Unsupervised Multiplex Graph Learning with Complementary and Consistent Information
arXiv:2308.01606 · doi:10.1145/3581783.3611971
Abstract
Unsupervised multiplex graph learning (UMGL) has been shown to achieve significant effectiveness for different downstream tasks by exploring both complementary information and consistent information among multiple graphs. However, previous methods usually overlook the issues in practical applications, i.e., the out-of-sample issue and the noise issue. To address the above issues, in this paper, we propose an effective and efficient UMGL method to explore both complementary and consistent information. To do this, our method employs multiple MLP encoders rather than graph convolutional network (GCN) to conduct representation learning with two constraints, i.e., preserving the local graph structure among nodes to handle the out-of-sample issue, and maximizing the correlation of multiple node representations to handle the noise issue. Comprehensive experiments demonstrate that our proposed method achieves superior effectiveness and efficiency over the comparison methods and effectively tackles those two issues. Code is available at https://github.com/LarryUESTC/CoCoMG.
References in corpus (12)
- DeepWalk: Online Learning of Social Representations
- Representation Learning with Contrastive Predictive Coding
- Graph Contrastive Learning with Adaptive Augmentation
- Graph Self-Supervised Learning: A Survey
- Representation Learning for Attributed Multiplex Heterogeneous Network
- HDMI: High-order Deep Multiplex Infomax
- The new challenges of multiplex networks: measures and models
- Understanding Dimensional Collapse in Contrastive Self-supervised Learning
- Self-Supervised Learning of Graph Neural Networks: A Unified Review
- X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning
- Relational Self-Supervised Learning on Graphs
- Message passing all the way up