Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
This work addresses the need for more interpretable AI by providing clearer explanations for complex models, though it is incremental as it builds on existing attribution methods.
The paper tackles the problem of entangled explanations in neural network predictions by proposing methods to extract relevant subspaces that capture distinct activation patterns, resulting in disentangled explanations that compare favorably to state-of-the-art techniques on benchmarks and use cases.
Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. Explanations often take the form of a heatmap identifying input features (e.g. pixels) that are relevant to the model's decision. These explanations, however, entangle the potentially multiple factors that enter into the overall complex decision strategy. We propose to disentangle explanations by extracting at some intermediate layer of a neural network, subspaces that capture the multiple and distinct activation patterns (e.g. visual concepts) that are relevant to the prediction. To automatically extract these subspaces, we propose two new analyses, extending principles found in PCA or ICA to explanations. These novel analyses, which we call principal relevant component analysis (PRCA) and disentangled relevant subspace analysis (DRSA), maximize relevance instead of e.g. variance or kurtosis. This allows for a much stronger focus of the analysis on what the ML model actually uses for predicting, ignoring activations or concepts to which the model is invariant. Our approach is general enough to work alongside common attribution techniques such as Shapley Value, Integrated Gradients, or LRP. Our proposed methods show to be practically useful and compare favorably to the state of the art as demonstrated on benchmarks and three use cases.