论文标题
全面的自我语义传播，用于自我监督的图形表示学习
Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
论文作者
论文摘要
无监督/自我监督的图表表示学习对于下游节点和图形级分类任务至关重要。图的全球结构有助于区分表示表示和现有方法，主要通过施加其他监督来利用全球结构。但是，它们的全球语义通常对于所有节点/图表都是不变的，并且未能明确嵌入全球语义以丰富表示形式。在本文中，我们提出了全面的自我语义传播，以进行自我监督的图表学习（OEPG）。具体来说，我们介绍了实例自动感知的自我感知的自我语义描述符，利用整个图形数据集的每个节点/图和层次群之间的一阶特征差异。可以将描述符显式地集成到本地图卷积中，为新的邻居节点。此外，我们在自我语义的整个量表和层次结构上设计一个全晶归归式化，以从全面的角度将注意力重量分配给每个描述符。专门的借口任务和跨介绍动量更新将进一步开发用于局部全球相互适应。在下游任务中，OEPG始终在多个数据集跨尺度和域上获得2％〜6％的精度增益，从而达到最佳性能。值得注意的是，OEPG还推广到数量和拓扑服务的情况。
Unsupervised/self-supervised graph representation learning is critical for downstream node- and graph-level classification tasks. Global structure of graphs helps discriminating representations and existing methods mainly utilize the global structure by imposing additional supervisions. However, their global semantics are usually invariant for all nodes/graphs and they fail to explicitly embed the global semantics to enrich the representations. In this paper, we propose Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning (OEPG). Specifically, we introduce instance-adaptive global-aware ego-semantic descriptors, leveraging the first- and second-order feature differences between each node/graph and hierarchical global clusters of the entire graph dataset. The descriptors can be explicitly integrated into local graph convolution as new neighbor nodes. Besides, we design an omni-granular normalization on the whole scales and hierarchies of the ego-semantic to assign attentional weight to each descriptor from an omni-granular perspective. Specialized pretext tasks and cross-iteration momentum update are further developed for local-global mutual adaptation. In downstream tasks, OEPG consistently achieves the best performance with a 2%~6% accuracy gain on multiple datasets cross scales and domains. Notably, OEPG also generalizes to quantity- and topology-imbalance scenarios.
