Concept 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 a model's sensitivity and possible biases to a given concept. In this paper, we extend CAVs from post-hoc analysis to ante-hoc training in order to reduce model bias through fine-tuning using an additional Concept Loss. Concepts were defined on the final layer of the network in the past. We generalize it to intermediate layers using class prototypes. This facilitates class learning in the last convolution layer, which is known to be most informative. We also introduce Concept Distillation to create richer concepts using a pre-trained knowledgeable model as the teacher. Our method can sensitize or desensitize a model towards concepts. We show applications of concept-sensitive training to debias several classification problems. We also use concepts to induce prior knowledge into IID, a reconstruction problem. Concept-sensitive training can improve model interpretability, reduce biases, and induce prior knowledge. Please visit https://avani17101.github.io/Concept-Distilllation/ for code and more details.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
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, im…
Explainable ModelsKnowledge DistillationmodelMulti-Task LearningHuman-Centered Concept Explanations for Neural Networks
Understanding complex machine learning models such as deep neural networks with explanations is crucial in various applications. Many explanations stem from the model perspective, and may not necessarily effectively comm…
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 MakingHuman-Centered Evaluation of Explanations
The NLP community are increasingly interested in providing explanations for NLP models to help people make sense of model behavior and potentially improve human interaction with models. In addition to computational chall…
Less is More: Discovering Concise Network Explanations
We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automat…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)