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. 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. Lastly, different aspects of the proposed framework are investigated through experimental analysis and ablation studies. The code is publicly available at https://github.com/huawei-noah/noah-research/tree/master/graph_atlas.

翻译：时序图神经网络通过自动提取时序模式，在学习归纳式表示方面取得了显著成果。然而，以往的工作通常依赖复杂的记忆模块或低效的随机游走方法来构建时序表示。为解决这些局限性，我们提出一种高效且有效的基于注意力的编码器，该编码器利用时序边编码和基于窗口的子图采样来生成任务无关的嵌入表示。此外，我们提出一种基于非对比自监督学习的联合嵌入架构，无需标签即可学习丰富的时序嵌入表示。在7个基准数据集上的实验结果表明，在未来的链接预测任务中，我们的模型在传导式设置下平均优于最先进基线4.23%，在归纳式设置下平均优于3.30%，同时训练/推理时间仅需其5-10倍。最后，通过实验分析和消融研究探讨了所提出框架的不同方面。代码已开源：https://github.com/huawei-noah/noah-research/tree/master/graph_atlas