Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment

Abstract

Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information, which has recently garnered increasing attention. In contrast to static graphs, temporal graphs are typically organized as node interaction sequences over continuous time rather than an adjacency matrix. Most temporal graph learning methods model current interactions by incorporating historical neighborhood. However, such methods only consider first-order temporal information while disregarding crucial high-order structural information, resulting in suboptimal performance. To address this issue, we propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information to learn more informative node representations. Notably, the initial node representations combine first-order temporal and high-order structural information differently to calculate two conditional intensities. An alignment loss is then introduced to optimize the node representations, narrowing the gap between the two intensities and making them more informative. Concretely, in addition to modeling temporal information using historical neighbor sequences, we further consider structural knowledge at both local and global levels. At the local level, we generate structural intensity by aggregating features from high-order neighbor sequences. At the global level, a global representation is generated based on all nodes to adjust the structural intensity according to the active statuses on different nodes. Extensive experiments demonstrate that the proposed model S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.

References in corpus (21)

• Adam: A Method for Stochastic Optimization
• A Comprehensive Survey on Graph Neural Networks
• DeepWalk: Online Learning of Social Representations
• Neural Graph Collaborative Filtering
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
• Structural Deep Clustering Network
• Parameterized Explainer for Graph Neural Network
• Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure
• TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal
• Where are we in embedding spaces? A Comprehensive Analysis on Network Embedding Approaches for Recommender Systems
• TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification
• Graph-based Semi-supervised Learning: A Comprehensive Review
• Deep Temporal Graph Clustering
• Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning
• G${}^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering
• DyExplainer: Explainable Dynamic Graph Neural Networks
• DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs
• SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoning

Cited by in corpus (4)

• Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Negative-Free Self-Supervised Gaussian Embedding of Graphs
• Self-Supervised Contrastive Graph Clustering Network via Structural Information Fusion