Hierarchical interpretations for neural network predictions
This addresses the black-box nature of DNNs for users needing trust and diagnosis, though it is incremental as it builds on existing interpretation methods.
The paper tackles the problem of interpreting deep neural network predictions by introducing agglomerative contextual decomposition (ACD), which produces hierarchical clusters of input features to explain predictions, showing effectiveness in diagnosing errors and identifying bias on datasets like Stanford Sentiment Treebank and ImageNet.
Deep neural networks (DNNs) have achieved impressive predictive performance due to their ability to learn complex, non-linear relationships between variables. However, the inability to effectively visualize these relationships has led to DNNs being characterized as black boxes and consequently limited their applications. To ameliorate this problem, we introduce the use of hierarchical interpretations to explain DNN predictions through our proposed method, agglomerative contextual decomposition (ACD). Given a prediction from a trained DNN, ACD produces a hierarchical clustering of the input features, along with the contribution of each cluster to the final prediction. This hierarchy is optimized to identify clusters of features that the DNN learned are predictive. Using examples from Stanford Sentiment Treebank and ImageNet, we show that ACD is effective at diagnosing incorrect predictions and identifying dataset bias. Through human experiments, we demonstrate that ACD enables users both to identify the more accurate of two DNNs and to better trust a DNN's outputs. We also find that ACD's hierarchy is largely robust to adversarial perturbations, implying that it captures fundamental aspects of the input and ignores spurious noise.