lei Z (2017) \u201cHin2vec: Explore meta-paths in heterogeneous information networks for representation learning. In: Proceedings of the 2017 ACM on Conference on information and knowledge management, pp. 1797\u20131806","DOI":"10.1145\/3132847.3132953"},{"key":"2259_CR34","doi-asserted-by":"crossref","unstructured":"Fu X, Zhang J, Meng Z, King I (2020) Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of the web conference, pp. 2331\u20132341","DOI":"10.1145\/3366423.3380297"},{"issue":"1","key":"2259_CR35","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s11192-017-2467-y","volume":"113","author":"MK Hayat","year":"2017","unstructured":"Hayat MK, Daud A (2017) Anomaly detection in heterogeneous bibliographic information networks using co-evolution pattern mining. Scientometrics 113(1):149\u2013175","journal-title":"Scientometrics"},{"key":"2259_CR36","doi-asserted-by":"publisher","first-page":"36\u00a0958","DOI":"10.1109\/ACCESS.2019.2905101","volume":"7","author":"MK Hayat","year":"2019","unstructured":"Hayat MK, Daud A, Alshdadi AA, Banjar A, Abbasi RA, Bao Y, Dawood H (2019) Towards deep learning prospects: insights for social media analytics. IEEE access 7:36\u00a0958-36\u00a0979","journal-title":"IEEE access"},{"key":"2259_CR37","doi-asserted-by":"crossref","unstructured":"Zhao J, Wang X, Shi C, Liu Z, Ye Y (2020) Network schema preserving heterogeneous information network embedding. In: International joint conference on artificial intelligence (IJCAI)","DOI":"10.24963\/ijcai.2020\/190"},{"key":"2259_CR38","doi-asserted-by":"crossref","unstructured":"Hu Z, Dong Y, Wang K, Sun Y (2020) Heterogeneous graph transformer. In: Proceedings of The Web Conference pp. 2704\u20132710","DOI":"10.1145\/3366423.3380027"},{"key":"2259_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2019.101663","volume":"80","author":"W Shao","year":"2020","unstructured":"Shao W, Peng Y, Zu C, Wang M, Zhang D, Initiative ADN et al (2020) Hypergraph based multi-task feature selection for multimodal classification of alzheimer\u2019s disease. Comput Med Imaging Graph 80:101663","journal-title":"Comput Med Imaging Graph"},{"key":"2259_CR40","doi-asserted-by":"crossref","unstructured":"Yang D, Qu B, Yang J, Cudre-Mauroux P (2019) Revisiting user mobility and social relationships in lbsns: a hypergraph embedding approach. In: The world wide web conference, pp. 2147\u20132157","DOI":"10.1145\/3308558.3313635"},{"key":"2259_CR41","doi-asserted-by":"crossref","unstructured":"Zhou D, Huang J, Sch\u00f6lkopf B (2006) Learning with hypergraphs: clustering, classification, and embedding. Adv neural inf process syst, vol.\u00a019","DOI":"10.7551\/mitpress\/7503.003.0205"},{"key":"2259_CR42","doi-asserted-by":"publisher","unstructured":"Feng Yifan, You Haoxuan, Zhang Zizhao, Ji Rongrong, Gao Yue (2019) Hypergraph Neural Networks. In: Proceedings of the AAAI conference on artificial intelligence 33(01):3558\u20133565. https:\/\/doi.org\/10.1609\/aaai.v33i01.33013558","DOI":"10.1609\/aaai.v33i01.33013558"},{"issue":"3","key":"2259_CR43","doi-asserted-by":"publisher","first-page":"3181","DOI":"10.1109\/TPAMI.2022.3182052","volume":"45","author":"Y Gao","year":"2022","unstructured":"Gao Y, Feng Y, Ji S, Ji R (2022) Hgnn+: General hypergraph neural networks. IEEE Trans Pattern Anal Mach Intell 45(3):3181\u20133199","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2259_CR44","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.neunet.2022.08.028","volume":"157","author":"J Liu","year":"2023","unstructured":"Liu J, Song L, Wang G, Shang X (2023) Meta-hgt: metapath-aware hypergraph transformer for heterogeneous information network embedding. Neural