Aggregating explanation methods for neural networks stabilizes explanationsDownload PDF

Laura Rieger, Lars Kai Hansen

25 Sep 2019 (modified: 24 Dec 2019)ICLR 2020 Conference Blind SubmissionReaders: Everyone
  • Original Pdf: pdf
  • TL;DR: We show in theory and in practice that combining multiple explanation methods for DNN benefits the explanation.
  • Abstract: Despite a growing literature on explaining neural networks, no consensus has been reached on how to explain a neural network decision or how to evaluate an explanation. Our contributions in this paper are twofold. First, we investigate schemes to combine explanation methods and reduce model uncertainty to obtain a single aggregated explanation. The aggregation is more robust and aligns better with the neural network than any single explanation method.. Second, we propose a new approach to evaluating explanation methods that circumvents the need for manual evaluation and is not reliant on the alignment of neural networks and humans decision processes.
  • Code:
  • Keywords: explainability, deep learning, interpretability, XAI
11 Replies