ConceptDistil: Model-Agnostic Distillation of Concept Explanations
Concept-based explanations aims to fill the model interpretability gap for non-technical humans-in-the-loop. Previous work has focused on providing concepts for specific models (eg, neural networks) or data types (eg, images), and by either trying to extract concepts from an already trained network or training self-explainable models through multi-task learning. In this work, we propose ConceptDistil, a method to bring concept explanations to any black-box classifier using knowledge distillation. ConceptDistil is decomposed into two components:(1) a concept model that predicts which domain concepts are present in a given instance, and (2) a distillation model that tries to mimic the predictions of a black-box model using the concept model predictions. We validate ConceptDistil in a real world use-case, showing that it is able to optimize both tasks, bringing concept-explainability to any black-box model.
Code (0)
등록된 구현이 없습니다.
Tasks
Explainable ModelsKnowledge DistillationmodelMulti-Task LearningSimilar Papers 제목 키워드 기반
DiConStruct: Causal Concept-based Explanations through Black-Box Distillation
Model interpretability plays a central role in human-AI decision-making systems. Ideally, explanations should be expressed using human-interpretable semantic concepts. Moreover, the causal relations between these concept…
Decision MakingConLUX: Concept-Based Local Unified Explanations
With the rapid advancements of various machine learning models, there is a significant demand for model-agnostic explanation techniques, which can explain these models across different architectures. Mainstream model-agn…
An Axiomatic Approach to Model-Agnostic Concept Explanations
Concept explanation is a popular approach for examining how human-interpretable concepts impact the predictions of a model. However, most existing methods for concept explanations are tailored to specific models. To addr…
Model SelectionConcept Distillation: Leveraging Human-Centered Explanations for Model Improvement
Humans use abstract concepts for understanding instead of hard features. Recent interpretability research has focused on human-centered concept explanations of neural networks. Concept Activation Vectors (CAVs) estimate …
Explanation Bottleneck Models
Recent concept-based interpretable models have succeeded in providing meaningful explanations by pre-defined concept sets. However, the dependency on the pre-defined concepts restricts the application because of the limi…
Decoder