TY - GEN
T1 - Graph Communal Contrastive Learning
AU - Li, Bolian
AU - Jing, Baoyu
AU - Tong, Hanghang
N1 - This work was partially supported by (i) National Key Research and Development Program of China 2020AAA0108503, (ii) NSFC Grants 62072034, U1809206, and 61772346. Rong-Hua Li is the corresponding author of this paper.
PY - 2022/4/25
Y1 - 2022/4/25
N2 - Graph representation learning is crucial for many real-world applications (e.g. social relation analysis). A fundamental problem for graph representation learning is how to effectively learn representations without human labeling, which is usually costly and time-consuming. Graph contrastive learning (GCL) addresses this problem by pulling the positive node pairs (or similar nodes) closer while pushing the negative node pairs (or dissimilar nodes) apart in the representation space. Despite the success of the existing GCL methods, they primarily sample node pairs based on the node-level proximity yet the community structures have rarely been taken into consideration. As a result, two nodes from the same community might be sampled as a negative pair. We argue that the community information should be considered to identify node pairs in the same communities, where the nodes insides are semantically similar. To address this issue, we propose a novel Graph Communal Contrastive Learning (gCooL) framework to jointly learn the community partition and learn node representations in an end-to-end fashion. Specifically, the proposed gCooL consists of two components: a Dense Community Aggregation (DeCA) algorithm for community detection and a Reweighted Self-supervised Cross-contrastive (ReSC) training scheme to utilize the community information. Additionally, the real-world graphs are complex and often consist of multiple views. In this paper, we demonstrate that the proposed gCooL can also be naturally adapted to multiplex graphs. Finally, we comprehensively evaluate the proposed gCooL on a variety of real-world graphs. The experimental results show that the gCooL outperforms the state-of-the-art methods.
AB - Graph representation learning is crucial for many real-world applications (e.g. social relation analysis). A fundamental problem for graph representation learning is how to effectively learn representations without human labeling, which is usually costly and time-consuming. Graph contrastive learning (GCL) addresses this problem by pulling the positive node pairs (or similar nodes) closer while pushing the negative node pairs (or dissimilar nodes) apart in the representation space. Despite the success of the existing GCL methods, they primarily sample node pairs based on the node-level proximity yet the community structures have rarely been taken into consideration. As a result, two nodes from the same community might be sampled as a negative pair. We argue that the community information should be considered to identify node pairs in the same communities, where the nodes insides are semantically similar. To address this issue, we propose a novel Graph Communal Contrastive Learning (gCooL) framework to jointly learn the community partition and learn node representations in an end-to-end fashion. Specifically, the proposed gCooL consists of two components: a Dense Community Aggregation (DeCA) algorithm for community detection and a Reweighted Self-supervised Cross-contrastive (ReSC) training scheme to utilize the community information. Additionally, the real-world graphs are complex and often consist of multiple views. In this paper, we demonstrate that the proposed gCooL can also be naturally adapted to multiplex graphs. Finally, we comprehensively evaluate the proposed gCooL on a variety of real-world graphs. The experimental results show that the gCooL outperforms the state-of-the-art methods.
KW - community detection
KW - graph contrastive learning
KW - self-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85129872868&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129872868&partnerID=8YFLogxK
U2 - 10.1145/3485447.3512208
DO - 10.1145/3485447.3512208
M3 - Conference contribution
AN - SCOPUS:85129872868
T3 - WWW 2022 - Proceedings of the ACM Web Conference 2022
SP - 1203
EP - 1213
BT - WWW 2022 - Proceedings of the ACM Web Conference 2022
PB - Association for Computing Machinery
T2 - 31st ACM World Wide Web Conference, WWW 2022
Y2 - 25 April 2022 through 29 April 2022
ER -