Text-attributed graph (TAG) is an important type of graph structured data with text descriptions for each node. Few- and zero-shot node classification on TAGs have many applications in fields such as academia and social networks. However, the two tasks are challenging due to the lack of supervision signals, and existing methods only use the contrastive loss to align graph-based node embedding and language-based text embedding. In this paper, we propose Hound to improve accuracy by introducing more supervision signals, and the core idea is to go beyond the node-text pairs that come with data. Specifically, we design three augmentation techniques, i.e., node perturbation, text matching, and semantics negation to provide more reference nodes for each text and vice versa. Node perturbation adds/drops edges to produce diversified node embeddings that can be matched with a text. Text matching retrieves texts with similar embeddings to match with a node. Semantics negation uses a negative prompt to construct a negative text with the opposite semantics, which is contrasted with the original node and text. We evaluate Hound on 5 datasets and compare with 13 state-of-the-art baselines. The results show that Hound consistently outperforms all baselines, and its accuracy improvements over the best-performing baseline are usually over 5%.

翻译：文本属性图（TAG）是一种重要的图结构数据类型，其中每个节点都附有文本描述。在TAG上进行少样本和零样本节点分类在学术界和社交网络等领域具有广泛的应用。然而，由于监督信号的缺乏，这两项任务极具挑战性，现有方法仅使用对比损失来对齐基于图的节点嵌入和基于语言的文本嵌入。本文提出Hound方法，通过引入更多监督信号来提高分类准确率，其核心思想是超越数据自带的节点-文本配对。具体而言，我们设计了三种增强技术：节点扰动、文本匹配和语义否定，以针对每个文本提供更多参考节点，反之亦然。节点扰动通过添加/删除边来生成多样化的节点嵌入，使其能与文本匹配。文本匹配通过检索具有相似嵌入的文本来与节点匹配。语义否定则使用负向提示构建一个具有相反语义的负向文本，并将其与原始节点和文本进行对比。我们在5个数据集上评估了Hound，并与13个最先进的基线方法进行了比较。结果表明，Hound在所有数据集上均一致优于所有基线方法，其相对于最佳基线的准确率提升通常超过5%。