New framework trains interpretable AI models using bi-objective optimization

This paper introduces Interpretability-Guided Bi-objective Optimization (IGBO), a new framework designed to train models that are both accurate and interpretable. IGBO integrates structured domain knowledge by using a bi-objective formulation and encodes feature importance hierarchies into a Directed Acyclic Graph (DAG). The framework utilizes Temporal Integrated Gradients (TIG) to measure feature importance and proposes a novel Relative Importance Score for quantifying feature attribution over time. AI

IMPACT Introduces a novel framework for enhancing model interpretability, potentially aiding in the development of more trustworthy AI systems.

RANK_REASON This is a research paper detailing a new framework for model interpretability. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Central Limit Theorem
• Directed Acyclic Graph
• Interpretability-Guided Bi-objective Optimization
• Temporal Integrated Gradients

• paper
• other

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