Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209179910> ?p ?o ?g. }
- W3209179910 abstract "The demand for explainable machine learning (ML) models has been growing rapidly in recent years. Amongst the methods proposed to associate ML model predictions with human-understandable rationale, counterfactual explanations are one of the most popular. They consist of post-hoc rules derived from counterfactual examples (CFs), i.e., modified versions of input samples that result in alternative output responses from the predictive model to be explained. However, existing CF generation strategies either exploit the internals of specific models (e.g., random forests or neural networks), or depend on each sample's neighborhood, which makes them hard to be generalized for more complex models and inefficient for larger datasets. In this work, we aim to overcome these limitations and introduce a model-agnostic algorithm to generate optimal counterfactual explanations. Specifically, we formulate the problem of crafting CFs as a sequential decision-making task and then find the optimal CFs via deep reinforcement learning (DRL) with discrete-continuous hybrid action space. Differently from other techniques, our method is easily applied to any black-box model, as this resembles the environment that the DRL agent interacts with. In addition, we develop an algorithm to extract explainable decision rules from the DRL agent's policy, so as to make the process of generating CFs itself transparent. Extensive experiments conducted on several datasets have shown that our method outperforms existing CF generation baselines." @default.
- W3209179910 created "2021-11-08" @default.
- W3209179910 creator A5004145814 @default.
- W3209179910 creator A5008454216 @default.
- W3209179910 creator A5011299100 @default.
- W3209179910 creator A5044165871 @default.
- W3209179910 creator A5054352845 @default.
- W3209179910 creator A5054877470 @default.
- W3209179910 date "2021-10-22" @default.
- W3209179910 modified "2023-10-16" @default.
- W3209179910 title "ReLACE: Reinforcement Learning Agent for Counterfactual Explanations of Arbitrary Predictive Models" @default.
- W3209179910 cites W2121863487 @default.
- W3209179910 cites W2144366468 @default.
- W3209179910 cites W2201581102 @default.
- W3209179910 cites W2243397390 @default.
- W3209179910 cites W2739657930 @default.
- W3209179910 cites W2769421449 @default.
- W3209179910 cites W2803532212 @default.
- W3209179910 cites W2803974723 @default.
- W3209179910 cites W2804393646 @default.
- W3209179910 cites W2888487581 @default.
- W3209179910 cites W2891340972 @default.
- W3209179910 cites W2897417898 @default.
- W3209179910 cites W2909392392 @default.
- W3209179910 cites W2945315238 @default.
- W3209179910 cites W2951544639 @default.
- W3209179910 cites W2953945697 @default.
- W3209179910 cites W2963257680 @default.
- W3209179910 cites W2963312729 @default.
- W3209179910 cites W2963319332 @default.
- W3209179910 cites W2964126074 @default.
- W3209179910 cites W2979156612 @default.
- W3209179910 cites W2979997102 @default.
- W3209179910 cites W2989569331 @default.
- W3209179910 cites W2990881605 @default.
- W3209179910 cites W3023497337 @default.
- W3209179910 cites W3034616174 @default.
- W3209179910 cites W3034697737 @default.
- W3209179910 cites W3041133507 @default.
- W3209179910 cites W3043146651 @default.
- W3209179910 cites W3081364375 @default.
- W3209179910 cites W3092961465 @default.
- W3209179910 cites W3094613840 @default.
- W3209179910 cites W3099331386 @default.
- W3209179910 cites W3102161834 @default.
- W3209179910 cites W3104371626 @default.
- W3209179910 cites W3122175177 @default.
- W3209179910 cites W3125240708 @default.
- W3209179910 cites W3125997628 @default.
- W3209179910 hasPublicationYear "2021" @default.
- W3209179910 type Work @default.
- W3209179910 sameAs 3209179910 @default.
- W3209179910 citedByCount "0" @default.
- W3209179910 crossrefType "posted-content" @default.
- W3209179910 hasAuthorship W3209179910A5004145814 @default.
- W3209179910 hasAuthorship W3209179910A5008454216 @default.
- W3209179910 hasAuthorship W3209179910A5011299100 @default.
- W3209179910 hasAuthorship W3209179910A5044165871 @default.
- W3209179910 hasAuthorship W3209179910A5054352845 @default.
- W3209179910 hasAuthorship W3209179910A5054877470 @default.
- W3209179910 hasBestOaLocation W32091799101 @default.
- W3209179910 hasConcept C108650721 @default.
- W3209179910 hasConcept C111919701 @default.
- W3209179910 hasConcept C119857082 @default.
- W3209179910 hasConcept C127413603 @default.
- W3209179910 hasConcept C154945302 @default.
- W3209179910 hasConcept C15744967 @default.
- W3209179910 hasConcept C165696696 @default.
- W3209179910 hasConcept C185592680 @default.
- W3209179910 hasConcept C198531522 @default.
- W3209179910 hasConcept C201995342 @default.
- W3209179910 hasConcept C2780451532 @default.
- W3209179910 hasConcept C38652104 @default.
- W3209179910 hasConcept C41008148 @default.
- W3209179910 hasConcept C43617362 @default.
- W3209179910 hasConcept C50644808 @default.
- W3209179910 hasConcept C77805123 @default.
- W3209179910 hasConcept C97541855 @default.
- W3209179910 hasConcept C98045186 @default.
- W3209179910 hasConceptScore W3209179910C108650721 @default.
- W3209179910 hasConceptScore W3209179910C111919701 @default.
- W3209179910 hasConceptScore W3209179910C119857082 @default.
- W3209179910 hasConceptScore W3209179910C127413603 @default.
- W3209179910 hasConceptScore W3209179910C154945302 @default.
- W3209179910 hasConceptScore W3209179910C15744967 @default.
- W3209179910 hasConceptScore W3209179910C165696696 @default.
- W3209179910 hasConceptScore W3209179910C185592680 @default.
- W3209179910 hasConceptScore W3209179910C198531522 @default.
- W3209179910 hasConceptScore W3209179910C201995342 @default.
- W3209179910 hasConceptScore W3209179910C2780451532 @default.
- W3209179910 hasConceptScore W3209179910C38652104 @default.
- W3209179910 hasConceptScore W3209179910C41008148 @default.
- W3209179910 hasConceptScore W3209179910C43617362 @default.
- W3209179910 hasConceptScore W3209179910C50644808 @default.
- W3209179910 hasConceptScore W3209179910C77805123 @default.
- W3209179910 hasConceptScore W3209179910C97541855 @default.
- W3209179910 hasConceptScore W3209179910C98045186 @default.
- W3209179910 hasLocation W32091799101 @default.
- W3209179910 hasOpenAccess W3209179910 @default.
- W3209179910 hasPrimaryLocation W32091799101 @default.