paper-with-me

홈 › Papers

Explaining the root causes of unit-level changes

2022-06-26 · Kailash Budhathoki, George Michailidis, Dominik Janzing

Existing methods of explainable AI and interpretable ML cannot explain change in the values of an output variable for a statistical unit in terms of the change in the input values and the change in the "mechanism" (the function transforming input to output). We propose two methods based on counterfactuals for explaining unit-level changes at various input granularities using the concept of Shapley values from game theory. These methods satisfy two key axioms desirable for any unit-level change attribution method. Through simulations, we study the reliability and the scalability of the proposed methods. We get sensible results from a case study on identifying the drivers of the change in the earnings for individuals in the US.

📄 PDF Abstract BibTeX arXiv:2206.12986

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Counterfactuals 설명 없음

Similar Papers 제목 키워드 기반

Explaining Concept Drift through the Evolution of Group Counterfactuals

2025-09-11 · Ignacy Stępka, Jerzy Stefanowski arxiv

Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-studied topic, explaining how and why the …

A Framework for Explainable Concept Drift Detection in Process Mining

2021-05-27 · Jan Niklas Adams, Sebastiaan J. van Zelst, Lara Quack, Kathrin Hausmann 외

Rapidly changing business environments expose companies to high levels of uncertainty. This uncertainty manifests itself in significant changes that tend to occur over the lifetime of a process and possibly affect its pe…

Drift Detection

Automating Detection and Root-Cause Analysis of Flaky Tests in Quantum Software

2026-03-09 · Janakan Sivaloganathan, Ainaz Jamshidi, Andriy Miranskyy, Lei Zhang arxiv

Like classical software, quantum software systems rely on automated testing. However, their inherently probabilistic outputs make them susceptible to quantum flakiness -- tests that pass or fail inconsistently without co…

Identifying Patient-Specific Root Causes of Disease

2022-05-23 · Eric V. Strobl, Thomas A. Lasko

Complex diseases are caused by a multitude of factors that may differ between patients. As a result, hypothesis tests comparing all patients to all healthy controls can detect many significant variables with inconsequent…

Causal InferenceDiagnostic

Automatic Cause Detection of Performance Problems in Web Applications

2021-03-08 · Quentin Fournier, Naser Ezzati-Jivan, Daniel Aloise, Michel R. Dagenais

The execution of similar units can be compared by their internal behaviors to determine the causes of their potential performance issues. For instance, by examining the internal behaviors of different fast or slow web re…

Clustering