Netw 157:65\u201376","journal-title":"Neural Netw"},{"key":"2259_CR45","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.ins.2022.12.075","volume":"624","author":"T Wu","year":"2023","unstructured":"Wu T, Ling Q (2023) Self-supervised heterogeneous hypergraph network for knowledge tracing. Inf Sci 624:200\u2013216","journal-title":"Inf Sci"},{"key":"2259_CR46","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3450658","author":"Malik Khizar Hayat","year":"2024","unstructured":"Hayat Malik Khizar, Xue Shan, Wu Jia, Yang Jian (2024) Heterogeneous hypergraph embedding for node classification in dynamic networks. IEEE Trans Artif Intell. https:\/\/doi.org\/10.1109\/TAI.2024.3450658","journal-title":"IEEE Trans Artif Intell"},{"key":"2259_CR47","unstructured":"Gao H, Ji S (2019) Graph u-nets. In: international conference on machine learning. PMLR, pp. 2083\u20132092"},{"key":"2259_CR48","unstructured":"Ying Z, You J, Morris C, Ren X, Hamilton W, Leskovec J (2018) Hierarchical graph representation learning with differentiable pooling. Adv Neural Inf Process Syst, vol.\u00a031"},{"key":"2259_CR49","unstructured":"Bianchi FM, Grattarola D, Alippi C (2020) Spectral clustering with graph neural networks for graph pooling. In International conference on machine learning. PMLR, pp. 874\u2013883"},{"key":"2259_CR50","doi-asserted-by":"crossref","unstructured":"Qiu J, Chen Q, Dong Y, Zhang J, Yang H, Ding M, Wang K, Tang J (2020) \u201cGcc: Graph contrastive coding for graph neural network pre-training. In:n Proceedings of the 26th ACM sigkdd internationl conference on knowledge discovery and data mining, pp. 1150\u20131160","DOI":"10.1145\/3394486.3403168"},{"key":"2259_CR51","first-page":"5812","volume":"33","author":"Y You","year":"2020","unstructured":"You Y, Chen T, Sui Y, Chen T, Wang Z, Shen Y (2020) Graph contrastive learning with augmentations. Adv Neural Inf Process Syst 33:5812\u20135823","journal-title":"Adv Neural Inf Process Syst"},{"key":"2259_CR52","doi-asserted-by":"crossref","unstructured":"Park C, Kim D, Han J, Yu H (2020) \u201cUnsupervised attributed multiplex network embedding. In: Proceedings of the AAAI conference on artificial intelligence, vol.\u00a034, no.\u00a004, pp. 5371\u20135378","DOI":"10.1609\/aaai.v34i04.5985"},{"key":"2259_CR53","doi-asserted-by":"crossref","unstructured":"Wang X, Liu N, Han H, Shi C (2021) \u201cSelf-supervised heterogeneous graph neural network with co-contrastive learning. In: Proceedings of the 27th ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1726\u20131736","DOI":"10.1145\/3447548.3467415"},{"issue":"10","key":"2259_CR54","doi-asserted-by":"publisher","first-page":"13914","DOI":"10.1109\/TNNLS.2023.3273255","volume":"35","author":"Gen Shi","year":"2024","unstructured":"Shi Gen, Zhu Yifan, Liu Jian K., Li Xuesong (2024) HeGCL: advance self-supervised learning in heterogeneous graph-level representation. IEEE Trans Neural Netw Learn Syst 35(10):13914\u201313925. https:\/\/doi.org\/10.1109\/TNNLS.2023.3273255","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-024-02259-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-024-02259-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-024-02259-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T13:50:05Z","timestamp":1738331405000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-024-02259-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,15]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["2259"],"URL":"https:\/\/doi.org\/10.1007\/s10115-024-02259-4","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2024,11,15]]},"assertion":[{"value":"17 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}