压缩带文本的图数据，保持训练精度的同时大幅减小规模。
Text-attributed Graph Condensation via Text Selection and Attribute Matching
- 通过选择关键文本片段和匹配属性相似性来压缩图结构
- 在1%数据量下仍保持接近原始模型的准确率
- 适合处理大规模图文图数据的高效训练场景
文本属性图（TAG）是一种重要图结构数据，每个节点附带文本描述。现有方法联合训练图神经网络与语言模型，导致空间和时间开销巨大，尤其在大规模数据上。为此，我们提出TAGSAM，一种压缩方法，在保留训练精度的前提下压缩TAG。该方法包含两个核心设计：子图文本选择与属性相似性匹配，分别用于压缩文本描述和图拓扑。文本方面，通过最大化互信息选择并合并多个相关文本中的代表性片段；图拓扑方面，传统基于训练轨迹匹配（MTT）的方法存在高方差问题，我们通过对齐稳定相似性矩阵缓解此问题。在六个先进基线上的评估显示，相同压缩比例下，TAGSAM平均提升基线4.9%准确率；即使压缩至原图1%大小，仍保持良好训练精度。代码已公开于https://github.com/SundayVHan/TAGSAM。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。