GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Sinha, Aarush
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918156057968640
author Sinha, Aarush
author_facet Sinha, Aarush
contents Integrating Pre-trained Language Models (PLMs) with Graph Neural Networks (GNNs) remains a central challenge in text-rich heterophilic graph learning. We propose a novel integration framework that enables effective fusion between powerful pre-trained text encoders and Relational Graph Convolutional Networks (R-GCNs). Our method enhances the alignment of textual and structural representations through a bidirectional fusion mechanism and contrastive node-level optimization. To evaluate the approach, we train two variants using different PLMs: Snowflake-Embed (state-of-the-art) and GTE-base, each paired with an R-GCN backbone. Experiments on five heterophilic benchmarks demonstrate that our integration method achieves state-of-the-art results on four datasets, surpassing existing GNN and large language model-based approaches. Notably, Snowflake-Embed + R-GCN improves accuracy on the Texas dataset by over 8\% and on Wisconsin by nearly 5\%. These results highlight the effectiveness of our fusion strategy for advancing text-rich graph representation learning.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classification
Sinha, Aarush
Computation and Language
Artificial Intelligence
Machine Learning
Integrating Pre-trained Language Models (PLMs) with Graph Neural Networks (GNNs) remains a central challenge in text-rich heterophilic graph learning. We propose a novel integration framework that enables effective fusion between powerful pre-trained text encoders and Relational Graph Convolutional Networks (R-GCNs). Our method enhances the alignment of textual and structural representations through a bidirectional fusion mechanism and contrastive node-level optimization. To evaluate the approach, we train two variants using different PLMs: Snowflake-Embed (state-of-the-art) and GTE-base, each paired with an R-GCN backbone. Experiments on five heterophilic benchmarks demonstrate that our integration method achieves state-of-the-art results on four datasets, surpassing existing GNN and large language model-based approaches. Notably, Snowflake-Embed + R-GCN improves accuracy on the Texas dataset by over 8\% and on Wisconsin by nearly 5\%. These results highlight the effectiveness of our fusion strategy for advancing text-rich graph representation learning.
title GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classification
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2503.05763