{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:18:09Z","timestamp":1778545089090,"version":"3.51.4"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Netw Sci"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>With real-world network systems typically comprising a large number of interactive components and inherently dynamic, Graph Continual Learning (GCL) has gained increasing popularity in recent years. Furthermore, most applications involve multiple entities and relationships with associated attributes, which has led to widely adopting Heterogeneous Information Networks (HINs) for capturing such rich structural and semantic meaning. In this context, we deal with the problem of learning multi-type node representations in a time evolving graph setting, harnessing the expressive power of Graph Neural Networks (GNNs). To this purpose, we propose a novel framework, named DyHANE\u2014Dynamic Heterogeneous Attributed\u00a0Network Embedding, which dynamically identifies a representative sample of multi-typed nodes as training set and updates the parameters of a GNN module, enabling the generation of up-to-date representations for all nodes in the network. We show the advantage of employing HINs on a data-incremental classification task. We compare the results obtained by DyHANE on a multi-step, incremental heterogeneous GAT model trained on a sample of changed and unchanged nodes, with the results obtained by either the same model trained from scratch or the same model trained solely on changed nodes. We demonstrate the effectiveness of the proposed approach in facing two major related challenges: (i) to avoid model re-train from scratch if only a subset of the network has been changed and (ii) to mitigate the risk of losing established patterns if the new nodes exhibit unseen properties. To the best of our knowledge, this is the first work that deals with the task of (deep) graph continual learning on HINs.<\/jats:p>","DOI":"10.1007\/s41109-024-00633-3","type":"journal-article","created":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T11:01:58Z","timestamp":1720177318000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["DyHANE: dynamic heterogeneous attributed network embedding through experience node replay"],"prefix":"10.1007","volume":"9","author":[{"given":"Liliana","family":"Martirano","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dino","family":"Ienco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Interdonato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Tagarelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,5]]},"reference":[{"key":"633_CR1","unstructured":"Brody S, Alon U, Yahav E (2021) How attentive are graph attention networks? CoRR. arXiv:2105.14491"},{"key":"633_CR2","unstructured":"Chen J, Ma T, Xiao C (2018) Fastgcn: fast learning with graph convolutional networks via importance sampling. CoRR arXiv:1801.10247"},{"key":"633_CR3","doi-asserted-by":"crossref","unstructured":"Dong Y, Chawla NV, Swami A (2017) etapath2vec: 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":"633_CR4","doi-asserted-by":"crossref","unstructured":"Du L, Wang Y, Song G, Lu Z, Wang J (2018) Dynamic network embedding: an extended approach for skip-gram based network embedding. In: IJCAI, vol. 2018, pp 2086\u20132092","DOI":"10.24963\/ijcai.2018\/288"},{"key":"633_CR5","doi-asserted-by":"publisher","unstructured":"Khoshraftar S, An A (2022) A survey on graph representation learning methods. CoRR. https:\/\/doi.org\/10.48550\/arXiv.2204.01855","DOI":"10.48550\/arXiv.2204.01855"},{"key":"633_CR6","unstructured":"Kingma DP, Ba J (2017) Adam: a method for stochastic optimization. CoRR. arXiv:1412.6980"},{"key":"633_CR7","doi-asserted-by":"crossref","unstructured":"Kirkpatrick J, Pascanu R, Rabinowitz NC, Veness J, Desjardins G, Rusu AA, Milan K, Quan J, Ramalho T, Grabska-Barwinska A, Hassabis D, Clopath C, Kumaran D, Hadsell R (2016) Overcoming catastrophic forgetting in neural networks. CoRR arXiv:1612.00796","DOI":"10.1073\/pnas.1611835114"},{"key":"633_CR8","doi-asserted-by":"crossref","unstructured":"Ma Y, Guo Z, Ren Z, Tang J, Yin D (2020) Streaming raph neural networks. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, pp 719\u2013728","DOI":"10.1145\/3397271.3401092"},{"issue":"1","key":"633_CR9","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/S41109-022-00504-9","volume":"7","author":"L Martirano","year":"2022","unstructured":"Martirano L, Zangari L, Tagarelli A (2022) Co-mlhan: contrastive learning for multilayer heterogeneous attributed networks. Appl Netw Sci 7(1):65. https:\/\/doi.org\/10.1007\/S41109-022-00504-9","journal-title":"Appl Netw Sci"},{"key":"633_CR10","doi-asserted-by":"publisher","unstructured":"McCloskey M, Cohen NJ (1989). Catastrophic interference in connectionist networks: The sequential learning problem. In: Psychology of learning and motivation, Academic Press, vol. 24, pp 109\u2013165. https:\/\/doi.org\/10.1016\/S0079-7421(08)60536-8","DOI":"10.1016\/S0079-7421(08)60536-8"},{"issue":"11","key":"633_CR11","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1080\/14786440109462720","volume":"2","author":"K Pearson","year":"1901","unstructured":"Pearson K (1901) Liii. On lines and planes of closest fit to systems of points in space. Lond Edinb Dublin Philos Mag J Sci 2(11):559\u2013572","journal-title":"Lond Edinb Dublin Philos Mag J Sci"},{"issue":"3","key":"633_CR12","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1109\/TC.2021.3057082","volume":"71","author":"H Peng","year":"2022","unstructured":"Peng H, Yang R, Wang Z, Li J, He L, Yu PS, Zomaya AY, Ranjan R (2022) Lime: low-cost and incremental learning for dynamic heterogeneous information networks. IEEE Trans Comput 71(3):628\u2013642. https:\/\/doi.org\/10.1109\/TC.2021.3057082","journal-title":"IEEE Trans Comput"},{"key":"633_CR13","doi-asserted-by":"crossref","unstructured":"Perini M, Ramponi G, Carbone P, Kalavri V (2022) Learning on streaming graphs with experience replay. In: Proceedings of the 37th ACM\/SIGAPP symposium on applied computing, pp 470\u2013478","DOI":"10.1145\/3477314.3507113"},{"key":"633_CR14","doi-asserted-by":"publisher","unstructured":"Priem J, Piwowar HA, Orr R (2022) Openalex: a fully-open index of scholarly works, authors, venues, institutions, and concepts. CoRR. https:\/\/doi.org\/10.48550\/ARXIV.2205.01833","DOI":"10.48550\/ARXIV.2205.01833"},{"key":"633_CR15","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-bert: sentence embeddings using siamese bert-networks. CoRR. arXiv:1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"633_CR16","unstructured":"Shang J, Qu M, Liu J, Kaplan LM, Han J, Peng J (2016) Meta-path guided embedding for similarity search in large-scale heterogeneous information networks. CoRR arXiv:1610.09769"},{"key":"633_CR17","doi-asserted-by":"crossref","unstructured":"Shen Z, Ma H, Wang K (2018) web-scale system for scientific knowledge exploration. CoRR. arXiv:1805.12216","DOI":"10.18653\/v1\/P18-4015"},{"key":"633_CR18","doi-asserted-by":"crossref","unstructured":"Shi B, Weninger, T (2014)ining interesting meta-paths from complex heterogeneous information networks. In: 2014 IEEE international conference on data mining workshop, IEEE, pp 488\u2013495","DOI":"10.1109\/ICDMW.2014.25"},{"key":"633_CR19","unstructured":"Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. CoRR. arXiv:1703.01365"},{"key":"633_CR20","unstructured":"Trivedi R, Farajtabar M, Biswal P, Zha H (2019) Dyrep: learning representations over dynamic graphs. In: International conference on learning representations"},{"key":"633_CR21","doi-asserted-by":"crossref","unstructured":"Wan G, Du B, Pan S, Haffari G(2020) einforcement learning based meta-path discovery in large-scale heterogeneous information networks. In: Proceedings of the Aaai conference on artificial intelligence, vol. 34, pp 6094\u20136101","DOI":"10.1609\/aaai.v34i04.6073"},{"key":"633_CR22","doi-asserted-by":"crossref","unstructured":"Wang J, Song G, Wu Y, Wang L (2020) Streaming graph neural networks via continual learning. CoRR arXiv:2009.10951","DOI":"10.1145\/3340531.3411963"},{"key":"633_CR23","doi-asserted-by":"crossref","unstructured":"Wang J, Zhu W, Song G, Wang L (2022) Streaming graph neural networks with generative replay. In: Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, pp 1878\u20131888","DOI":"10.1145\/3534678.3539336"},{"key":"633_CR24","unstructured":"Wei X, Liu Z, Sun L, Yu, PS (2018) Unsupervised meta-path reduction on heterogeneous information networks. arXiv preprint arXiv:1810.12503"},{"key":"633_CR25","doi-asserted-by":"crossref","unstructured":"Xie Y, Ou Z, Chen L, Liu Y, Xu K, Yang C, Zheng Z (2021) Learning and updating node embedding on dynamic heterogeneous information network. In: Proceedings of the 14th ACM international conference on web search and data mining, pp 184\u2013192","DOI":"10.1145\/3437963.3441745"},{"key":"633_CR26","doi-asserted-by":"crossref","unstructured":"Xue H, Yang L, Jiang W, Wei Y, Hu Y, Lin Y (2020) Modeling dynamic heterogeneous network for link prediction using hierarchical attention with temporal RNN. CoRR arXiv:2004.01024","DOI":"10.1007\/978-3-030-67658-2_17"},{"key":"633_CR27","doi-asserted-by":"crossref","unstructured":"Yang L, Xiao Z, Jiang W, Wei Y, Hu Y, Wang H (2020) Dynamic heterogeneous graph embedding using hierarchical attentions. In: Advances in information retrieval: 42nd European conference on IR research, ECIR 2020, Lisbon, Portugal, April 14\u201317, 2020, Proceedings, Part II 42, Springer, pp 425\u2013432","DOI":"10.1007\/978-3-030-45442-5_53"},{"key":"633_CR28","doi-asserted-by":"crossref","unstructured":"Zhou F, Cao C (2021) Overcoming catastrophic forgetting in graph neural networks with experience replay. In: Proceedings of the AAAI conference on artificial intelligence, vol. 35, pp 4714\u20134722","DOI":"10.1609\/aaai.v35i5.16602"},{"key":"633_CR29","unstructured":"Zhou F, Xu X, Li C, Trajcevski G, Zhong T, Zhang K (2020) A heterogeneous dynamical graph neural networks approach to quantify scientific impact. CoRR arXiv:2003.12042"}],"container-title":["Applied Network Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41109-024-00633-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41109-024-00633-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41109-024-00633-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T11:34:34Z","timestamp":1720179274000},"score":1,"resource":{"primary":{"URL":"https:\/\/appliednetsci.springeropen.com\/articles\/10.1007\/s41109-024-00633-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,5]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["633"],"URL":"https:\/\/doi.org\/10.1007\/s41109-024-00633-3","relation":{},"ISSN":["2364-8228"],"issn-type":[{"value":"2364-8228","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,5]]},"assertion":[{"value":"18 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No ethical concerns apply.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors provide their consent for publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interest and no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter discussed in this manuscript.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"30"}}