New TaLK method distills text-attributed graph datasets efficiently

Researchers have developed TaLK, a novel dataset distillation method specifically designed for text-attributed graphs (TAGs). This approach couples a language model with a graph-aware neural tangent kernel, enabling efficient distillation without repeated joint training on the full dataset. TaLK effectively captures both textual semantics and graph structure, achieving up to 97% of full-dataset performance using only 1% of synthetic data in experiments. AI

IMPACT This method could significantly reduce the computational cost of training models on text-attributed graph data.

RANK_REASON The cluster contains a research paper detailing a new method for dataset distillation in machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• ScienceCast
• TaLK
• Yeongho Kim

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →