We study the problem of learning universal features across multiple graphs through self-supervision. Graph self supervised learning has been shown to facilitate representation learning, and produce competitive models compared to supervised baselines. However, existing methods of self-supervision learn features from one graph, and thus, produce models that are specialized to a particular graph. We hypothesize that leveraging multiple graphs of the same type/class can improve the quality of learnt representations in the model by extracting features that are universal to the class of graphs. We adopt a transformer backbone that acts as a universal representation learning module for multiple graphs. We leverage neighborhood aggregation coupled with graph-specific embedding generator to transform disparate node embeddings from multiple graphs to a common space for the universal backbone. We learn both universal and graph-specific parameters in an end-to-end manner. Our experiments reveal that leveraging multiple graphs of the same type -- citation networks -- improves the quality of representations and results in better performance on downstream node classification task compared to self-supervision with one graph. The results of our study improve the state-of-the-art in graph self-supervised learning, and bridge the gap between self-supervised and supervised performance.

翻译：我们研究通过自监督方式在多个图之间学习通用特征的问题。图自监督学习已被证明能促进表示学习，并生成与有监督基线相媲美的竞争性模型。然而，现有的自监督方法仅从单个图中学习特征，因此生成的模型仅针对特定图具有专长。我们假设，利用同一类型/类别的多个图可以通过提取该类图的通用特征来提升模型中学习到的表示质量。我们采用Transformer骨干网络作为多个图的通用表示学习模块。通过结合邻域聚合与图特定嵌入生成器，我们将来自多个图的异构节点嵌入转换至通用骨干网络的共同空间。我们以端到端方式同时学习通用参数和图特定参数。实验表明，利用同一类型的多个图（引文网络）能够提升表示质量，并在下游节点分类任务上取得优于单图自监督学习的性能。本研究结果改进了图自监督学习的最优方法，缩小了自监督与有监督性能之间的差距。