New LandscapeSHAP method assigns credit in topological data analysis

Researchers have developed LandscapeSHAP, a novel method for attributing machine learning model predictions to specific features derived from topological data analysis. This approach specifically addresses the challenge of assigning credit to individual points within a persistence diagram, a complex data structure used in topological data analysis. The method provides an exact solution for linear models and offers an efficient Monte Carlo sampling approach for nonlinear models, ensuring fair credit allocation based on Shapley value axioms. AI

IMPACT Introduces a novel method for feature attribution in machine learning, specifically for data derived from topological analysis.

RANK_REASON Academic paper introducing a new methodology for feature attribution in machine learning applied to topological data analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• LandscapeSHAP
• machine learning
• Nikola Milićević
• persistence landscape
• Shapley Values
• topological data analysis

• paper
• other

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