mlsanityData to 14 Oct 2026

Text-attributed Graph Condensation via Text Selection and Attribute Matching

arXiv 2606.03839 ↗First posted 2 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 2 Jun 2026.

Builds on

24 of 45 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  8. 2016An overview of gradient descent optimization algorithmscited by 1,033
  9. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  10. 2021Graph Condensation for Graph Neural Networkscited by 150
  11. 2023Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Promptingcited by 62
  12. 2024GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphscited by 58
12 more
  1. 2023Fast Graph Condensation with Structure-based Neural Tangent Kernelcited by 36
  2. 2023ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddingscited by 32
  3. 2023On the Generalization of Multi-modal Contrastive Learningcited by 30
  4. 2024Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partitioncited by 23
  5. 2024EXGC: Bridging Efficiency and Explainability in Graph Condensationcited by 20
  6. 2022The Power of Uniform Sampling for Coresetscited by 18
  7. 2024Disentangled Condensation for Large-scale Graphscited by 10
  8. 2024Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep Networkscited by 6
  9. 2024Retrofitting Temporal Graph Neural Networks with Transformercited by 5
  10. 2024Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domainscited by 5
  11. 2024Towards Scalable and Deep Graph Neural Networks via Noise Maskingcited by 4
  12. 2025Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graphcited by 1

Built on by

Not cited yet.