Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective
Graph contrastive learning (GCL) emerges as the most representative approach for graph representation learning, which leverages the principle of maximizing mutual information (InfoMax) to learn node representations applied in downstream tasks. To explore better generalization from GCL to downstream...
Saved in:
Main Authors | , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
20.11.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Graph contrastive learning (GCL) emerges as the most representative approach
for graph representation learning, which leverages the principle of maximizing
mutual information (InfoMax) to learn node representations applied in
downstream tasks. To explore better generalization from GCL to downstream
tasks, previous methods heuristically define data augmentation or pretext
tasks. However, the generalization ability of GCL and its theoretical principle
are still less reported. In this paper, we first propose a metric named GCL-GE
for GCL generalization ability. Considering the intractability of the metric
due to the agnostic downstream task, we theoretically prove a mutual
information upper bound for it from an information-theoretic perspective.
Guided by the bound, we design a GCL framework named InfoAdv with enhanced
generalization ability, which jointly optimizes the generalization metric and
InfoMax to strike the right balance between pretext task fitting and the
generalization ability on downstream tasks. We empirically validate our
theoretical findings on a number of representative benchmarks, and experimental
results demonstrate that our model achieves state-of-the-art performance. |
---|---|
DOI: | 10.48550/arxiv.2211.10929 |