Authors: Yacine Izza, Xuanxiang Huang, Antonio Morgado, Jordi Planes, Alexey Ignatiev, Joao Marques-Silva

Published on: May 14, 2024

Impact Score: 7.6

Arxiv code: Arxiv:2405.08297

Summary

• What is new: Introduction of novel algorithms for scaling up the performance of logic-based explainers to handle machine learning models with a large number of inputs.
• Why this is important: Logic-based XAI struggles with the complexity of logic reasoning for highly complex ML models, particularly with a large number of inputs.
• What the research proposes: Developing enhanced algorithms that effectively scale logic-based explainability for complex machine learning models with extensive inputs.
• Results: The novel algorithms improved the scalability and performance of logic-based explainers, making it feasible to compute and enumerate explanations for models with numerous inputs.

Technical Details

Technological frameworks used: nan

Models used: Logic-based XAI models

Data used: nan

Potential Impact

High-stakes industries such as healthcare, finance, and autonomous driving that rely on complex ML models for critical decision-making could benefit significantly.

Want to implement this idea in a business?

We have generated a startup concept here: ClarifyAI.