Semi-Supervised Text-Attributed Graph Distillation

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.

arXiv:2607.20477v1 Announce Type: new Abstract: {\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. To 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.