GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks
Keywords: Graph, LLMs, Graph Neural Networks
Abstract: Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse research fields of artificial intelligence especially for open-ended tasks. While the idea is less explored in the graph domain, despite the availability of numerous powerful graph models (GMs), they are restricted to tasks in a pre-defined form. Although several methods applying LLMs to graph have been proposed, they fail to simultaneously handle the pre-defined and open-ended tasks, by using LLM as node feature enhancer or as a standalone predictor. To break this dilemma, we propose to bridge the pretrained GM and LLM by a Translator, named GraphTranslator, aiming to leverage GM to handle the pre-defined tasks effectively and utilize the extended interface of LLMs to offer various open-ended tasks for GM. To train such Translator, we propose a Producer capable of constructing the graph-language alignment data along node information, neighbor information and model bias. By treating the node representation as a type of language, the proposed GraphTranslator empowers a LLM to make predictions based on node representation and language instructions, providing a unified perspective for both pre-defined and open-ended tasks. Extensive results show that the proposed GraphTranslator effectively improves the results of zero-shot node classification. The preliminary graph question answering experiments reveal our GraphTranslator potential across a broad spectrum of open-ended applications through language instructions.
Track: Graph Algorithms and Learning for the Web
Submission Guidelines Scope: Yes
Submission Guidelines Blind: Yes
Submission Guidelines Format: Yes
Submission Guidelines Limit: Yes
Submission Guidelines Authorship: Yes
Student Author: Yes
Submission Number: 2232
Loading