Large Language Model Meets Graph Neural Network in Knowledge Distillation

Despite recent community revelations about the advancements and potential of Large Language Models (LLMs) in understanding Text-Attributed Graphs (TAG), the deployment of LLMs for production is hindered by their high computational and storage requirements, as well as long latencies during inference. Simultaneously, although traditional Graph Neural Networks (GNNs) are light weight and adept at learning structural features of graphs, their ability to grasp the complex semantics in TAGs is somewhat constrained for real applications. To address these limitations, we concentrate on the downstream task of node classification in TAG and propose a novel graph knowledge distillation framework, termed Linguistic Graph Knowledge Distillation (LinguGKD), using LLMs as teacher models and GNNs as student models for knowledge distillation. It involves TAG-oriented instruction tuning of LLM on designed node classification prompts, followed by aligning the hierarchically learned node features of the teacher LLM and the student GNN in latent space, employing a layer-adaptive contrastive learning strategy. Through extensive experiments on a variety of LLM and GNN models and multiple benchmark datasets, the proposed LinguGKD significantly boosts the student GNN's predictive accuracy and convergence rate, without the need of extra data or model parameters. Compared to teacher LLM, distilled GNN achieves superior inference speed equipped with much fewer computing and storage demands, when surpassing the teacher LLM's classification performance on some of benchmark datasets.