ABSTRACT
Link prediction is one of the most essential tasks in data mining. A lot of studies have shown great progress in homogeneous graph. However, besides recommendation system and knowledge graph, little research solves the problem of link prediction in heterogeneous graphs. The main cause behind the failure of link prediction in heterogeneous graphs is that the way of connecting nodes is different from that in homogeneous graphs. In this article, we come up with a new model, Pro-SEAL, since it originates from SEAL. We notice that original labeling trick only takes distance into consideration, ignoring that different kinds of nodes with same distance may contribute to varying degrees. With this in mind, we design a novel labeling trick and make improvement in the final GNN learning structure. We take both ground-truth label and distance into account since they both matter when edges link. It expands framework of graph neural network(GNN) in link prediction and enables it to better adapt to heterogeneous graph for the first time. Extensive experiments on eight real-world datasets show that our model has obtained great results compared with some classic and advanced model.
- Sergi Abadal, Akshay Jain, Robert Guirado, Jorge López-Alonso, and Eduard Alarcón. 2021. Computing Graph Neural Networks: A Survey from Algorithms to Accelerators. arxiv:2010.00130 [cs, stat]Google Scholar
- Lada A Adamic and Eytan Adar. 2003. Friends and Neighbors on the Web. Social Networks 25, 3 (July 2003), 211–230. https://doi.org/10.1016/S0378-8733(03)00009-1Google ScholarCross Ref
- Gonen Ashkenasy, Reshma Jagasia, Maneesh Yadav, and M Reza Ghadiri. 2004. Design of a directed molecular network. Proceedings of the National Academy of Sciences 101, 30 (2004), 10872–10877.Google ScholarCross Ref
- Hongxu Chen, Hongzhi Yin, Weiqing Wang, Hao Wang, Quoc Viet Hung Nguyen, and Xue Li. 2018. PME: projected metric embedding on heterogeneous networks for link prediction. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 1177–1186.Google ScholarDigital Library
- Gobinda G Chowdhury. 2010. Introduction to modern information retrieval. Facet publishing.Google ScholarDigital Library
- Yuxiao Dong, Ziniu Hu, Kuansan Wang, Yizhou Sun, and Jie Tang. 2020. Heterogeneous Network Representation Learning.. In IJCAI, Vol. 20. 4861–4867.Google Scholar
- Yuxiao Dong, Jie Tang, Sen Wu, Jilei Tian, Nitesh V Chawla, Jinghai Rao, and Huanhuan Cao. 2012. Link prediction and recommendation across heterogeneous social networks. In 2012 IEEE 12th International conference on data mining. IEEE, 181–190.Google ScholarDigital Library
- Johannes Gasteiger, Aleksandar Bojchevski, and Stephan Günnemann. 2022. Predict Then Propagate: Graph Neural Networks Meet Personalized PageRank. arxiv:1810.05997 [cs, stat]Google Scholar
- Aditya Grover and Jure Leskovec. 2016. Node2vec: Scalable Feature Learning for Networks. arxiv:1607.00653 [cs, stat]Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017).Google Scholar
- Mohammad Al Hasan and Mohammed J. Zaki. 2011. A Survey of Link Prediction in Social Networks. In Social Network Data Analytics, Charu C. Aggarwal (Ed.). Springer US, Boston, MA, 243–275. https://doi.org/10.1007/978-1-4419-8462-3_9Google ScholarCross Ref
- Ivan Herman, Guy Melançon, and M Scott Marshall. 2000. Graph Visualization and Navigation in Information Visualization: A Survey. IEEE Transactions on visualization and computer graphics 6, 1 (2000), 24–43.Google ScholarDigital Library
- Paul Jaccard. 1901. Étude comparative de la distribution florale dans une portion des Alpes et des Jura. Bull Soc Vaudoise Sci Nat 37 (1901), 547–579.Google Scholar
- Leo Katz. 1953. A New Status Index Derived from Sociometric Analysis. Psychometrika 18, 1 (March 1953), 39–43. https://doi.org/10.1007/BF02289026Google ScholarCross Ref
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Thomas N. Kipf and Max Welling. 2016. Variational Graph Auto-Encoders. arxiv:1611.07308 [cs, stat]Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. arxiv:1609.02907 [cs, stat]Google Scholar
