通过社区结构感知提升文本分类，避免类别边界模糊。
ModTGCN: Modularity-aware Graph Neural Networks for Text Classification
- 引入模块度目标，强化文档间的类内聚性
- 在Ohsumed等低同质性数据集上准确率显著提升
- 适合处理复杂、类别分散的文本分类任务
基于图的文本分类模型通常依赖局部邻域聚合，忽视了语义文档图中强存在的类一致聚类结构。忽略这一特性会导致类别边界模糊和过平滑问题。我们提出ModTGCN，一种面向文本分类的模块度感知图神经网络，通过联合优化交叉熵与基于模块度的辅助目标，促进类一致的文档社区形成，同时保持判别性表示。模块度在由Transformer嵌入（预训练或微调）构建的文档-文档相似性图上计算。为提升可扩展性，将原始异构TextGCN图分解为独立的文档-词和词-词组件，实现2倍至10倍的训练加速。我们进一步研究了图构建策略、标签感知边重加权及模块度优化的监督选择。在五个基准数据集上的实验表明性能持续提升，尤其在Ohsumed和20NG等复杂、低同质性数据集上效果更显著。
原文摘要 · Abstract (English)
Graph-based text classification models typically rely on local neighborhood aggregation and overlook global community structure, despite semantic document graphs exhibiting strong class-consistent clustering. Ignoring this can blur class boundaries and lead to over-smoothing. We propose ModTGCN, a modularity-aware graph neural network for text classification that jointly optimizes cross-entropy and a modularity-based auxiliary objective to promote class-coherent document communities while preserving discriminative representations. The modularity term is computed on a document-document similarity graph derived from transformer embeddings (pretrained or fine-tuned). To improve scalability, we decouple the original heterogeneous TextGCN graph into separate document-word and word-word components, achieving 2x-10x faster training. We further study graph construction strategies, label-aware edge reweighting, and supervision choices for modularity optimization. Experiments on five benchmarks show consistent gains, with larger improvements on complex, low homophily datasets such as Ohsumed and 20NG.
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。