{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T18:08:28Z","timestamp":1778522908256,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Key Project of Regional Innovation and Development Joint Fund of National Natural Science Foundation of China","award":["U22A2025"],"award-info":[{"award-number":["U22A2025"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mobile Netw Appl"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Link prediction, which aims to infer missing edges or predict future edges based on currently observed graph connections, has emerged as a powerful technique for diverse applications such as recommendation, relation completion, etc. While there is rich literature on link prediction based on node representation learning, direct link embedding is relatively less studied and less understood. One common practice in previous work characterizes a link by manipulate the embeddings of its incident node pairs, which is not capable of capturing effective link features. Moreover, common link prediction methods such as random walks and graph auto-encoder usually rely on full-graph training, suffering from poor scalability and high resource consumption on large-scale graphs. In this paper, we propose Inductive Subgraph Embedding for Link Prediciton (SE4LP) \u2014 an end-to-end scalable representation learning framework for link prediction, which utilizes the strong correlation between central links and their neighborhood subgraphs to characterize links. We sample the \u201clink-centric induced subgraphs\u201d as input, with a subgraph-level contrastive discrimination as pretext task, to learn the intrinsic and structural link features via subgraph classification. Extensive experiments on five datasets demonstrate that SE4LP has significant superiority in link prediction in terms of performance and scalability, when compared with state-of-the-art methods. Moreover, further analysis demonstrate that introducing self-supervision in link prediction can significantly reduce the dependence on training data and improve the generalization and scalability of model.<\/jats:p>","DOI":"10.1007\/s11036-024-02339-3","type":"journal-article","created":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T06:10:00Z","timestamp":1730787000000},"page":"312-323","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Inductive Subgraph Embedding for Link Prediction"],"prefix":"10.1007","volume":"30","author":[{"given":"Jin","family":"Si","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanqing","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Xuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,5]]},"reference":[{"key":"2339_CR1","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th international conference on learning representations"},{"key":"2339_CR2","doi-asserted-by":"crossref","unstructured":"Gong S, Zhou J, Xie C, Xuan Q (2023) Neighborhood homophily-based graph convolutional network. In: Proceedings of the 32nd ACM international conference on information and knowledge management, pp 3908\u20133912","DOI":"10.1145\/3583780.3615195"},{"key":"2339_CR3","doi-asserted-by":"crossref","unstructured":"Bo D, Wang X, Shi C, Zhu M, Lu E, Cui P (2020) Structural deep clustering network. In: Proceedings of the web conference 2020, pp 1400\u20131410","DOI":"10.1145\/3366423.3380214"},{"issue":"1","key":"2339_CR4","first-page":"842","volume":"35","author":"J Zhou","year":"2021","unstructured":"Zhou J, Chen Z, Du M, Chen L, Yu S, Chen G, Xuan Q (2021) Robustecd: enhancement of network structure for robust community detection. IEEE Trans Knowl Data Eng 35(1):842\u2013856","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2339_CR5","unstructured":"Dai H, Dai B, Song L (2016) Discriminative embeddings of latent variable models for structured data. In: International conference on machine learning. PMLR, pp 2702\u20132711"},{"key":"2339_CR6","doi-asserted-by":"publisher","first-page":"3433","DOI":"10.1109\/TIFS.2022.3208471","volume":"17","author":"J Zhou","year":"2022","unstructured":"Zhou J, Hu C, Chi J, Wu J, Shen M, Xuan Q (2022) Behavior-aware account deanonymization on ethereum interaction graph. IEEE Trans Inf Forensics Secur 17:3433\u20133448","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"4","key":"2339_CR7","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1007\/s10994-021-06098-0","volume":"111","author":"L Pasa","year":"2022","unstructured":"Pasa L, Navarin N, Sperduti A (2022) Polynomial-based graph convolutional neural networks for graph classification. Mach Learn 111(4):1205\u20131237","journal-title":"Mach Learn"},{"key":"2339_CR8","doi-asserted-by":"crossref","unstructured":"Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International conference on knowledge discovery and data mining, pp 701\u2013710","DOI":"10.1145\/2623330.2623732"},{"key":"2339_CR9","doi-asserted-by":"crossref","unstructured":"Dileo M, Zignani M, Gaito S (2023) Temporal graph learning for dynamic link prediction with text in online social networks. Mach Learn, 1\u201320","DOI":"10.1007\/s10994-023-06475-x"},{"issue":"12","key":"2339_CR10","doi-asserted-by":"publisher","first-page":"5057","DOI":"10.1007\/s10994-023-06402-0","volume":"112","author":"A Moradan","year":"2023","unstructured":"Moradan A, Draganov A, Mottin D, Assent I (2023) Ucode: unified community detection with graph convolutional networks. Mach Learn 112(12):5057\u20135080","journal-title":"Mach Learn"},{"key":"2339_CR11","doi-asserted-by":"crossref","unstructured":"Subramonian A (2021) Motif-driven contrastive learning of graph representations. