GCL-OT：基于最优传输的图对比学习用于异质文本属性图
GCL-OT: Graph Contrastive Learning with Optimal Transport for Heterophilic Text-Attributed Graphs
AI总结：
GCL-OT通过最优传输和定制机制解决文本属性图中的异质性问题，提升结构-文本对齐效果。
摘要：
最近，结构-文本对比学习在文本属性图上展示了有前景的性能，通过利用图神经网络和语言模型的互补优势。然而，现有方法通常依赖于相似性估计中的同质假设和硬优化目标，这限制了它们在异质图中的应用。尽管现有方法可以通过结构调整或邻居聚合来缓解异质性，但它们通常将文本嵌入视为静态目标，导致对齐不充分。在本工作中，我们识别出文本属性图中的多粒度异质性，包括完全异质性、部分异质性和潜在同质性，这使得结构-文本对齐特别具有挑战性，因为存在混合、噪声和缺失的语义相关性。为了实现灵活且双向的对齐，我们提出GCL-OT，一种新的图对比学习框架，结合最优传输，配备了针对每种异质性类型的定制机制。具体而言，对于部分异质性，我们设计了一个基于RealSoftMax的相似性估计器，以强调关键邻居-词交互，同时减轻背景噪声。对于完全异质性，我们引入了一个基于提示的过滤器，在最优传输对齐过程中自适应地排除无关噪声。此外，我们结合了最优传输引导的软监督，以揭示具有相似语义的潜在邻居，增强潜在同质性的学习。理论分析显示，GCL-OT可以提高互信息界和贝叶斯误差保证。在九个基准上的广泛实验表明，GCL-OT优于最先进的方法，证明了其有效性和鲁棒性。
英文摘要：
Recently, structure-text contrastive learning has shown promising performance on text-attributed graphs by leveraging the complementary strengths of graph neural networks and language models. However, existing methods typically rely on homophily assumptions in similarity estimation and hard optimization objectives, which limit their applicability to heterophilic graphs. Although existing methods can mitigate heterophily through structural adjustments or neighbor aggregation, they usually treat textual embeddings as static targets, leading to suboptimal alignment. In this work, we identify multi-granular heterophily in text-attributed graphs, including complete heterophily, partial heterophily, and latent homophily, which makes structure-text alignment particularly challenging due to mixed, noisy, and missing semantic correlations. To achieve flexible and bidirectional alignment, we propose GCL-OT, a novel graph contrastive learning framework with optimal transport, equipped with tailored mechanisms for each type of heterophily. Specifically, for partial heterophily, we design a RealSoftMax-based similarity estimator to emphasize key neighbor-word interactions while easing background noise. For complete heterophily, we introduce a prompt-based filter that adaptively excludes irrelevant noise during optimal transport alignment. Furthermore, we incorporate OT-guided soft supervision to uncover potential neighbors with similar semantics, enhancing the learning of latent homophily. Theoretical analysis shows that GCL-OT can improve the mutual information bound and Bayes error guarantees. Extensive experiments on nine benchmarks show that GCL-OT outperforms state-of-the-art methods, demonstrating its effectiveness and robustness.
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。
