{"slug": "semi-supervised-text-attributed-graph-distillation", "title": "Semi-Supervised Text-Attributed Graph Distillation", "summary": "Researchers propose a semi-supervised framework called WSD for distilling text-attributed graphs (TAGs) that integrates graph topology with textual semantics. The method uses dual-pathway encoders and Wasserstein Distance-based graph sketching to generate human-readable summaries, achieving state-of-the-art performance-compression trade-offs on GNN and LLM downstream tasks.", "body_md": "arXiv:2607.20477v1 Announce Type: new\nAbstract: {\\em Text-Attributed Graphs} (TAGs) have emerged as an expressive data model for integrating graph topology with rich textual semantics. Existing representation learning methods over TAGs suffer from severe scalability bottlenecks, particularly together with {\\em Large Language Models} (LLMs). While data distillation offers a promising data-centric solution, existing methods fail to capture the complex interplay between graph and text modalities, struggle with the label scarcity inherent in semi-supervised settings, and lack the ability to produce the human-readable textual attributes required for downstream LLM-based tasks.\nTo address these challenges, we propose \\algo{}, a unified semi-supervised framework guided by the {\\em Wasserstein Distance} (WSD). Grounded in our empirical findings on real TAGs, \\algo{} introduces a graph-text collaborative encoding module that utilizes dual-pathway encoders (graph-aware and -free) within a collaborative self-training scheme to harvest reliable pseudo-labels and fuse complementary graph-text features. Furthermore, we develop a theoretically grounded WSD-based graph sketching algorithm and a cost-effective LLM text synthesis module, which leverages cluster-based keyword extraction to generate coherent, human-readable summaries for condensed nodes. Extensive experiments on benchmark datasets demonstrate that \\algo{} achieves a state-of-the-art performance-compression trade-off in terms of both GNN- and LLM-based downstream tasks, enabling effective and efficient TAG learning or analytics.", "url": "https://wpnews.pro/news/semi-supervised-text-attributed-graph-distillation", "canonical_source": "https://arxiv.org/abs/2607.20477", "published_at": "2026-07-24 04:00:00+00:00", "updated_at": "2026-07-24 04:07:41.684190+00:00", "lang": "en", "topics": ["machine-learning", "large-language-models"], "entities": ["WSD", "Text-Attributed Graphs", "Large Language Models", "Wasserstein Distance"], "alternates": {"html": "https://wpnews.pro/news/semi-supervised-text-attributed-graph-distillation", "markdown": "https://wpnews.pro/news/semi-supervised-text-attributed-graph-distillation.md", "text": "https://wpnews.pro/news/semi-supervised-text-attributed-graph-distillation.txt", "jsonld": "https://wpnews.pro/news/semi-supervised-text-attributed-graph-distillation.jsonld"}}