Papers › Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex

Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex

16 Apr 2025arXiv:2504.12474archive 2025-07-28

Azadeh Beiranvand, Seyed Mehdi Vahidipour

Text-attributed graphs (TAGs) present unique challenges in representation learning by requiring models to capture both the semantic richness of node-associated texts and the structural dependencies of the graph. While graph neural networks (GNNs) excel at modeling topological information, they lack the capacity to process unstructured text. Conversely, large language models (LLMs) are proficient in text understanding but are typically unaware of graph structure. In this work, we propose BiGTex (Bidirectional Graph Text), a novel architecture that tightly integrates GNNs and LLMs through stacked Graph-Text Fusion Units. Each unit allows for mutual attention between textual and structural representations, enabling information to flow in both directions, text influencing structure and structure guiding textual interpretation. The proposed architecture is trained using parameter-efficient fine-tuning (LoRA), keeping the LLM frozen while adapting to task-specific signals. Extensive experiments on five benchmark datasets demonstrate that BiGTex achieves state-of-the-art performance in node classification and generalizes effectively to link prediction. An ablation study further highlights the importance of soft prompting and bi-directional attention in the model's success.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Azadeh297/BiGTex officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Link PredictionNode ClassificationRepresentation Learningparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Property Prediction ogbn-arxiv BiGTex Ext. data Yes #1 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv BiGTex Number of params 5332968 #1 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv BiGTex Test Accuracy 0.8851 ± 0.0027 #1 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv BiGTex Validation Accuracy 0.8934 ± 0.0011 #1 of 86 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections