Can we Soft Prompt LLMs for Graph Learning Tasks?
This work addresses the problem of modality mismatch for researchers and practitioners aiming to leverage LLMs in graph-based applications like social networks and biological data, representing an incremental advancement in hybrid methods.
The authors tackled the challenge of applying Large Language Models (LLMs) to graph learning tasks by introducing GraphPrompter, a framework that aligns graph information with LLMs using soft prompts, and demonstrated its effectiveness in node classification and link prediction on benchmark datasets.
Graph plays an important role in representing complex relationships in real-world applications such as social networks, biological data and citation networks. In recent years, Large Language Models (LLMs) have achieved tremendous success in various domains, which makes applying LLMs to graphs particularly appealing. However, directly applying LLMs to graph modalities presents unique challenges due to the discrepancy and mismatch between the graph and text modalities. Hence, to further investigate LLMs' potential for comprehending graph information, we introduce GraphPrompter, a novel framework designed to align graph information with LLMs via soft prompts. Specifically, GraphPrompter consists of two main components: a graph neural network to encode complex graph information and an LLM that effectively processes textual information. Comprehensive experiments on various benchmark datasets under node classification and link prediction tasks demonstrate the effectiveness of our proposed method. The GraphPrompter framework unveils the substantial capabilities of LLMs as predictors in graph-related tasks, enabling researchers to utilize LLMs across a spectrum of real-world graph scenarios more effectively.