Topology-monitorable Contrastive Learning on Dynamic Graphs
Open Access
- 24 August 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4700-4711
Abstract
Graph contrastive learning is a representative self-supervised graph learning that has demonstrated excellent performance in learning node representations. Despite the extensive studies on graph contrastive learning models, most existing models are tailored to static graphs, hindering their application to real-world graphs which are often dynamically evolving. Directly applying these models to dynamic graphs brings in severe efficiency issues in repetitively updating the learned embeddings. To address this challenge, we propose IDOL, a novel contrastive learning framework for dynamic graph representation learning. IDOL conducts the graph propagation process based on a specially designed Personalized PageRank algorithm which can capture the topological changes incrementally. This effectively eliminates heavy recomputation while maintaining high learning quality. Our another main design is a topology-monitorable sampling strategy which lays the foundation of graph contrastive learning. We further show that the design in IDOL achieves a desired performance guarantee. Our experimental results on multiple dynamic graphs show that IDOL outperforms the strongest baselines on node classification tasks in various performance metrics.Keywords
Funding Information
- Ministry of Education, Singapore, (AcRF Tier-2 Grant (T2EP20122-0003))
This publication has 34 references indexed in Scilit:
- Single-Source Personalized PageRanks with Workload RobustnessIEEE Transactions on Knowledge and Data Engineering, 2022
- PSGraph: How Tencent trains extremely large-scale graphs with Spark?2020
- Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning2019
- BATON: Batch One-Hop Personalized PageRanks with Efficiency and AccuracyIEEE Transactions on Knowledge and Data Engineering, 2019
- Generating Synthetic Graphs for Large Sensitive and Correlated Social Networks2019
- Related Pins at Pinterest2017
- Social bootstrapping2014
- WTF2013
- Local Computation of PageRank Contributions2007
- Local Graph Partitioning using PageRank Vectors2006