Summary of Cogs: Model Agnostic Causality Constrained Counterfactual Explanations Using Goal-directed Asp, by Sopam Dasgupta et al.
CoGS: Model Agnostic Causality Constrained Counterfactual Explanations using goal-directed ASP
by Sopam Dasgupta, Joaquín Arias, Elmer Salazar, Gopal Gupta
First submitted to arxiv on: 30 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 paper introduces CoGS (Counterfactual Generation with s(CASP)), a model-agnostic framework for generating counterfactual explanations for classification models. The framework uses the goal-directed Answer Set Programming system s(CASP) to compute realistic and causally consistent modifications to feature values, accounting for causal dependencies between them. By leveraging rule-based machine learning algorithms (RBML), notably the FOLD-SE algorithm, CoGS extracts the underlying logic of a statistical model to generate counterfactual solutions. The framework is capable of tracing a step-by-step path from an undesired outcome to a desired one, offering interpretable and actionable explanations of the changes required to achieve the desired outcome. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary CoGS helps people understand why machines make certain decisions by showing how things would have had to be different for a better outcome. This is important because we want to know what’s behind an unfair loan rejection or why someone didn’t get hired. The framework works with any machine learning model and can even explain complex decisions. |
Keywords
» Artificial intelligence » Classification » Machine learning » Statistical model
