{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T04:56:46Z","timestamp":1769403406381,"version":"3.49.0"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T00:00:00Z","timestamp":1668643200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:p>The network embedding task is to represent a node in a network as a low-dimensional vector while incorporating the topological and structural information. Most existing approaches solve this problem by factorizing a proximity matrix, either directly or implicitly. In this work, we introduce a network embedding method from a new perspective, which leverages Modern Hopfield Networks (MHN) for associative learning. Our network learns associations between the content of each node and that node's neighbors. These associations serve as memories in the MHN. The recurrent dynamics of the network make it possible to recover the masked node, given that node's neighbors. Our proposed method is evaluated on different benchmark datasets for downstream tasks such as node classification, link prediction, and graph coarsening. The results show competitive performance compared to the common matrix factorization techniques and deep learning based methods.<\/jats:p>","DOI":"10.3389\/fdata.2022.1044709","type":"journal-article","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T06:50:50Z","timestamp":1668667850000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Modern Hopfield Networks for graph embedding"],"prefix":"10.3389","volume":"5","author":[{"given":"Yuchen","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitry","family":"Krotov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed J.","family":"Zaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1530","DOI":"10.1103\/PhysRevLett.55.1530","article-title":"Storing infinite numbers of patterns in a spin-glass model of neural networks","volume":"55","author":"Amit","year":"1985","journal-title":"Phys. Rev. Lett"},{"key":"B2","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1080\/03081088508817681","article-title":"Eigenvalues of the laplacian of a graph","volume":"18","year":"1985","journal-title":"Linear Multilin. Algeb"},{"key":"B3","doi-asserted-by":"publisher","first-page":"i47","DOI":"10.1093\/bioinformatics\/bti1007","article-title":"Protein function prediction via graph kernels","volume":"21","author":"Borgwardt","year":"2005","journal-title":"Bioinformatics"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6203","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna","year":"2013","journal-title":"arXiv preprint arXiv:1312.6203"},{"key":"B5","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1145\/2806416.2806512","article-title":"\u201cGrarep: learning graph representations with global structural information,\u201d","volume-title":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","author":"Cao","year":"2015"},{"key":"B6","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11849","article-title":"\u201cHarp: hierarchical representation learning for networks,\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32","author":"Chen","year":"2018"},{"key":"B7","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1209\/0295-5075\/2\/4\/012","article-title":"Saturation level of the hopfield model for neural network","volume":"2","author":"Crisanti","year":"1986","journal-title":"Europhys. Lett"},{"key":"B8","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1021\/jm00106a046","article-title":"Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. correlation with molecular orbital energies and hydrophobicity","volume":"34","author":"Debnath","year":"1991","journal-title":"J. Med. Chem"},{"key":"B9","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1007\/s10955-017-1806-y","article-title":"On a model of associative memory with huge storage capacity","volume":"168","author":"Demircigil","year":"2017","journal-title":"J. Stat. Phys"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1944","DOI":"10.1109\/TPAMI.2007.1115","article-title":"Weighted graph cuts without eigenvectors a multilevel approach","volume":"29","author":"Dhillon","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B11","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1016\/S0022-2836(03)00628-4","article-title":"Distinguishing enzyme structures from non-enzymes without alignments","volume":"330","author":"Dobson","year":"2003","journal-title":"J. Mol. Biol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/TNN.2008.2005601","article-title":"Normalized mutual information feature selection","volume":"20","author":"Est\u00e9vez","year":"2009","journal-title":"IEEE Trans. Neural Netw"},{"key":"B13","first-page":"1871","article-title":"Liblinear: a library for large linear classification","volume":"9","author":"Fan","year":"2008","journal-title":"J. Mach. Learn. Res"},{"key":"B14","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/978-3-662-39778-7_10","article-title":"\u201cSingular value decomposition and least squares solutions,\u201d","author":"Golub","year":"1971","journal-title":"Linear Algebra"},{"key":"B15","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1145\/2939672.2939754","article-title":"\u201cnode2vec: scalable feature learning for networks,\u201d","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Grover","year":"2016"},{"key":"B16","first-page":"153","article-title":"Locality preserving projections","volume":"16","author":"He","year":"2004","journal-title":"Adv. Neural Inform. Process. Syst"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC53243.2021.00042","article-title":"\u201cDistmile: a distributed multi-level framework for scalable graph embedding,\u201d","author":"He","year":"2021","journal-title":"2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC)"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.05163","article-title":"Deep convolutional networks on graph-structured data (2015)","author":"Henaff","year":"2015","journal-title":"arXiv preprint arXiv:1506.05163"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1201\/9780429499661","author":"Hertz","year":"2018","journal-title":"Introduction to the Theory of Neural Computation"},{"key":"B20","first-page":"459","article-title":"\u201cMultidimensional scaling and data clustering,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Hofmann","year":"1995"},{"key":"B21","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/0378-8733(83)90021-7","article-title":"Stochastic blockmodels: first steps","volume":"5","author":"Holland","year":"1983","journal-title":"Soc. Netw"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2554","DOI":"10.1073\/pnas.79.8.2554","article-title":"Neural networks and physical systems with emergent collective computational abilities","volume":"79","author":"Hopfield","year":"1982","journal-title":"Proc. Natl. Acad. Sci. U.S.A"},{"key":"B23","doi-asserted-by":"publisher","first-page":"3088","DOI":"10.1073\/pnas.81.10.3088","article-title":"Neurons with graded response have collective computational properties like those of two-state