ABSTRACT
Network representation learning is a technique that embeds the nodes in a network into a low-dimensional vector space, providing strong support for network analysis tasks such as node classification, link prediction, and community detection. This paper provides a summary of the research in the field of network representation learning in recent years. Firstly, the definition of network representation learning is introduced. Then, traditional network representation learning methods are presented, including matrix factorization-based methods, random walk-based methods, and neural network-based methods. However, traditional network representation learning methods can only be applicable to the traditional networks abstracted as the graphs and not applicable to the hypernetworks abstracted as the hypergraphs. Therefore, this paper also introduces hypernetwork representation learning methods, including homogeneous hypernetwork representation learning and heterogeneous hypernetwork representation learning. Finally, this paper summarizes future research directions in network representation learning.
- Zhu Y, Ye Z L, Zhao H X, Zhang K. Text-enhanced network representation learning [J]. Frontiers of Computer Science, 2020, 14(6): 146322.Google ScholarDigital Library
- Halevy N, Kalish Y. Broadening versus deepening: gender and brokering in social networks [J]. Social Psychological and Personality Science, 2022, 13(2): 618-625.Google ScholarCross Ref
- Toth I, Lazar Z I, Varga L, Jarai-Szabo F, Papp I, Florian R V, Ercsey-Ravasz M. Mitigating ageing bias in article level metrics using citation network analysis [J]. Journal of Informetrics, 2021, 15(1): 101105.Google ScholarCross Ref
- Zarbakhshnia N, Soleimani H, Goh M, Razavi S S. A novel multi-objective model for green forward and reverse logistics network design [J]. Journal of Cleaner Production, 2019, 208: 1304-1316.Google ScholarCross Ref
- Somolinos FJ, León C, Guerrero-Aspizua S. Drug repurposing using biological networks [J]. Processes, 2021, 9(6):1057.Google ScholarCross Ref
- Hong X B, Zhang T, Cui Z, Yang J. Variational gridded graph convolution network for node classification [J]. IEEE/CAA Journal of Automatica Sinica, 2021, 8(10): 1697-1708.Google ScholarCross Ref
- Wang J, Liu J, Zhao G S. Dynamic link prediction method of task and user in mobile crowd sensing [J]. Computer Communications, 2022, 189: 110-119.Google ScholarDigital Library
- Liu Z G, Yuan G X, Luo X. Symmetry and nonnegativity-constrained matrix factorization for community detection [J]. IEEE/CAA Journal of Automatica Sinica, 2022, 9(9):1691-1693.Google ScholarCross Ref
- Cen Y K, Zou X, Zhang J W, Yang H X, Zhou J R, Tang J. Representation learning for attributed multiplex heterogeneous network [C]. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2019, 1358-1368.Google ScholarDigital Library
- Mikolov T, Sutskever I, Chen K, Corrado G, Dean J. Distributed representations of words and phrases and their compositionality [C]. In Proceedings of the 26th International Conference on Neural Information Processing Systems, 2013, 3111-3119.Google ScholarDigital Library
- Perozzi B, Alrfou R, Skiena S. Deepwalk: online learning of social representations [C]. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014, 701-710.Google ScholarDigital Library
- Tang J, Qu M, Wang M Z, Zhang M, Yan J, Mei Q Z. Line: large-scale information network embedding [C]. In Proceedings of the 24th International World Wide Web Conference, 2015, 1067-1077.Google ScholarDigital Library
- Grover A, Leskovec J. Node2vec: scalable feature learning for networks [C]. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, 855-864.Google ScholarDigital Library
- Yang C, Liu Z Y, Zhao D L, Sun M S, Chang E Y. Network representation learning with rich text information [C]. In Proceedings of the 24th International Joint Conference on Artificial Intelligence, 2015, 2111-2117.Google ScholarDigital Library
- Tu C C, Zeng X K, Wang H, Zhang Z Y, Liu Z Y, Sun M S, Zhang B, Lin L Y. A unified framework for community detection and network representation learning [J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(6): 1051-1065.Google ScholarCross Ref
- Pan S R, Wu J, Zhu X Q, Zhang C Q, Wang Y. Tri-party deep network representation [C]. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, 2016, 1895-1901.Google Scholar
- Gao H C, Huang H. Deep attributed network embedding [C]. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018, 3364-3370.Google ScholarDigital Library
- Tang J, Qu M, Mei Q Z. PTE: predictive text embedding through large-scale heterogeneous text networks [C]. In Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015, 1165-1174.Google ScholarDigital Library
- Dong Y X, Chawla N V, Swami A. Metapath2vec: scalable representation learning for heterogeneous networks [C]. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2017, 135-144.Google ScholarDigital Library
