Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph

TL;DR

This paper introduces Text Semantics Augmentation (TSA), a novel method that enhances few- and zero-shot node classification on text-attributed graphs by leveraging semantic-based text augmentations, significantly improving accuracy.

Contribution

The paper proposes two new text augmentation techniques, positive semantics matching and negative semantics contrast, to provide richer semantic supervision for node classification.

Findings

TSA outperforms 13 state-of-the-art baselines on 5 datasets.

Accuracy improvements over the best baseline are usually over 5%.

Text-based augmentations significantly enhance classification performance.

Abstract

Text-attributed graph (TAG) provides a text description for each graph node, and few- and zero-shot node classification on TAGs have many applications in fields such as academia and social networks. Existing work utilizes various graph-based augmentation techniques to train the node and text embeddings, while text-based augmentations are largely unexplored. In this paper, we propose Text Semantics Augmentation (TSA) to improve accuracy by introducing more text semantic supervision signals. Specifically, we design two augmentation techniques, i.e., positive semantics matching and negative semantics contrast, to provide more reference texts for each graph node or text description. Positive semantic matching retrieves texts with similar embeddings to match with a graph node. Negative semantic contrast adds a negative prompt to construct a text description with the opposite semantics, which is contrasted with the original node and text. We evaluate TSA on 5 datasets and compare with 13 state-of-the-art baselines. The results show that TSA consistently outperforms all baselines, and its accuracy improvements over the best-performing baseline are usually over 5%.