Link Prediction on Heterophilic Graphs via Disentangled Representation Learning
Open Access
- Author:
- Zhou, Shijie
- Graduate Program:
- Informatics
- Degree:
- Master of Science
- Document Type:
- Master Thesis
- Date of Defense:
- March 14, 2023
- Committee Members:
- Suhang Wang, Thesis Advisor/Co-Advisor
Dongwon Lee, Committee Member
Jeffrey Bardzell, Program Head/Chair
Xiang Zhang, Committee Member - Keywords:
- Graph Learning
Heterophilic Graph
Disentangled Representation Learning
Machine Learning - Abstract:
- Link prediction is an important task that has wide applications in various domains. However, the majority of existing link prediction approaches assume that the given graph follows homophily assumption, and design similarity-based heuristics or representation learning approaches to predict links. However, many real-world graphs are heterophilic graphs, where the homophily assumption does not hold, which challenges existing link prediction methods. Generally, in heterophilic graphs, there are many latent factors causing the link formation, and two linked nodes tend to be similar in one or two factors but might be dissimilar in other factors, leading to low overall similarity. Thus, one way is to learn disentangled representation for each node with each vector capturing the latent representation of a node on one factor, which paves a way to model the link formation in heterophilic graphs, resulting in better node representation learning and link prediction performance. However, the work on this is rather limited. Therefore, in this paper, we study a novel problem of exploring disentangled representation learning for link prediction on heterophilic graphs. We propose a novel framework DisenLink which can learn disentangled representations by modeling the link formation and perform factor-aware message-passing to facilitate link prediction. Extensive experiments on 13 real-world datasets demonstrate the effectiveness of DisenLink for link prediction on both heterophilic and homophilic graphs.