Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph
This work addresses node classification in text-attributed graphs for applications in academia and social networks, representing an incremental advance by focusing on text-based augmentations.
The paper tackles few- and zero-shot node classification on text-attributed graphs by proposing Text Semantics Augmentation (TSA), which uses positive matching and negative contrast techniques to enhance text semantic supervision, resulting in accuracy improvements of over 5% compared to state-of-the-art baselines across 5 datasets.
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%.