HiTeC: 基于语义感知增强的文本属性超图层次对比学习
HiTeC: Hierarchical Contrastive Learning on Text-Attributed Hypergraph with Semantic-Aware Augmentation
AI总结：
提出HiTeC框架，通过两阶段层次对比学习，结合结构感知文本编码预训练和语义感知增强，解决文本属性超图中文本与拓扑关联不足、随机增强噪声及长程依赖捕获问题。
摘要：
对比学习已成为自监督超图学习的主流范式，能够在无需昂贵标签的情况下实现有效训练。然而，现实世界超图中的节点实体通常关联丰富的文本信息，这在先前工作中被大量忽略。直接将现有基于对比学习的方法应用于此类文本属性超图（TAHGs）会导致三个关键限制：（1）普遍使用的图无关文本编码器无法捕获文本语义与超图拓扑之间的相关性，导致表示表达能力不足。（2）它们对随机数据增强的依赖引入了噪声并削弱了对比信号。（3）主要关注节点和超边级别的对比信号限制了捕获长程依赖的能力，而这对于有效的表示学习至关重要。为解决这些挑战，我们引入了HiTeC，一个两阶段层次对比学习框架，用于在TAHGs上进行有效的自监督学习。在第一阶段，我们使用结构感知的对比目标预训练文本编码器，以克服传统方法的图无关特性。在第二阶段，我们首先引入语义感知增强，包括结构上下文化的文本增强和语义感知的超边丢弃，以促进信息丰富的视图生成。随后，我们提出一个多尺度对比损失，结合基于$s$步行走的子图级别目标，以捕获长程依赖。在六个真实世界数据集上的大量实验验证了我们提出方法的有效性。
英文摘要：
Contrastive learning (CL) has become a dominant paradigm for self-supervised hypergraph learning, enabling effective training without costly labels. However, node entities in real-world hypergraphs are often associated with rich textual information, which has been largely ignored in prior works. Directly applying existing CL-based methods to such text-attributed hypergraphs (TAHGs) leads to three key limitations: (1) The common use of graph-agnostic text encoders fails to capture the correlations between textual semantics and hypergraph topology, resulting in less expressive representations. (2) Their reliance on random data augmentations introduces noise and weakens the contrastive signals. (3) The primary focus on node- and hyperedge-level contrastive signals limits the ability to capture long-range dependencies, which is essential for effective representation learning. To address these challenges, we introduce HiTeC, a two-stage hierarchical contrastive learning framework for effective self-supervised learning on TAHGs. In the first stage, we pre-train the text encoder with a structure-aware contrastive objective to overcome the graph-agnostic nature of conventional methods. In the second stage, we begin by introducing semantic-aware augmentations, including structure-contextualized text augmentation and semantic-aware hyperedge dropping, to facilitate informative view generation. Subsequently, we propose a multi-scale contrastive loss with an $s$-walk-based subgraph-level objective to capture long-range dependencies. Extensive experiments on six real-world datasets validate the effectiveness of our proposed method.
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。
