On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis
This addresses the problem of demystifying black-box deep learning systems for researchers and practitioners in Explainable AI, though it is incremental as it builds on existing symbolic methods.
The paper tackles the challenge of interpreting hidden neuron activations in deep learning by introducing a model-agnostic post-hoc method that uses a Wikipedia-derived concept hierarchy and OWL-reasoning-based Concept Induction to attach meaningful class expressions as explanations to neurons. Results show the method provides a competitive edge in quantitative and qualitative evaluations compared to prior work.
A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would help answer the question of what a deep learning system internally detects as relevant in the input, demystifying the otherwise black-box nature of deep learning systems. The state of the art indicates that hidden node activations can, in some cases, be interpretable in a way that makes sense to humans, but systematic automated methods that would be able to hypothesize and verify interpretations of hidden neuron activations are underexplored. This is particularly the case for approaches that can both draw explanations from substantial background knowledge, and that are based on inherently explainable (symbolic) methods. In this paper, we introduce a novel model-agnostic post-hoc Explainable AI method demonstrating that it provides meaningful interpretations. Our approach is based on using a Wikipedia-derived concept hierarchy with approximately 2 million classes as background knowledge, and utilizes OWL-reasoning-based Concept Induction for explanation generation. Additionally, we explore and compare the capabilities of off-the-shelf pre-trained multimodal-based explainable methods. Our results indicate that our approach can automatically attach meaningful class expressions as explanations to individual neurons in the dense layer of a Convolutional Neural Network. Evaluation through statistical analysis and degree of concept activation in the hidden layer show that our method provides a competitive edge in both quantitative and qualitative aspects compared to prior work.