.png){kind=icon}
Return
Multiview Graph Contrastive Learning Based on Learnable Graph Augmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSS.2026.3660965.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph contrastive learning has recently gained prominence as a key technique in the domain of graph representation learning. Most graph contrastive learning methods generate two graph views by augmenting the input graph and maximizing the consistency of their representations. However, due to a lack of prior knowledge of graph data, existing graph augmentation methods often generate low-quality views, which can destroy the core structural information of the graph and thus affect the model’s learning. The fundamental limitation lies in the semantic-agnostic nature of such augmentations, which fail to adapt to the underlying data distribution and the model’s evolving training state. In addition, existing contrastive learning methods typically employ a single contrastive strategy and rely on numerous similarity calculations, which makes it challenging to fully capture the diverse features in a graph. To address these limitations, we propose a multiview graph contrastive learning method based on learnable graph augmentation (MGLGA). Specifically, this method abandons the traditional random graph augmentation, constructs views through dynamic feature learning, and generates feature views using a graph feature learner and a postprocessing module, thereby focusing on the essential structural features of the graph while minimizing interference with the view generation. This learnable paradigm ensures that the augmented views maintain high semantic fidelity and provide adaptive, curriculum-like learning signals throughout the training process, thereby theoretically promoting better generalization. Moreover, we design a three-branch structure to capture both fine-grained and coarse-grained knowledge of the graph through node-level and graph-level contrasts. We further develop a structure-aware group discrimination loss through contrastive objective optimization, enhancing the model’s capacity for capturing graph structural patterns. Comprehensive evaluations demonstrate state-of-the-art performance across multiple downstream benchmarks.
Keywords:
Graph contrastive learning (GCL)
node classification
node clustering
self-supervised learning
Journal
IF:
4.9
Papers:
622
Citations:
6.8K
Organization
Cited Papers
AM-GCN: Adaptive Multi-channel Graph Convolutional Networks.png)
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
OAAI
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningIF0
OAAIShareSave
ShareSaveShareSaveGCCProceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningOAAI
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningIF0
OAAIShareSaveShareSave
View more