New benchmark TILBench surveys tabular imbalanced learning methods

A new survey and benchmark called TILBench has been released, addressing the persistent challenge of imbalanced learning in tabular data applications. The research, authored by Jiaqi Luo and colleagues, systematically categorizes existing imbalance-handling strategies and empirically evaluates over 40 methods across 57 datasets. Findings indicate that no single method is universally superior; effectiveness is highly dependent on specific dataset characteristics and computational limitations, leading to practical recommendations for method selection. AI

IMPACT Provides a standardized benchmark and practical guidance for selecting imbalanced learning methods in tabular data applications.

RANK_REASON The cluster contains an academic paper detailing a new benchmark and survey. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Hugging Face
• Jiaqi Luo
• TILBench

• paper
• other

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