Summary of Cogs: Causality Constrained Counterfactual Explanations Using Goal-directed Asp, by Sopam Dasgupta et al.
CoGS: Causality Constrained Counterfactual Explanations using goal-directed ASP
by Sopam Dasgupta, Joaquín Arias, Elmer Salazar, Gopal Gupta
First submitted to arxiv on: 11 Jul 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG); Logic in Computer Science (cs.LO)
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 CoGS (Counterfactual Generation with s(CASP)) framework aims to provide transparency in machine learning models by generating counterfactual explanations for rule-based algorithms, such as FOLD-SE. The framework utilizes the goal-directed Answer Set Programming system s(CASP) to identify causally consistent changes to attribute values that could have led to a different outcome. This approach enables users to understand how decisions were made and why certain outcomes occurred. By considering causal dependencies between features, CoGS finds a path from an undesired outcome to a desired one using counterfactuals. The framework’s evaluation is presented in the paper. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The CoGS framework helps make machine learning models more transparent by explaining their decision-making processes. It does this by finding changes that could have led to a different outcome, taking into account how features are connected. This approach is important for situations where people need to know why certain decisions were made, like loan approvals or hiring. The framework uses a special kind of programming called s(CASP) and works with rule-based machine learning models, specifically the FOLD-SE algorithm. |
Keywords
» Artificial intelligence » Machine learning
