Summary of Distance-restricted Explanations: Theoretical Underpinnings & Efficient Implementation, by Yacine Izza et al.
Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementation
by Yacine Izza, Xuanxiang Huang, Antonio Morgado, Jordi Planes, Alexey Ignatiev, Joao Marques-Silva
First submitted to arxiv on: 14 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Logic-Based XAI approach offers rigorous guarantees of computed explanations, addressing the trust issues in complex machine learning (ML) models. The research focuses on developing novel algorithms to scale up the performance of logic-based explainers for computing and enumerating ML model explanations with a large number of inputs. By leveraging distance-restricted explanations, the study aims to bridge the gap between adversarial robustness and explanation quality, paving the way for safer high-stakes applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper solves the problem of making complex machine learning models more understandable by developing new algorithms to explain how they work. The goal is to make it possible to understand ML model explanations even when there are many inputs to consider. This will help people trust ML models in important situations. |
Keywords
» Artificial intelligence » Machine learning
