Graph Concept Bottleneck Models
Concept Bottleneck Models (CBMs) provide explicit interpretations for deep neural networks through concepts and allow intervention with concepts to adjust final predictions. Existing CBMs assume concepts are conditionally independent given labels and isolated from each other, ignoring the hidden relationships among concepts. However, the set of concepts in CBMs often has an intrinsic structure where concepts are generally correlated: changing one concept will inherently impact its related concepts. To mitigate this limitation, we propose GraphCBMs: a new variant of CBM that facilitates concept relationships by constructing latent concept graphs, which can be combined with CBMs to enhance model performance while retaining their interpretability. Our experiment results on real-world image classification tasks demonstrate Graph CBMs offer the following benefits: (1) superior in image classification tasks while providing more concept structure information for interpretability; (2) able to utilize latent concept graphs for more effective interventions; and (3) robust in performance across different training and architecture settings.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationSimilar Papers 제목 키워드 기반
Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning
We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, concept bottleneck, where each concept is a meaningful phrase, and predi…
Graph LearningGraph Integrated Multimodal Concept Bottleneck Model
With growing demand for interpretability in deep learning, especially in high stakes domains, Concept Bottleneck Models (CBMs) address this by inserting human understandable concepts into the prediction pipeline, but the…
Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer
Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, which is often hidden within their black-bo…
Relational Concept Bottleneck Models
The design of interpretable deep learning models working in relational domains poses an open challenge: interpretable deep learning methods, such as Concept Bottleneck Models (CBMs), are not designed to solve relational …
Deep Learningimage-classificationImage ClassificationKnowledge Graphs+1Learning Concept Bottleneck Models from Mechanistic Explanations
Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to l…
Knowledge Graphs