Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387210540> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4387210540 abstract "Machine learning (ML) based systems have been suffering a lack of interpretability. To address this problem, counterfactual explanations (CEs) have been proposed. CEs are unique as they provide workable suggestions to users, in addition to explaining why a certain outcome was predicted. However, the application of CEs has been hindered by two main challenges, namely general user preferences and variable ML systems. User preferences, in particular, tend to be general rather than specific feature values. Additionally, CEs need to be customized to suit the variability of ML models, while also maintaining robustness even when these validation models change. To overcome these challenges, we propose several possible general user preferences that have been validated by user research and map them to the properties of CEs. We also introduce a new method called uline{T}ree-based uline{C}onditions uline{O}ptional uline{L}inks (T-COL), which has two optional structures and several groups of conditions for generating CEs that can be adapted to general user preferences. Meanwhile, a group of conditions lead T-COL to generate more robust CEs that have higher validity when the ML model is replaced. We compared the properties of CEs generated by T-COL experimentally under different user preferences and demonstrated that T-COL is better suited for accommodating user preferences and variable ML systems compared to baseline methods including Large Language Models." @default.
- W4387210540 created "2023-10-01" @default.
- W4387210540 creator A5017251333 @default.
- W4387210540 creator A5035378456 @default.
- W4387210540 creator A5044868467 @default.
- W4387210540 creator A5071389166 @default.
- W4387210540 creator A5078907399 @default.
- W4387210540 date "2023-09-27" @default.
- W4387210540 modified "2023-10-01" @default.
- W4387210540 title "T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems" @default.
- W4387210540 doi "https://doi.org/10.48550/arxiv.2309.16146" @default.
- W4387210540 hasPublicationYear "2023" @default.
- W4387210540 type Work @default.
- W4387210540 citedByCount "0" @default.
- W4387210540 crossrefType "posted-content" @default.
- W4387210540 hasAuthorship W4387210540A5017251333 @default.
- W4387210540 hasAuthorship W4387210540A5035378456 @default.
- W4387210540 hasAuthorship W4387210540A5044868467 @default.
- W4387210540 hasAuthorship W4387210540A5071389166 @default.
- W4387210540 hasAuthorship W4387210540A5078907399 @default.
- W4387210540 hasBestOaLocation W43872105401 @default.
- W4387210540 hasConcept C104317684 @default.
- W4387210540 hasConcept C108650721 @default.
- W4387210540 hasConcept C111368507 @default.
- W4387210540 hasConcept C119857082 @default.
- W4387210540 hasConcept C12725497 @default.
- W4387210540 hasConcept C127313418 @default.
- W4387210540 hasConcept C134306372 @default.
- W4387210540 hasConcept C154945302 @default.
- W4387210540 hasConcept C15744967 @default.
- W4387210540 hasConcept C182365436 @default.
- W4387210540 hasConcept C185592680 @default.
- W4387210540 hasConcept C2781067378 @default.
- W4387210540 hasConcept C33923547 @default.
- W4387210540 hasConcept C41008148 @default.
- W4387210540 hasConcept C55493867 @default.
- W4387210540 hasConcept C63479239 @default.
- W4387210540 hasConcept C77805123 @default.
- W4387210540 hasConceptScore W4387210540C104317684 @default.
- W4387210540 hasConceptScore W4387210540C108650721 @default.
- W4387210540 hasConceptScore W4387210540C111368507 @default.
- W4387210540 hasConceptScore W4387210540C119857082 @default.
- W4387210540 hasConceptScore W4387210540C12725497 @default.
- W4387210540 hasConceptScore W4387210540C127313418 @default.
- W4387210540 hasConceptScore W4387210540C134306372 @default.
- W4387210540 hasConceptScore W4387210540C154945302 @default.
- W4387210540 hasConceptScore W4387210540C15744967 @default.
- W4387210540 hasConceptScore W4387210540C182365436 @default.
- W4387210540 hasConceptScore W4387210540C185592680 @default.
- W4387210540 hasConceptScore W4387210540C2781067378 @default.
- W4387210540 hasConceptScore W4387210540C33923547 @default.
- W4387210540 hasConceptScore W4387210540C41008148 @default.
- W4387210540 hasConceptScore W4387210540C55493867 @default.
- W4387210540 hasConceptScore W4387210540C63479239 @default.
- W4387210540 hasConceptScore W4387210540C77805123 @default.
- W4387210540 hasLocation W43872105401 @default.
- W4387210540 hasOpenAccess W4387210540 @default.
- W4387210540 hasPrimaryLocation W43872105401 @default.
- W4387210540 hasRelatedWork W3006943036 @default.
- W4387210540 hasRelatedWork W4200027074 @default.
- W4387210540 hasRelatedWork W4200511449 @default.
- W4387210540 hasRelatedWork W4206534706 @default.
- W4387210540 hasRelatedWork W4211177414 @default.
- W4387210540 hasRelatedWork W4229079080 @default.
- W4387210540 hasRelatedWork W4299487748 @default.
- W4387210540 hasRelatedWork W4385957992 @default.
- W4387210540 hasRelatedWork W4385965371 @default.
- W4387210540 hasRelatedWork W4386025632 @default.
- W4387210540 isParatext "false" @default.
- W4387210540 isRetracted "false" @default.
- W4387210540 workType "article" @default.