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 15980\u201315981","DOI":"10.1609\/aaai.v35i18.17986"},{"key":"2339_CR12","doi-asserted-by":"crossref","unstructured":"Hao J, Chen M, Yu W, Sun Y, Wang W (2019) Universal representation learning of knowledge bases by jointly embedding instances and ontological concepts. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery and data mining, pp 1709\u20131719","DOI":"10.1145\/3292500.3330838"},{"issue":"2","key":"2339_CR13","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/s10994-021-06044-0","volume":"111","author":"Y Pei","year":"2022","unstructured":"Pei Y, Huang T, Ipenburg W, Pechenizkiy M (2022) Resgcn: attention-based deep residual modeling for anomaly detection on attributed networks. Mach Learn 111(2):519\u2013541","journal-title":"Mach Learn"},{"issue":"3","key":"2339_CR14","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/S0378-8733(03)00009-1","volume":"25","author":"LA Adamic","year":"2003","unstructured":"Adamic LA, Adar E (2003) Friends and neighbors on the web. Soc Netw 25(3):211\u2013230","journal-title":"Soc Netw"},{"issue":"8","key":"2339_CR15","doi-asserted-by":"publisher","first-page":"1507","DOI":"10.1109\/TKDE.2018.2801854","volume":"30","author":"C Fu","year":"2018","unstructured":"Fu C, Zhao M, Fan L, Chen X, Chen J, Wu Z, Xia Y, Xuan Q (2018) Link weight prediction using supervised learning methods and its application to yelp layered network. IEEE Trans Knowl Data Eng 30(8):1507\u20131518","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"2339_CR16","first-page":"754","volume":"33","author":"S Yu","year":"2019","unstructured":"Yu S, Zhao M, Fu C, Zheng J, Huang H, Shu X, Xuan Q, Chen G (2019) Target defense against link-prediction-based attacks via evolutionary perturbations. IEEE Trans Knowl Data Eng 33(2):754\u2013767","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2339_CR17","doi-asserted-by":"crossref","unstructured":"Stoica G, Stretcu O, Platanios EA, Mitchell T, P\u00f3czos B (2020) Contextual parameter generation for knowledge graph link prediction. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 3000\u20133008","DOI":"10.1609\/aaai.v34i03.5693"},{"key":"2339_CR18","doi-asserted-by":"crossref","unstructured":"Yu S, Wu Y, Gan R, Zhou J, Zheng Z, Xuan Q (2022) Discover important paths in the knowledge graph based on dynamic relation confidence. In: China national conference on big data and social computing. Springer, pp 341\u2013358","DOI":"10.1007\/978-981-19-7532-5_22"},{"key":"2339_CR19","doi-asserted-by":"crossref","unstructured":"Grover A, Leskovec J (2016) node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 855\u2013864","DOI":"10.1145\/2939672.2939754"},{"key":"2339_CR20","unstructured":"Kipf TN, Welling M (2016) Variational graph auto-encoders. NIPS Workshop on Bayesian Deep Learning"},{"key":"2339_CR21","doi-asserted-by":"crossref","unstructured":"Pan S, Hu R, Long G, Jiang J, Yao L, Zhang C (2018) Adversarially regularized graph autoencoder for graph embedding. In: IJCAI International joint conference on artificial intelligence","DOI":"10.24963\/ijcai.2018\/362"},{"key":"2339_CR22","doi-asserted-by":"crossref","unstructured":"Qiu J, Dong Y, Ma H, Li J, Wang K, Tang J (2018) Network embedding as matrix factorization: unifying deepwalk, line, pte, and node2vec. In: Proceedings of the 11th ACM international conference on web search and data mining, pp 459\u2013467","DOI":"10.1145\/3159652.3159706"},{"key":"2339_CR23","doi-asserted-by":"crossref","unstructured":"Cao S, Lu W, Xu Q (2015) Grarep: learning graph representations with global structural information. In: Proceedings of the 24th ACM international on conference on information and knowledge management, pp 891\u2013900","DOI":"10.1145\/2806416.2806512"},{"key":"2339_CR24","unstructured":"Zhang M, Chen Y (2018) Link prediction based on graph neural networks. In: Proceedings of the 32nd international conference on neural information processing systems, vol 31, pp 5165\u20135175"},{"key":"2339_CR25","doi-asserted-by":"crossref","unstructured":"Jiao Y, Xiong Y, Zhang J, Zhang Y, Zhang T, Zhu Y (2020) Sub-graph contrast for scalable self-supervised graph representation learning. In: 2020 IEEE International conference on data mining (ICDM). IEEE, pp 222\u2013231","DOI":"10.1109\/ICDM50108.2020.00031"},{"key":"2339_CR26","unstructured":"Hamilton WL, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In: Proceedings of the 31st international conference on neural information processing systems, pp 