neurons","volume":"81","author":"Hopfield","year":"1984","journal-title":"Proc. Natl. Acad. Sci. U.S.A"},{"key":"B24","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.neucom.2015.07.128","article-title":"Dimensionality reduction on anchorgraph with an efficient locality preserving projection","volume":"187","author":"Jiang","year":"2016","journal-title":"Neurocomputing"},{"key":"B25","first-page":"4452","article-title":"\u201cGraph coarsening with preserved spectral properties,\u201d","author":"Jin","year":"2020","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1137\/S1064827595287997","article-title":"A fast and high quality multilevel scheme for partitioning irregular graphs","volume":"20","author":"Karypis","year":"1998","journal-title":"SIAM J. Sci. Comput"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.02907","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv preprint arXiv:1609.02907"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.06446","article-title":"Hierarchical associative memory","author":"Krotov","year":"2021","journal-title":"arXiv preprint arXiv:2107.06446"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2008.06996","article-title":"Large associative memory problem in neurobiology and machine learning","author":"Krotov","year":"2020","journal-title":"arXiv preprint arXiv:2008.06996"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.01164","article-title":"Dense associative memory for pattern recognition","author":"Krotov","year":"2016","journal-title":"arXiv preprint arXiv:1606.01164"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v15i1.18067","article-title":"\u201cMile: a multi-level framework for scalable graph embedding,\u201d","author":"Liang","year":"2021","journal-title":"Proceedings of the International AAAI Conference on Web and Social Media, Vol. 15"},{"key":"B32","first-page":"1","article-title":"Graph reduction with spectral and cut guarantees","volume":"20","author":"Loukas","year":"2019","journal-title":"J. Mach. Learn. Res"},{"key":"B33","unstructured":"MahoneyM.\n          Large Text Compression Benchmark2011"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1301.3781","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"","journal-title":"arXiv preprint arXiv:1301.3781"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"","journal-title":"arXiv preprint arXiv:1310.4546"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2007.08663","article-title":"Tudataset: a collection of benchmark datasets for learning with graphs","author":"Morris","year":"2020","journal-title":"arXiv preprint arXiv:2007.08663"},{"key":"B37","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1145\/2939672.2939751","article-title":"\u201cAsymmetric transitivity preserving graph embedding,\u201d","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Ou","year":"2016"},{"key":"B38","doi-asserted-by":"publisher","first-page":"D529","DOI":"10.1093\/nar\/gky1079","article-title":"The biogrid interaction database: 2019 update","volume":"47","author":"Oughtred","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"B39","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1145\/2623330.2623732","article-title":"\u201cDeepwalk: online learning of social representations,\u201d","volume-title":"Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Perozzi","year":"2014"},{"key":"B40","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1145\/3159652.3159706","article-title":"\u201cNetwork embedding as matrix factorization: unifying deepwalk, line, pte, and node2vec,\u201d","volume-title":"Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining","author":"Qiu","year":"2018"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2008.02217","article-title":"Hopfield networks is all you need","author":"Ramsauer","year":"2020","journal-title":"arXiv preprint arXiv:2008.02217"},{"key":"B42","unstructured":"RezaZ.\n            HuanL.\n          Social Computing Data Repository2009"},{"key":"B43","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9277","article-title":"\u201cThe network data repository with interactive graph analytics and visualization,\u201d","volume-title":"AAAI","author":"Rossi","year":"2015"},{"key":"B44","first-page":"1165","article-title":"\u201cPte: Predictive text embedding through large-scale heterogeneous text networks,\u201d","volume-title":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Tang","year":""},{"key":"B45","first-page":"1067","article-title":"\u201cLine: large-scale information network embedding,\u201d","volume-title":"Proceedings of the 24th International Conference on World Wide Web","author":"Tang","year":""},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v28i1.8916","article-title":"\u201cLearning deep representations for graph clustering,\u201d","volume-title":"Proceedings of the AAAI Confernce on Artificial Intelligence, Vol. 28","author":"Tian","year":"2014"},{"key":"B47","doi-asserted-by":"publisher","first-page":"061910","DOI":"10.1103\/PhysRevE.66.061910","article-title":"Storage capacity of attractor neural networks with depressing synapses","volume":"66","author":"Torres","year":"2002","journal-title":"Phys. Rev. E"},{"key":"B48","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1145\/3219819.3219991","article-title":"\u201cNetlsd: hearing the shape of a graph,\u201d","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Tsitsulin","year":"2018"},{"key":"B49","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","article-title":"A tutorial on spectral clustering","volume":"17","author":"Von Luxburg","year":"2007","journal-title":"Stat. Comput"},{"key":"B50","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/s10115-007-0103-5","article-title":"Comparison of descriptor spaces for chemical compound retrieval and classification","volume":"14","author":"Wale","year":"2008","journal-title":"Knowl. Inform. Syst"},{"key":"B51","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1145\/2939672.2939753","article-title":"\u201cStructural deep network embedding,\u201d","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Wang","year":"2016"},{"key":"B52","first-page":"2111","article-title":"\u201cNetwork representation learning with rich text information,\u201d","volume-title":"IJCAI, Vol. 2015","author":"Yang","year":"2015"},{"key":"B53","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1137\/1.9781611976700.19","article-title":"\u201cNode proximity is all you need: unified structural and positional node and graph embedding,\u201d","author":"Zhu","year":"2021","journal-title":"Proceedings of the 2021 SIAM International Conference on Data Mining (SDM)"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2022.1044709\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T06:51:16Z","timestamp":1668667876000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2022.1044709\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,17]]},"references-count":53,"alternative-id":["10.3389\/fdata.2022.1044709"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2022.1044709","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,17]]},"article-number":"1044709"}}