Aggregating explanation methods for stable and robust explainability.
By Laura Rieger, Lars Kai Hansen. 2019
16 citations recorded by the source corpus.
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. We provide evidence that the aggregation is better at identifying important features, than on individual methods. Adversarial attacks on explanations is a recent active research topic. As our second contribution, we present evidence that aggregate explanations are much more robust to attacks than individual explanation methods.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Chandan Singh
- Bin Yu
- Laura Rieger
- W. James Murdoch
- Xisen Jin
- John C. Duchi
- Francis R. Bach
- Martin J. Wainwright
Citations in the corpus
- Interpretations are useful: penalizing explanations to align neural networks with prior knowledge (2019, background): “They can be categorized as gradient-based (Springenberg et al., 2014; Sundararajan et al., 2017; Selvaraju et al., 2016; Baehrens et al., 2010; Rieger & Hansen, 2019), decomposition-based (Murdoch & Szlam, 2017; Shrikumar et al., 2016; Bach et al., 2015) and others (Dabkowski & Gal, 2017; Fong &…”