- Shi C, Hu B B, Zhao W X, Yu P S. Heterogeneous information network embedding for recommendation [J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(2): 357-370.Google ScholarDigital Library
- Chang S Y, Han W, Tang J L, Qi G J, Aggarwal C C, Huang T S. Heterogeneous network embedding via deep architectures [C]. In Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015, 119-128.Google ScholarDigital Library
- Liu W Y, Chen P Y, Yeung S, Suzumura T, Chen L L. Principled multilayer network embedding [C]. In Proceedings of the 17th IEEE International Conference on Data Mining, 2017, 134-141.Google ScholarCross Ref
- Qu M, Tang J, Shang J B, Ren X, Zhang M, Han J W. An attention-based collaboration framework for multi-view network representation learning [C]. In Proceedings of the 26th ACM International Conference on Information and Knowledge Management, 2017, 1767-1776.Google ScholarDigital Library
- Shi Y, Han F Q, He X W, Yang C, Luo J, Han J W. Mvn2vec: preservation and collaboration in multi-view network embedding [EB/OL] [2018-1-19]. https://doi.org/10.48550/arXiv.1801.06597.Google ScholarCross Ref
- Symeonidis P. Matrix and tensor decomposition in recommender systems [C]. In Proceedings of the 10th ACM Conference on Recommender Systems, 2016, 429-430.Google ScholarDigital Library
- Zhou D Y, Huang J Y, Schölkopf B. Learning with hypergraphs: clustering, classification and embedding[C]. In Proceedings of the 19th International Conference on Neural Information Processing Systems, 2006, 1601-1608.Google Scholar
- Yadati N, Nimishakavi M, Yadav P, Nitin V, Louis A, Talukdar P. HyperGCN: a new method of training graph convolutional networks on hypergraphs [C]. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2019.Google Scholar
- Bai S, Zhang F H, Torr P H S. Hypergraph convolution and hypergraph attention [J]. Pattern Recognition, 2021, 110(1):107637-107667.Google ScholarCross Ref
- Jiang J W, Wei Y X, Feng Y F, Cao J X, Gao Y. Dynamic hypergraph neural networks [C]. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019, 2635-2641.Google ScholarDigital Library
- Feng Y F, You H X, Zhang Z Z, Ji R R, Gao Y. Hypergraph neural networks [C]. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019, 3558-3565.Google ScholarDigital Library
- Krishna K, Murty M N. Genetic k-means algorithm [J]. IEEE Transactions on Systems Man and Cybernetics, 1999, 29(3): 433-439.Google ScholarDigital Library
- Gui H, Liu J L, Tao F B, Jiang M, Norick B Han J W. Large-scale embedding learning in heterogeneous event data [C]. In Proceedings of the 16th IEEE International Conference on Data Mining, 2016, 907-912.Google ScholarCross Ref
- Baytas I M, Xiao C, Wang F, Jain A K, Zhou J Y. Heterogeneous hyper-network embedding [C]. In Proceedings of the 18th IEEE International Conference on Data Mining, 2018, 875-880.Google ScholarCross Ref
- Tu K, Cui P, Wang X, Wang F, Zhu W W. Structural deep embedding for hyper-networks [C]. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018, 426-433.Google ScholarCross Ref
- Zhang R C, Zou Y S, Ma J. Hyper-SAGNN: a self-attention based graph neural network for hypergraphs. [EB/OL]. [2019-11-6]. https://doi.org/10.48550/arXiv.1911.02613.Google ScholarCross Ref
- Huang J, Liu X, Song Y Q. Hyper-path-based representation learning for hyper-networks [C]. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019, 449-458.Google ScholarDigital Library
Index Terms
- A Survey of Complex Network Representation Learning Methods
Recommendations
Deep Inductive Network Representation Learning
WWW '18: Companion Proceedings of the The Web Conference 2018This paper presents a general inductive graph representation learning framework called DeepGL for learning deep node and edge features that generalize across-networks. In particular, DeepGL begins by deriving a set of base features from the graph (e.g., ...
A survey on heterogeneous network representation learning
Highlights- We put forward a novel taxonomy of existing heterogeneous network representation learning algorithms, including path based algorithms, semantic unit based ...
AbstractHeterogeneous information networks usually contain different kinds of nodes and distinguishing types of relations, which can preserve more information than homogeneous information networks. Heterogeneous network representation learning ...
A survey of structural representation learning for social networks
Highlights- Structural similarity metrics and learning techniques are introduced.
- A method ...
AbstractSocial networks have a plethora of applications, and analysis of these applications has been gaining much interest from the research community. The high dimensionality of social network data poses a significant obstacle in its analysis,...
Comments