Empowering LLMs with Structural Role Inference for Zero-Shot Graph Learning

TL;DR

This paper introduces DuoGLM, a novel framework that enhances large language models' ability to understand graph structures by explicitly reasoning about node roles, significantly improving zero-shot and transfer learning performance.

Contribution

DuoGLM is a training-free, dual-perspective approach that incorporates relation-aware templates and topology-to-role inference for better graph reasoning with LLMs.

Findings

14.3% accuracy gain in zero-shot node classification

7.6% AUC improvement in cross-domain transfer

Substantial performance improvements across eight benchmark datasets

Abstract

Large Language Models have emerged as a promising approach for graph learning due to their powerful reasoning capabilities. However, existing methods exhibit systematic performance degradation on structurally important nodes such as bridges and hubs. We identify the root cause of these limitations. Current approaches encode graph topology into static features but lack reasoning scaffolds to transform topological patterns into role-based interpretations. This limitation becomes critical in zero-shot scenarios where no training data establishes structure-semantics mappings. To address this gap, we propose DuoGLM, a training-free dual-perspective framework for structure-aware graph reasoning. The local perspective constructs relation-aware templates capturing semantic interactions between nodes and neighbors. The global perspective performs topology-to-role inference to generate functional descriptions of structural positions. These complementary perspectives provide explicit reasoning mechanisms enabling LLMs to distinguish topologically similar but semantically different nodes. Extensive experiments across eight benchmark datasets demonstrate substantial improvements. DuoGLM achieves 14.3\% accuracy gain in zero-shot node classification and 7.6\% AUC improvement in cross-domain transfer compared to existing methods. The results validate the effectiveness of explicit role reasoning for graph understanding with LLMs.