SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
Jul 24, 2023
Speakers
Xueyuan Chen
Speaker · 0 followers
Shangzhe Li
Speaker · 0 followers
About
In contrastive learning, the choice of “view” controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, based on the theory of graph information bottleneck, we deduce the definition of this anchor view; put differently, the anchor view with essential information of input graph is supposed to have the minimal structural uncertainty. Furthermore, guided by structural entropy, we implement the anchor view, termed SEGA, for graph contrastive learning. We extensively validate the proposed anchor view on various benchmarks regarding graph classification under unsupervised, semi-supervised, and transfer learning and achieve significant performance boosts compared to the state-of-the-art methods.In contrastive learning, the choice of “view” controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, base…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Beyond In-Domain Scenarios: Robust Density-Aware Calibration
Watch later
Sample Complexity of Probability Divergences under Group Symmetry
Watch later
Ziyu Chen, …
A Connection between One-Step RL and Critic Regularization in Reinforcement Learning
Watch later
Explaining the effects of non-convergent MCMC in the training of Energy-Based Models
Watch later
Why Does Throwing Away Data Improve Worst-Group Error?
Watch later
