Augmentation techniques and sampling strategies are crucial in contrastive learning, but in most existing works, augmentation techniques require careful design, and their sampling strategies can only capture a small amount of intrinsic supervision information. Additionally, the existing methods require complex designs to obtain two different representations of the data. To overcome these limitations, we propose a novel framework called the Self-Contrastive Graph Diffusion Network (SCGDN). Our framework consists of two main components: the Attentional Module (AttM) and the Diffusion Module (DiFM). AttM aggregates higher-order structure and feature information to get an excellent embedding, while DiFM balances the state of each node in the graph through Laplacian diffusion learning and allows the cooperative evolution of adjacency and feature information in the graph. Unlike existing methodologies, SCGDN is an augmentation-free approach that avoids "sampling bias" and semantic drift, without the need for pre-training. We conduct a high-quality sampling of samples based on structure and feature information. If two nodes are neighbors, they are considered positive samples of each other. If two disconnected nodes are also unrelated on $k$NN graph, they are considered negative samples for each other. The contrastive objective reasonably uses our proposed sampling strategies, and the redundancy reduction term minimizes redundant information in the embedding and can well retain more discriminative information. In this novel framework, the graph self-contrastive learning paradigm gives expression to a powerful force. SCGDN effectively balances between preserving high-order structure information and avoiding overfitting. The results manifest that SCGDN can consistently generate outperformance over both the contrastive methods and the classical methods.

翻译：在对比学习中，数据增强技术和采样策略至关重要，但现有多数方法中，增强技术需精心设计，且其采样策略仅能捕获少量内在监督信息。此外，现有方法需复杂设计来获得数据的两种不同表征。为解决这些限制，我们提出一种名为自对比图扩散网络（SCGDN）的新框架。该框架包含两大核心组件：注意力模块（AttM）和扩散模块（DiFM）。AttM通过聚合高阶结构和特征信息获得优质嵌入表示，而DiFM则通过拉普拉斯扩散学习平衡图中各节点的状态，并实现图中邻接关系与特征信息的协同演化。与现有方法不同，SCGDN是一种免增强的方法，可避免"采样偏差"和语义漂移，且无需预训练。我们基于结构和特征信息对样本进行高质量采样：若两个节点互为邻居，则被视为彼此的正样本；若两个非连通节点在$k$最近邻图上也无关联，则被视为彼此的负样本。对比目标合理利用了我们提出的采样策略，冗余缩减项可最小化嵌入中的冗余信息，并有效保留更多判别性信息。在此新框架中，图自对比学习范式展现出强大能力。SCGDN在保留高阶结构信息与避免过拟合之间实现有效平衡。结果表明，SCGDN在对比方法和经典方法中均能持续产生更优性能。