Relational Concept Bottleneck Models
This addresses the problem of interpretability in relational deep learning for researchers and practitioners, offering a novel hybrid approach that is incremental in bridging two existing methods.
The paper tackles the challenge of designing interpretable deep learning models for relational domains by proposing Relational Concept Bottleneck Models (R-CBMs), which combine the interpretability of Concept Bottleneck Models with the relational capabilities of Graph Neural Networks, achieving generalization performance matching existing black-box models and supporting concept-based explanations and test-time interventions.
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 problems, while relational deep learning models, such as Graph Neural Networks (GNNs), are not as interpretable as CBMs. To overcome these limitations, we propose Relational Concept Bottleneck Models (R-CBMs), a family of relational deep learning methods providing interpretable task predictions. As special cases, we show that R-CBMs are capable of both representing standard CBMs and message-passing GNNs. To evaluate the effectiveness and versatility of these models, we designed a class of experimental problems, ranging from image classification to link prediction in knowledge graphs. In particular we show that R-CBMs (i) match generalization performance of existing relational black-boxes, (ii) support the generation of quantified concept-based explanations, (iii) effectively respond to test-time interventions, and (iv) withstand demanding settings including out-of-distribution scenarios, limited training data regimes, and scarce concept supervisions.