DyG2Vec: Representation Learning for Dynamic Graphs with Self-Supervision

Temporal graph neural networks have shown promising results in learning inductive representations by automatically extracting temporal patterns. However, previous works often rely on complex memory modules or inefficient random walk methods to construct temporal representations. In addition, the existing dynamic graph encoders are non-trivial to adapt to self-supervised paradigms, which prevents them from utilizing unlabeled data. To address these limitations, we present an efficient yet effective attention-based encoder that leverages temporal edge encodings and window-based subgraph sampling to generate task-agnostic embeddings. Moreover, we propose a joint-embedding architecture using non-contrastive SSL to learn rich temporal embeddings without labels. Experimental results on 7 benchmark datasets indicate that on average, our model outperforms SoTA baselines on the future link prediction task by 4.23% for the transductive setting and 3.30% for the inductive setting while only requiring 5-10x less training/inference time. Additionally, we empirically validate the SSL pre-training significance under two probings commonly used in language and vision modalities. Lastly, different aspects of the proposed framework are investigated through experimental analysis and ablation studies.