K-Truss Based Temporal Graph Convolutional Network for Dynamic Graphs

Hongxi Li, Zuxuan Zhang, Dengzhe Liang, Yuncheng Jiang
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:739-754, 2024.

Abstract

Learning latent representations of nodes in graphs is important for many real-world applications, such as recommender systems, traffic prediction and fraud detection. Most of the existing research on graph representation learning has focused on static graphs. However, many real-world graphs are dynamic and their structures change over time, which makes learning dynamic node representations challenging. We propose a novel k-truss based temporal graph convolutional network named TTGCN to learn potential node representations on dynamic graphs. Specifically, TTGCN utilizes a novel truss-based graph convolutional layer named TrussGCN to capture the topology and hierarchical structure information of graphs, and combines it with a temporal evolution module to capture complex temporal dependencies. We conduct link prediction experiments on five different dynamic graph datasets. Experimental results demonstrate the superiority of TTGCN for dynamic graph embedding, as it consistently outperforms several state-of-the-art baselines in the link prediction task. In addition, our ablation experiments demonstrate the effectiveness of adopting TrussGCN in a dynamic graph embedding method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-li24d, title = {K-Truss Based Temporal Graph Convolutional Network for Dynamic Graphs}, author = {Li, Hongxi and Zhang, Zuxuan and Liang, Dengzhe and Jiang, Yuncheng}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {739--754}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/li24d/li24d.pdf}, url = {https://proceedings.mlr.press/v222/li24d.html}, abstract = {Learning latent representations of nodes in graphs is important for many real-world applications, such as recommender systems, traffic prediction and fraud detection. Most of the existing research on graph representation learning has focused on static graphs. However, many real-world graphs are dynamic and their structures change over time, which makes learning dynamic node representations challenging. We propose a novel k-truss based temporal graph convolutional network named TTGCN to learn potential node representations on dynamic graphs. Specifically, TTGCN utilizes a novel truss-based graph convolutional layer named TrussGCN to capture the topology and hierarchical structure information of graphs, and combines it with a temporal evolution module to capture complex temporal dependencies. We conduct link prediction experiments on five different dynamic graph datasets. Experimental results demonstrate the superiority of TTGCN for dynamic graph embedding, as it consistently outperforms several state-of-the-art baselines in the link prediction task. In addition, our ablation experiments demonstrate the effectiveness of adopting TrussGCN in a dynamic graph embedding method.} }
Endnote
%0 Conference Paper %T K-Truss Based Temporal Graph Convolutional Network for Dynamic Graphs %A Hongxi Li %A Zuxuan Zhang %A Dengzhe Liang %A Yuncheng Jiang %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-li24d %I PMLR %P 739--754 %U https://proceedings.mlr.press/v222/li24d.html %V 222 %X Learning latent representations of nodes in graphs is important for many real-world applications, such as recommender systems, traffic prediction and fraud detection. Most of the existing research on graph representation learning has focused on static graphs. However, many real-world graphs are dynamic and their structures change over time, which makes learning dynamic node representations challenging. We propose a novel k-truss based temporal graph convolutional network named TTGCN to learn potential node representations on dynamic graphs. Specifically, TTGCN utilizes a novel truss-based graph convolutional layer named TrussGCN to capture the topology and hierarchical structure information of graphs, and combines it with a temporal evolution module to capture complex temporal dependencies. We conduct link prediction experiments on five different dynamic graph datasets. Experimental results demonstrate the superiority of TTGCN for dynamic graph embedding, as it consistently outperforms several state-of-the-art baselines in the link prediction task. In addition, our ablation experiments demonstrate the effectiveness of adopting TrussGCN in a dynamic graph embedding method.
APA
Li, H., Zhang, Z., Liang, D. & Jiang, Y.. (2024). K-Truss Based Temporal Graph Convolutional Network for Dynamic Graphs. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:739-754 Available from https://proceedings.mlr.press/v222/li24d.html.

Related Material