Parallelized dichotomic search with feature-disjunction pruning computes distance-restricted contrastive explanations for deep neural networks far faster than a sequential baseline, demonstrated on MNIST and GTSRB.
VeriX: Towards Verified Explainability of Deep Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present VeriX (Verified eXplainability), a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models. We build such explanations and counterfactuals iteratively using constraint solving techniques and a heuristic based on feature-level sensitivity ranking. We evaluate our method on image recognition benchmarks and a real-world scenario of autonomous aircraft taxiing.
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Contrastive Explanations on Demand
Parallelized dichotomic search with feature-disjunction pruning computes distance-restricted contrastive explanations for deep neural networks far faster than a sequential baseline, demonstrated on MNIST and GTSRB.