CIMAGE：利用掩码图自编码器中的条件独立性
CIMAGE: Exploiting the Conditional Independence in Masked Graph Auto-encoders
AI总结：
CIMAGE利用条件独立性在潜在空间中引导掩码策略，通过CI感知的潜在因子分解和无监督聚类伪标签提升图自监督学习，在节点分类与链路预测上表现优异。
摘要：
近年来，在图神经网络（GNNs）中通过掩码封装关系信息的自监督学习（SSL）方法已展现出良好的性能。然而，大多数现有方法依赖特征空间或图空间中的随机掩码策略，这可能无法充分捕获与任务相关的信息。我们认为，这一局限源于无法在掩码与未掩码成分之间实现最小冗余，同时确保二者对潜在下游任务具有最大相关性。条件独立性（CI）天然满足最小冗余和最大相关性准则，但其应用通常需要获得下游标签。为应对这一挑战，我们提出了CIMAGE，这是一种利用条件独立性在潜在空间中引导有效掩码策略的新方法。CIMAGE利用具备CI意识的潜在因子分解生成两个不同的上下文，并借助无监督图聚类获得的高置信度伪标签。在该框架下，代理任务仅根据第一个上下文提供的信息重建被掩码的第二个上下文。我们的理论分析进一步支持了CIMAGE新颖的CI感知掩码方法的优越性，证明所学嵌入具有近似线性可分性，从而能够对下游任务进行准确预测。在多种图基准上的综合评估表明了CIMAGE的优势，其在节点分类和链路预测任务上获得了显著更高的平均排名。值得注意的是，我们提出的模型凸显了CI在增强图SSL方法学方面尚未充分探索的潜力，并为有效的图表示学习提供了更丰富的见解。
英文摘要：
Recent Self-Supervised Learning (SSL) methods encapsulating relational information via masking in Graph Neural Networks (GNNs) have shown promising performance. However, most existing approaches rely on random masking strategies in either feature or graph space, which may fail to capture task-relevant information fully. We posit that this limitation stems from an inability to achieve minimum redundancy between masked and unmasked components while ensuring maximum relevance of both to potential downstream tasks. Conditional Independence (CI) inherently satisfies the minimum redundancy and maximum relevance criteria, but its application typically requires access to downstream labels. To address this challenge, we introduce CIMAGE, a novel approach that leverages Conditional Independence to guide an effective masking strategy within the latent space. CIMAGE utilizes CI-aware latent factor decomposition to generate two distinct contexts, leveraging high-confidence pseudo-labels derived from unsupervised graph clustering. In this framework, the pretext task involves reconstructing the masked second context solely from the information provided by the first context. Our theoretical analysis further supports the superiority of CIMAGE's novel CI-aware masking method by demonstrating that the learned embedding exhibits approximate linear separability, which enables accurate predictions for the downstream task. Comprehensive evaluations across diverse graph benchmarks illustrate the advantage of CIMAGE, with notably higher average rankings on node classification and link prediction tasks. Notably, our proposed model highlights the under-explored potential of CI in enhancing graph SSL methodologies and offers enriched insights for effective graph representation learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
