LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning

TL;DR

This paper introduces GALLON, a framework that combines LLMs and GNNs by distilling multimodal molecular data into a unified model, significantly enhancing molecular property prediction accuracy and efficiency.

Contribution

The paper presents GALLON, a novel framework that effectively integrates multimodal data from LLMs and GNNs through knowledge distillation into an MLP for molecular analysis.

Findings

Improved accuracy in molecular property prediction.

Enhanced efficiency of the predictive model.

Effective integration of textual, visual, and structural data.

Abstract

Recent progress in Graph Neural Networks (GNNs) has greatly enhanced the ability to model complex molecular structures for predicting properties. Nevertheless, molecular data encompasses more than just graph structures, including textual and visual information that GNNs do not handle well. To bridge this gap, we present an innovative framework that utilizes multimodal molecular data to extract insights from Large Language Models (LLMs). We introduce GALLON (Graph Learning from Large Language Model Distillation), a framework that synergizes the capabilities of LLMs and GNNs by distilling multimodal knowledge into a unified Multilayer Perceptron (MLP). This method integrates the rich textual and visual data of molecules with the structural analysis power of GNNs. Extensive experiments reveal that our distilled MLP model notably improves the accuracy and efficiency of molecular property predictions.