2023/07/21 by Yuexin Li, Bryan Hooi, Li, Yuexin +1
Computer Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Social and Information Networks (cs.SI) #Text and Document Classification Technologies #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2307.11572
openalex publication_date 2023/07/21 · openalex created_date 2023/07/25 · openalex updated_date 2026/07/28
Multimodal data empowers machine learning models to better understand the world from various perspectives. In this work, we study the combination of text and graph modalities, a challenging but understudied combination which is prevalent across multiple settings including citation networks, social media, and the web. We focus on the popular task of node classification using limited labels; in particular, under the zero- and few-shot scenarios. In contrast to the standard pipeline which feeds standard precomputed (e.g., bag-of-words) text features into a graph neural network, we propose Text-And-Graph (TAG) learning, a more deeply multimodal approach that integrates the raw texts and graph topology into the model design, and can effectively learn from limited supervised signals without any meta-learning procedure. TAG is a two-stage model with (1) a prompt- and graph-based module which generates prior logits that can be directly used for zero-shot node classification, and (2) a trainable module that further calibrates these prior logits in a few-shot manner. Experiments on two node classification datasets show that TAG outperforms all the baselines by a large margin in both zero- and few-shot settings.