{"slug": "modtgcn-modularity-aware-graph-neural-networks-for-text-classification", "title": "ModTGCN: Modularity-aware Graph Neural Networks for Text Classification", "summary": "Researchers 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. The model decouples the heterogeneous TextGCN graph into separate document-word and word-word components, achieving 2x-10x faster training, and shows consistent gains on five benchmarks, with larger improvements on complex datasets like Ohsumed and 20NG.", "body_md": "arXiv:2606.23694v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/modtgcn-modularity-aware-graph-neural-networks-for-text-classification", "canonical_source": "https://arxiv.org/abs/2606.23694", "published_at": "2026-06-24 04:00:00+00:00", "updated_at": "2026-06-24 04:15:06.816328+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "natural-language-processing", "ai-research"], "entities": ["ModTGCN", "TextGCN", "Ohsumed", "20NG"], "alternates": {"html": "https://wpnews.pro/news/modtgcn-modularity-aware-graph-neural-networks-for-text-classification", "markdown": "https://wpnews.pro/news/modtgcn-modularity-aware-graph-neural-networks-for-text-classification.md", "text": "https://wpnews.pro/news/modtgcn-modularity-aware-graph-neural-networks-for-text-classification.txt", "jsonld": "https://wpnews.pro/news/modtgcn-modularity-aware-graph-neural-networks-for-text-classification.jsonld"}}