1025\u20131035"},{"issue":"4","key":"2339_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3012704","volume":"49","author":"V Mart\u00ednez","year":"2016","unstructured":"Mart\u00ednez V, Berzal F, Cubero J-C (2016) A survey of link prediction in complex networks. ACM Comput Surv (CSUR) 49(4):1\u201333","journal-title":"ACM Comput Surv (CSUR)"},{"key":"2339_CR28","doi-asserted-by":"crossref","unstructured":"Sun H, Tian P, Xiong Y, Zhang Y, Xiang Y, Jia X, Wang H (2024) Dynamise: dynamic signed network embedding for link prediction. Mach Learn, 1\u201317","DOI":"10.1109\/DSAA60987.2023.10302493"},{"key":"2339_CR29","unstructured":"Veli\u010dkovi\u0107 P, Fedus W, Hamilton WL, Li\u00f2 P, Bengio Y, Hjelm RD (2019) Deep graph infomax. In: Proceedings of the 7th international conference on learning representations"},{"key":"2339_CR30","unstructured":"You Y, Chen T, Sui Y, Chen T, Wang Z, Shen Y (2020) Graph contrastive learning with augmentations, vol 33, pp 5812\u20135823"},{"key":"2339_CR31","unstructured":"Chen J, Ma T, Xiao C (2018) FastGCN: fast learning with graph convolutional networks via importance sampling. In: Proceedings of the 6th international conference on learning representations"},{"key":"2339_CR32","doi-asserted-by":"crossref","unstructured":"Chiang W-L, Liu X, Si S, Li Y, Bengio S, Hsieh C-J (2019) Cluster-gcn: an efficient algorithm for training deep and large graph convolutional networks. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery and data mining, pp 257\u2013266","DOI":"10.1145\/3292500.3330925"},{"key":"2339_CR33","unstructured":"Zeng H, Zhou H, Srivastava A, Kannan R, Prasanna V (2020) Graphsaint: graph sampling based inductive learning method. In: In Proceedings of the 8th international conference on learning representations"},{"key":"2339_CR34","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning. PMLR, pp 1597\u20131607"},{"key":"2339_CR35","doi-asserted-by":"crossref","unstructured":"Wang Y, Wang W, Liang Y, Cai Y, Liu J, Hooi B (2020) Nodeaug: semisupervised node classification with data augmentation. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery and data mining, pp 207\u2013217","DOI":"10.1145\/3394486.3403063"},{"key":"2339_CR36","doi-asserted-by":"crossref","unstructured":"Zhou J, Shen J, Yu S, Chen G, Xuan Q (2020) M-evolve: structural-mappingbased data augmentation for graph classification. IEEE Trans Netw Sci Eng 8(1):190\u2013200","DOI":"10.1109\/TNSE.2020.3032950"},{"key":"2339_CR37","doi-asserted-by":"crossref","unstructured":"Zhou J, Shen J, Xuan Q (2020) Data augmentation for graph classification. In: Proceedings of the 29th ACM international conference on information & knowledge management, pp 2341\u20132344","DOI":"10.1145\/3340531.3412086"},{"key":"2339_CR38","unstructured":"Zhou J, Xie C, Wen Z, Zhao X, Xuan Q (2022) Data augmentation on graphs: a survey. arXiv preprint arXiv:2212.09970"},{"key":"2339_CR39","unstructured":"Zhu Y, Xu Y, Yu F, Liu Q, Wu S, Wang L (2020) Deep graph contrastive representation learning. arXiv preprint arXiv:2006.04131"},{"key":"2339_CR40","doi-asserted-by":"crossref","unstructured":"Zhu Y, Xu Y, Yu F, Liu Q, Wu S, Wang L (2021) Graph contrastive learning with adaptive augmentation. In: Proceedings of the web conference 2021, pp 2069\u20132080","DOI":"10.1145\/3442381.3449802"},{"issue":"3","key":"2339_CR41","first-page":"93","volume":"29","author":"P Sen","year":"2008","unstructured":"Sen P, Namata G, Bilgic M, Getoor L, Galligher B, Eliassi-Rad T (2008) Collective classification in network data. AI Mag 29(3):93\u201393","journal-title":"AI Mag"},{"key":"2339_CR42","unstructured":"Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: International conference on machine learning. PMLR, pp 1188\u20131196"},{"issue":"6","key":"2339_CR43","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1016\/j.physa.2010.11.027","volume":"390","author":"L L\u00fc","year":"2011","unstructured":"L\u00fc L, Zhou T (2011) Link prediction in complex networks: a survey. Physica A: Stat Mech Appl 390(6):1150\u20131170","journal-title":"Physica A: Stat Mech Appl"},{"key":"2339_CR44","unstructured":"Xu K, Hu W, Leskovec J, Jegelka S (2018) How powerful are graph neural networks? In: Proceedings of the 6th international conference on learning representations"}],"container-title":["Mobile Networks and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11036-024-02339-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11036-024-02339-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11036-024-02339-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T01:42:43Z","timestamp":1760492563000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11036-024-02339-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,5]]},"references-count":44,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2339"],"URL":"https:\/\/doi.org\/10.1007\/s11036-024-02339-3","relation":{},"ISSN":["1383-469X","1572-8153"],"issn-type":[{"value":"1383-469X","type":"print"},{"value":"1572-8153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,5]]},"assertion":[{"value":"28 April 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}