ABSTRACT
Dynamic Bipartite graph is naturally suited for modeling temporally evolving interaction in several domains, including digital payment and social media. Though dynamic graphs are widely studied, their focus remains on homogeneous graphs. This paper proposes a novel framework for representation learning in temporally evolving bipartite graphs. It introduces a bipartite graph transformer layer, a temporal bipartite graph encoder based on an attention mechanism for learning node representations. It further extends the information maximization objective based on noise contrastive learning to temporal bipartite graphs. This combination of bipartite encoder layer and noise contrastive loss ensures each node-set in the temporal bipartite graph is represented uniquely and disentangled from other node-set. We use four public datasets with temporal bipartite characteristics in experimentation. The proposed model shows promising results on the transductive and inductive dynamic link prediction task and on the temporal recommendation task.
- Jiangxia Cao*, Xixun Lin*, Shu Guo, Luchen Liu, Tingwen Liu, and Bin Wang. 2021. Bipartite Graph Embedding via Mutual Information Maximization. In ACM International Conference on Web Search and Data Mining (WSDM).Google Scholar
- Yuxiao Dong, Nitesh V. Chawla, and Ananthram Swami. 2017. Metapath2vec: Scalable Representation Learning for Heterogeneous Networks(KDD ’17). 135–144.Google Scholar
- Ming Gao, Xiangnan He, Leihui Chen, and Aoying Zhou. 2019. Learning Vertex Representations for Bipartite Networks. Computing Research Repository abs/1901.09676 (2019).Google Scholar
- Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 855–864.Google ScholarDigital Library
- William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. Computing Research Repository abs/1706.02216 (2017).Google Scholar
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations.Google Scholar
- Thomas N Kipf and Max Welling. 2016. Variational Graph Auto-Encoders. NIPS Workshop on Bayesian Deep Learning (2016).Google Scholar
- Srijan Kumar, Xikun Zhang, and Jure Leskovec. 2019. Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks. In Proceedings of the 25th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM.Google ScholarDigital Library
- Lynn H Loomis. 2013. An Introduction To Abstract Harmonic Analysis :.Google Scholar
- Gaurav Oberoi, Pranav Poduval, Karamjit Singh, Sangam Verma, and Pranay Gupta. 2022. CaPE: Category Preserving Embeddings for Similarity-Search in Financial Graphs. In Proceedings of the Third ACM International Conference on AI in Finance(ICAIF ’22). Association for Computing Machinery, 420–427.Google ScholarDigital Library
- Inkit Padhi, Yair Schiff, Igor Melnyk, Mattia Rigotti, Youssef Mroueh, Pierre Dognin, Jerret Ross, Ravi Nair, and Erik Altman. 2020. Tabular Transformers for Modeling Multivariate Time Series. https://doi.org/10.48550/ARXIV.2011.01843Google ScholarCross Ref
- Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao B. Schardl, and Charles E. Leiserson. 2020. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs. In Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
- Chanyoung Park, Donghyun Kim, Jiawei Han, and Hwanjo Yu. 2020. Unsupervised attributed multiplex network embedding. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 5371–5378.Google ScholarCross Ref
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2015. DeepWalk. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining.Google Scholar
- Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael M. Bronstein. 2020. Temporal Graph Networks for Deep Learning on Dynamic Graphs. Computing Research Repository abs/2006.10637 (2020).Google Scholar
- Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. 2015. LINE. International World Wide Web Conferences Steering Committee. https://doi.org/10.1145/2736277.2741093Google ScholarDigital Library
- Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, and Hongyuan Zha. 2019. DyRep: Learning Representations over Dynamic Graphs. In International Conference on Learning Representations.Google Scholar
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations.Google Scholar
- Andrew Wang, Rex Ying, Pan Li, Nikhil Rao, Karthik Subbian, and Jure Leskovec. 2021. Bipartite Dynamic Representations for Abuse Detection. In Proceedings of the 27th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM.Google ScholarDigital Library
- Da Xu, Chuanwei Ruan, Evren Körpeoglu, Sushant Kumar, and Kannan Achan. 2020. Inductive Representation Learning on Temporal Graphs. Computing Research Repository abs/2002.07962 (2020).Google Scholar
- Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L. Hamilton, and Jure Leskovec. 2018. Graph Convolutional Neural Networks for Web-Scale Recommender Systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM. https://doi.org/10.1145/3219819.3219890Google ScholarDigital Library
- Xujiang Zhao, Feng Chen, and Jin-Hee Cho. 2018. Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data. In 2018 IEEE International Conference on Big Data (Big Data). 1150–1155.Google Scholar
Index Terms
- Learning Temporal Representations of Bipartite Financial Graphs
Recommendations
A note on transformations of edge colorings of bipartite graphs
The author and A. Mirumian proved the following theorem: Let G be a bipartite graph with maximum degree @D and let t,n be integers, t>=n>=@D. Then it is possible to obtain, from one proper edge t-coloring of G, any proper edge n-coloring of G using only ...
Dominating induced matching in some subclasses of bipartite graphs
AbstractA subset M ⊆ E of edges of a graph G = ( V , E ) is called a matching if no two edges of M share a common vertex. An edge e ∈ E is said to dominate itself and all other edges adjacent to it. A matching M in a graph G = ( V , E ) is ...
Biclique Graphs of K3-free Graphs and Bipartite Graphs
AbstractA biclique of a graph is a maximal complete bipartite subgraph. The biclique graph of a graph G, KB(G), defined as the intersection graph of the bicliques of G, was introduced and characterized in 2010 by Groshaus and Szwarcfiter. However, this ...
Comments