Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?
This addresses the problem of adapting pre-trained GNNs to downstream tasks with minimal supervision for researchers and practitioners in graph machine learning, representing an incremental advancement in prompt learning techniques.
The paper tackles the challenge of building transferable Graph Neural Networks (GNNs) with CLIP-style pre-training despite scarce labeled data and weak text supervision, proposing a multi-modal prompt learning paradigm that embeds graphs in the same space as Large Language Models (LLMs) and achieves superior performance in few-shot, multi-task, and cross-domain settings.
While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and the conceptual gaps between domains. In this work, to address these issues, we propose a multi-modal prompt learning paradigm to effectively adapt pre-trained GNN to downstream tasks and data, given only a few semantically labeled samples, each with extremely weak text supervision. Our new paradigm embeds the graphs directly in the same space as the Large Language Models (LLMs) by learning both graph prompts and text prompts simultaneously. We demonstrate the superior performance of our paradigm in few-shot, multi-task-level, and cross-domain settings. Moreover, we build the first CLIP-style zero-shot classification prototype that can generalize GNNs to unseen classes with extremely weak text supervision. The code is available at https://github.com/Violet24K/Morpher.