New benchmark TAHB integrates text-attributed hypergraphs for AI research

Researchers have introduced TAHB, the first public benchmark designed to integrate text-attributed hypergraph structures with raw textual data. This benchmark comprises 10 real-world datasets spanning e-commerce, academia, movies, and politics networks. Experiments using TAHB demonstrate that incorporating LLM-enhanced textual semantics improves hypergraph learning performance, with a combined approach of structural and textual information yielding the best results for LLM-based prediction. AI

IMPACT This benchmark is expected to foster future research at the intersection of hypergraph learning and language models.

RANK_REASON The cluster describes a new academic paper introducing a benchmark for a specific area of AI research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• e-commerce
• Large Language Models
• LLM-as-Enhancer
• LLM-as-Predictor
• politics networks
• Pretrained Language Models

• paper
• infra

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