{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:02Z","timestamp":1763191082106,"version":"3.45.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229011","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Every Hop Etched in Memory: Tokenized Graph Mamba Meets Directed Graph Learning"],"prefix":"10.1109","author":[{"given":"Lizhi","family":"Liu","sequence":"first","affiliation":[{"name":"China UnionPay,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3837","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"NIPS","author":"Defferrard"},{"key":"ref2","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"NIPS","author":"Hamilton"},{"article-title":"Graph attention networks","volume-title":"ICLR","author":"Velickovic","key":"ref3"},{"article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"ICLR","author":"Kipf","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DSW.2018.8439897"},{"key":"ref7","article-title":"Spectral-based graph convolutional network for directed graphs","volume":"1907.08990","author":"Ma","year":"2019"},{"key":"ref8","article-title":"Directed graph convolutional network","volume":"2004.13970","author":"Tong","year":"2020"},{"key":"ref9","article-title":"Digraph inception convolutional networks","author":"Tong","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","first-page":"27003","article-title":"Magnet: A neural network for directed graphs","author":"Zhang","year":"2021","journal-title":"NeurIPS"},{"article-title":"Holonets: Spectral convolutions do extend to directed graphs","volume-title":"ICLR","author":"Koke","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-10018-9_28"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF02101702"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref15","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume":"2312.00752","author":"Gu","year":"2023"},{"article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"ICLR","author":"Gu","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111279"},{"key":"ref18","first-page":"5449","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"ICML","volume":"80","author":"Xu"},{"article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","volume-title":"ICLR","author":"Klicpera","key":"ref19"},{"key":"ref20","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"ICML","volume":"119","author":"Chen"},{"key":"ref21","first-page":"1098","article-title":"Universal graph contrastive learning with a novel laplacian perturbation","volume-title":"UAI","volume":"216","author":"Ko"},{"key":"ref22","first-page":"11144","article-title":"Transformers meet directed graphs","volume-title":"ICML","volume":"202","author":"Geisler"},{"key":"ref23","article-title":"A generalization of transformer networks to graphs","volume":"2012.09699","author":"Dwivedi","year":"2020"},{"key":"ref24","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","author":"Kreuzer","year":"2021","journal-title":"NeurIPS"},{"key":"ref25","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"ICML","volume":"70","author":"Gilmer"},{"key":"ref26","article-title":"Demystify mamba in vision: A linear attention perspective","volume":"2405.16605","author":"Han","year":"2024"},{"key":"ref27","first-page":"472","article-title":"Incorporating second-order functional knowledge for better option pricing","volume-title":"NIPS","author":"Dugas"},{"key":"ref28","first-page":"12360","article-title":"Root mean square layer normalization","author":"Zhang","year":"2019","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref31","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"ICML","volume":"162","author":"Hua"},{"key":"ref32","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"ICML","volume":"97","author":"Wu"},{"article-title":"Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking","volume-title":"ICLR","author":"Bojchevski","key":"ref33"},{"key":"ref34","article-title":"Wiki-cs: A wikipedia-based benchmark for graph neural networks","volume":"2007.02901","author":"Mernyei","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-023-00790-4"},{"key":"ref36","first-page":"19580","article-title":"Directed graph contrastive learning","author":"Tong","year":"2021","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20682"},{"key":"ref38","first-page":"25","article-title":"Edge directionality improves learning on heterophilic graphs","volume-title":"LoG","volume":"231","author":"Rossi"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/3654621.3654623"},{"article-title":"DUPLEX: dual GAT for complex embedding of directed graphs","volume-title":"ICML","author":"Ke","key":"ref40"},{"article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","key":"ref41"},{"key":"ref42","first-page":"12","article-title":"Pytorch geometric signed directed: A software package on graph neural networks for signed and directed graphs","volume-title":"LoG","volume":"231","author":"He"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2017.01.004"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097148"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3316628"},{"key":"ref49","first-page":"2072","article-title":"Exploring the role of node diversity in directed graph representation learning","volume-title":"IJCAI","author":"Huang"},{"key":"ref50","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","key":"ref51"},{"key":"ref52","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","volume":"202","author":"Radford"},{"key":"ref53","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","author":"Ying","year":"2021","journal-title":"NeurIPS"},{"key":"ref54","article-title":"Directed graph transformers","volume":"2024","author":"Wang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref55","article-title":"Simplifying and empowering transformers for large-graph representations","author":"Wu","year":"2023","journal-title":"NeurIPS"},{"key":"ref56","article-title":"Nodeformer: A scalable graph structure learning transformer for node classification","author":"Wu","year":"2022","journal-title":"NeurIPS"},{"key":"ref57","first-page":"31613","article-title":"Exphormer: Sparse transformers for graphs","volume-title":"ICML","volume":"202","author":"Shirzad"},{"article-title":"Nagphormer: A tokenized graph transformer for node classification in large graphs","volume-title":"ICLR","author":"Chen","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672044"},{"key":"ref60","article-title":"Graph-mamba: Towards long-range graph sequence modeling with selective state spaces","volume":"2402.00789","author":"Wang","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229011.pdf?arnumber=11229011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:14:02Z","timestamp":1763190842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229011\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229011","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}