Text-attributed Graph Condensation via Text Selection and Attribute Matching

2026-06-02 · Haowei Han, Yuxiang Wang, Guojia Wan, Hao Wang, Shanshan Feng, Hao Huang, Jiawei Jiang, Xiao Yan arxiv

Text-Attributed Graph (TAG) is an important type of graph structured data, where each node has a text description. TAG models usually train a Graph Neural Network (GNN) and language model jointly, which leads to high space and time consumption, especially on large datasets. To mitigate this, we propose TAGSAM, a condensation method that compresses TAGs while preserving training accuracy. TAGSAM comes with two key designs, i.e., subgraph text Selection and Attribute similarity Matching, which compress the text description and graph topology of TAG, respectively. For the texts, subgraph text selection selects and merges representative text chunks from multiple related text descriptions by maximizing mutual information. For the graph topology, popular condensation methods based on Matching Training Trajectories (MTT) suffer from high variance, which hinders accuracy. Our attribute similarity matching mitigates this issue by aligning stable similarity matrices. We evaluate TAGSAM against six state-of-the-art baselines, where it showcases superior performance. For the same compressed size, TAGSAM improves upon the best-performing baseline by an average of 4.9% in accuracy. Furthermore, it maintains competitive training accuracy even when the TAG is condensed to just 1% size. Our code is available at https://github.com/SundayVHan/TAGSAM

📄 PDF Abstract BibTeX arXiv:2606.03839

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural Network

DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs

2026-01-23 · Zekai Chen, Haodong Lu, Xunkai Li, Henan Sun 외 arxiv

Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. With the rise of large language models (LLMs), textual attributes in FGL graphs are gaining attention. Text-attributed …

Federated Learning Graph Learning

Bonsai: Gradient-free Graph Condensation for Node Classification

2024-10-23 · Mridul Gupta, Samyak Jain, Vansh Ramani, Hariprasad Kodamana 외

Graph condensation has emerged as a promising avenue to enable scalable training of GNNs by compressing the training dataset while preserving essential graph characteristics. Our study uncovers significant shortcomings i…

Classification Node Classification

Training-free Heterogeneous Graph Condensation via Data Selection

2024-12-20 · Yuxuan Liang, Wentao Zhang, Xinyi Gao, Ling Yang 외

Efficient training of large-scale heterogeneous graphs is of paramount importance in real-world applications. However, existing approaches typically explore simplified models to mitigate resource and time overhead, negle…

Graph Generation

Anchor-guided Hypergraph Condensation with Dual-level Discrimination

2026-05-11 · Fan Li, Xiaoyang Wang, Chen Chen, Wenjie Zhang arxiv

The increasing prevalence of large-scale hypergraphs poses significant computational challenges for hypergraph neural network (HNN) training. To address this, hypergraph condensation (HGC) distills large real hypergraphs…

Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition

2024-05-22 · Xinyi Gao, Guanhua Ye, Tong Chen, Wentao Zhang 외

The increasing prevalence of large-scale graphs poses a significant challenge for graph neural network training, attributed to their substantial computational requirements. In response, graph condensation (GC) emerges as…