Failing Conceptually: Concept-Based Explanations of Dataset Shift
Despite their remarkable performance on a wide range of visual tasks, machine learning technologies often succumb to data distribution shifts. Consequently, a range of recent work explores techniques for detecting these shifts. Unfortunately, current techniques offer no explanations about what triggers the detection of shifts, thus limiting their utility to provide actionable insights. In this work, we present Concept Bottleneck Shift Detection (CBSD): a novel explainable shift detection method. CBSD provides explanations by identifying and ranking the degree to which high-level human-understandable concepts are affected by shifts. Using two case studies (dSprites and 3dshapes), we demonstrate how CBSD can accurately detect underlying concepts that are affected by shifts and achieve higher detection accuracy compared to state-of-the-art shift detection methods.
Code (1)
Similar Papers 제목 키워드 기반
Codes, Functions, and Causes: A Critique of Brette's Conceptual Analysis of Coding
In a recent article, Brette argues that coding as a concept is inappropriate for explanations of neurocognitive phenomena. Here, we argue that Brette's conceptual analysis mischaracterizes the structure of causal claims …
Comprehensible Counterfactual Explanation on Kolmogorov-Smirnov Test
The Kolmogorov-Smirnov (KS) test is popularly used in many applications, such as anomaly detection, astronomy, database security and AI systems. One challenge remained untouched is how we can obtain an explanation on why…
Anomaly DetectionAstronomycounterfactualCounterfactual ExplanationRethinking Explainability in the Era of Multimodal AI
While multimodal AI systems (models jointly trained on heterogeneous data types such as text, time series, graphs, and images) have become ubiquitous and achieved remarkable performance across high-stakes applications, t…
Diverse Concept Proposals for Concept Bottleneck Models
Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number of human-interpretable concepts in the da…
Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice
Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial int…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)