- Ajay Kumar, Shashank Sheshar Singh, Kuldeep Singh, and Bhaskar Biswas. 2020. Link Prediction Techniques, Applications, and Performance: A Survey. Physica A: Statistical Mechanics and its Applications 553 (2020), 124289.Google Scholar
- Huijia Li, Wenzhe Xu, Chenyang Qiu, and Jian Pei. 2022. Fast Markov Clustering Algorithm Based on Belief Dynamics. IEEE Transactions on Cybernetics (2022), 1–10. https://doi.org/10.1109/TCYB.2022.3141598Google ScholarCross Ref
- Pan Li, Yanbang Wang, Hongwei Wang, and Jure Leskovec. 2020. Distance encoding–design provably more powerful gnns for structural representation learning. arXiv preprint arXiv:2009.00142 (2020).Google Scholar
- Derek Lim, Felix Hohne, Xiuyu Li, Sijia Linda Huang, Vaishnavi Gupta, Omkar Bhalerao, and Ser-Nam Lim. 2021. Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods. https://doi.org/10.48550/arXiv.2110.14446 arxiv:2110.14446 [cs, stat]Google ScholarCross Ref
- Francois Lorrain and Harrison C White. 1971. Structural equivalence of individuals in social networks. The Journal of mathematical sociology 1, 1 (1971), 49–80.Google ScholarCross Ref
- Mark EJ Newman. 2003. The structure and function of complex networks. SIAM review 45, 2 (2003), 167–256.Google Scholar
- M. E. J. Newman. 2001. Clustering and Preferential Attachment in Growing Networks. Physical Review E 64, 2 (July 2001), 025102. https://doi.org/10.1103/PhysRevE.64.025102 arxiv:cond-mat/0104209Google ScholarCross Ref
- Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, and Wenwu Zhu. 2016. Asymmetric Transitivity Preserving Graph Embedding. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, San Francisco California USA, 1105–1114. https://doi.org/10.1145/2939672.2939751Google ScholarDigital Library
- Shirui Pan, Ruiqi Hu, Guodong Long, Jing Jiang, Lina Yao, and Chengqi Zhang. 2019. Adversarially Regularized Graph Autoencoder for Graph Embedding. arxiv:1802.04407 [cs, stat]Google Scholar
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. DeepWalk: Online Learning of Social Representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 701–710. https://doi.org/10.1145/2623330.2623732 arxiv:1403.6652 [cs]Google ScholarDigital Library
- Chenyang Qiu, Yingsheng Geng, Junrui Lu, Kaida Chen, Shitong Zhu, Ya Su, Guoshun Nan, Can Zhang, Junsong Fu, Qimei Cui, and Xiaofeng Tao. 2023. 3D-IDS: Doubly Disentangled Dynamic Intrusion Detection. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD’ 23). Association for Computing Machinery, 1–13. https://doi.org/10.1145/3580305.3599238Google ScholarDigital Library
- Chenyang Qiu, Zhaoci Huang, Wenzhe Xu, and Huijia Li. 2022. Fast Community Detection based on Graph Autoencoder Reconstruction. In 2022 7th International Conference on Big Data Analytics (ICBDA). IEEE, 265–271.Google ScholarCross Ref
- Chenyang Qiu, Zhaoci Huang, Wenzhe Xu, and Huijia Li. 2022. VGAER: graph neural network reconstruction based community detection. AAAI’22 DLG (2022).Google Scholar
- Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, and Jie Tang. 2018. Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and Node2vec. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining. ACM, Marina Del Rey CA USA, 459–467. https://doi.org/10.1145/3159652.3159706Google ScholarDigital Library
- Erzsébet Ravasz, Anna Lisa Somera, Dale A Mongru, Zoltán N Oltvai, and A-L Barabási. 2002. Hierarchical organization of modularity in metabolic networks. science 297, 5586 (2002), 1551–1555.Google Scholar
- Sam T Roweis and Lawrence K Saul. 2000. Nonlinear dimensionality reduction by locally linear embedding. science 290, 5500 (2000), 2323–2326.Google Scholar
- Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE transactions on neural networks 20, 1 (2008), 61–80.Google Scholar
- Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2017. Modeling Relational Data with Graph Convolutional Networks. arxiv:1703.06103 [cs, stat]Google Scholar
- Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective Classification in Network Data. AI magazine 29, 3 (2008), 93–93.Google Scholar
- Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. 2015. LINE: Large-scale Information Network Embedding. In Proceedings of the 24th International Conference on World Wide Web. 1067–1077. https://doi.org/10.1145/2736277.2741093 arxiv:1503.03578 [cs]Google ScholarDigital Library
- Komal Teru, Etienne Denis, and Will Hamilton. 2020. Inductive relation prediction by subgraph reasoning. In International Conference on Machine Learning. PMLR, 9448–9457.Google Scholar
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. arxiv:1710.10903 [cs, stat]Google Scholar
- Xiao Wang, Deyu Bo, Chuan Shi, Shaohua Fan, Yanfang Ye, and S Yu Philip. 2022. A survey on heterogeneous graph embedding: methods, techniques, applications and sources. IEEE Transactions on Big Data (2022).Google Scholar
- Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, and Shiqiang Yang. 2017. Community Preserving Network Embedding. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31.Google ScholarCross Ref
- Jiaxuan You, Jonathan M Gomes-Selman, Rex Ying, and Jure Leskovec. 2021. Identity-aware graph neural networks. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 10737–10745.Google ScholarCross Ref
- Muhan Zhang and Yixin Chen. [n.d.]. Link Prediction Based on Graph Neural Networks. ([n. d.]).Google Scholar
- Muhan Zhang and Yixin Chen. 2019. Inductive matrix completion based on graph neural networks. arXiv preprint arXiv:1904.12058 (2019).Google Scholar
- Muhan Zhang, Zhicheng Cui, Marion Neumann, and Yixin Chen. 2018. An end-to-end deep learning architecture for graph classification. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32.Google ScholarCross Ref
- Muhan Zhang, Pan Li, Yinglong Xia, Kai Wang, and Long Jin. [n.d.]. Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning. ([n. d.]).Google Scholar
- Shijie Zhou, Zhimeng Guo, Charu Aggarwal, Xiang Zhang, and Suhang Wang. 2022. Link Prediction on Heterophilic Graphs via Disentangled Representation Learning. arXiv preprint arXiv:2208.01820 (2022).Google Scholar
- Tao Zhou, Linyuan Lu, and Yi-Cheng Zhang. 2009. Predicting Missing Links via Local Information. The European Physical Journal B 71, 4 (Oct. 2009), 623–630. https://doi.org/10.1140/EPJB/E2009-00335-8 arxiv:0901.0553 [physics]Google ScholarCross Ref
- Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. 2020. Beyond homophily in graph neural networks: Current limitations and effective designs. Advances in Neural Information Processing Systems 33 (2020), 7793–7804.Google Scholar
Index Terms
- How ground-truth label helps link prediction in heterogeneous graphs
Recommendations
Neighborhood overlap-aware heterogeneous hypergraph neural network for link prediction
Highlights- We introduce graph structural information learned from overlapped neighbors to maintain graph topology, thus assisting in link prediction.
- We propose NOH that uses a heterogeneous hypergraph variational autoencoder to learn latent node ...
AbstractIn real world, a large number of networks are heterogeneous, containing different types of semantics and connections. Existing studies typically only consider lower-order pairwise relations rather than higher-order group interactions. Furthermore,...
NHP: Neural Hypergraph Link Prediction
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge ManagementLink prediction insimple graphs is a fundamental problem in which new links between vertices are predicted based on the observed structure of the graph. However, in many real-world applications, there is a need to model relationships among vertices that ...
Fine-Grained Semantics-Aware Heterogeneous Graph Neural Networks
Web Information Systems Engineering – WISE 2020AbstractDesigning a graph neural network for heterogeneous graph which contains different types of nodes and links have attracted increasing attention in recent years. Most existing methods leverage meta-paths to capture the rich semantics in ...
Comments