Proceedings

Graph Debiased Contrastive Learning with Joint Representation Clustering

Han Zhao, Xu Yang, Zhenru Wang, Erkun Yang, Cheng Deng

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3434-3440.

https://doi.org/10.24963/ijcai.2021/473

Keywords

  • Machine Learning: Unsupervised Learning
  • Machine Learning: Clustering

Abstract

By contrasting positive-negative counterparts, graph contrastive learning has become a prominent technique for unsupervised graph representation learning. However, existing methods fail to consider the class information and will introduce false-negative samples in the random negative sampling, causing poor performance. To this end, we propose a graph debiased contrastive learning framework, which can jointly perform representation learning and clustering. Specifically, representations can be optimized by aligning with clustered class information, and simultaneously, the optimized representations can promote clustering, leading to more powerful representations and clustering results. More importantly, we randomly select negative samples from the clusters which are different from the positive sample's cluster. In this way, as the supervisory signals, the clustering results can be utilized to effectively decrease the false-negative samples. Extensive experiments on five datasets demonstrate that our method achieves new state-of-the-art results on graph clustering and classification tasks.

Han Zhao, Xu Yang, Zhenru Wang, Erkun Yang, and Cheng Deng. 2021. Graph Debiased Contrastive Learning with Joint Representation Clustering. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3434–3440. https://doi.org/10.24963/ijcai.2021/473
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards