Lune

CVPR Findings2026

BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis

Rui Dong, Zitong Wang, Jiaxing Li, Weihuang Zheng, Youyong Kong

Abstract

Graph Neural Networks (GNNs) have been widely used in diverse brain network analysis tasks based on preprocessed functional magnetic resonance imaging (fMRI) data. However, their performances are constrained due to high feature sparsity and inherent limitations of domain knowledge within uni-modal neurographs. Meanwhile, large language models (LLMs) have demonstrated powerful representation capabilities. Combining LLMs with GNNs presents a promising direction for brain network analysis. While LLMs and MLLMs have emerged in neuroscience, integration of LLMs with graph-based data remains unexplored. In this work, we deal with these issues by incorporating LLM's powerful representation and generalization capabilities. Considering great cost for directly tuning LLMs, we instead function LLM as enhancer to boost GNN's performance on downstream tasks. Our method, namely BLEG, can be divided into three stages. We firstly prompt LLM to get augmented texts for fMRI graph data, then we design a "LLM-LM" instruction tuning method to get enhanced textual representations at a relatively lower cost. GNN is trained together for coarsened alignment. Finally we finetune an adapter after GNN for given downstream tasks. Alignment loss between LM and GNN logits is designed to further enhance GNN's representation. Extensive experiments on different datasets con-

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • One For All: Towards Training One Graph Model For All Classification Tasks cites GraphGPT: Graph Instruction Tuning for Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on8

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. Representing Long-Range Context for Graph Neural Networks with Global AttentionZhanghao Wu, Paras Jain, Matthew A. Wright, Azalia Mirhoseini et al.NeurIPS 2021 · 450 citations
  3. One For All: Towards Training One Graph Model For All Classification TasksHao Liu, Jiarui Feng, Lecheng Kong, Ningyue Liang et al.ICLR 2024 · 253 citations
  4. GraphGPT: Graph Instruction Tuning for Large Language ModelsJiabin Tang, Yuhao Yang, Wei Wei, Lei Shi et al.SIGIR 2024 · 182 citations
  5. Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation LearningXiaoxin He, Xavier Bresson, Thomas Laurent, Adam Perold et al.ICLR 2024 · 151 citations

Related papers

  1. Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized ApproachHang Gao, Chenhao Zhang, Fengge Wu, Changwen Zheng et al.AAAI 2025 · 6 citations
  2. 'Hello, World!': Making GNNs Talk with LLMsSunwoo Kim, Soo Yong Lee, Jaemin Yoo, Kijung ShinEMNLP Findings 2025
  3. Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud DetectionTairan Huang, Yili Wang, Qiutong Li, Changlong He et al.ACM MM 2025 · 10 citations
  4. Graph Neural Prompting with Large Language ModelsYijun Tian, Huan Song, Zichen Wang, Haozhu Wang et al.AAAI 2024 · 90 citations
  5. Each graph is a new language: Graph Learning with LLMsHuachi Zhou, Jiahe Du, Chuang Zhou, Chang Yang et al.ACL Findings 2025 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines