Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion
This work addresses the challenge of scalable and effective GNN-LLM integration for graph learning, offering an adaptive solution that improves performance on specific node subgroups without high computational costs.
The paper tackles the problem of inefficient fusion of Large Language Models (LLMs) and Graph Neural Networks (GNNs) for text-attributed graphs by proposing GLANCE, a framework that selectively invokes LLMs based on node-specific signals, achieving up to +13% gains on heterophilous nodes while maintaining top overall performance.
Learning on text-attributed graphs has motivated the use of Large Language Models (LLMs) for graph learning. However, most fusion strategies are applied uniformly across all nodes and attain only small overall performance gains. We argue this result stems from aggregate metrics that obscure when LLMs provide benefit, inhibiting actionable signals for new strategies. In this work, we reframe LLM-GNN fusion around nodes where GNNs typically falter. We first show that performance can significantly differ between GNNs and LLMs, with each excelling on distinct structural patterns, such as local homophily. To leverage this finding, we propose GLANCE (GNN with LLM Assistance for Neighbor- and Context-aware Embeddings), a framework that invokes an LLM to refine a GNN's prediction. GLANCE employs a lightweight router that, given inexpensive per-node signals, decides whether to query the LLM. Since the LLM calls are non-differentiable, the router is trained with an advantage-based objective that compares the utility of querying the LLM against relying solely on the GNN. Across multiple benchmarks, GLANCE achieves the best performance balance across node subgroups, achieving significant gains on heterophilous nodes (up to $+13\%$) while simultaneously achieving top overall performance. Our findings highlight the value of adaptive, node-aware GNN-LLM architectures, where selectively invoking the LLM enables scalable deployment on large graphs without incurring high computational costs.