FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304757966> ?p ?o ?g. }

• W4304757966 endingPage "1276" @default.
• W4304757966 startingPage "1266" @default.
• W4304757966 abstract "Whether AI explanations can help users achieve specific tasks efficiently (i.e., usable explanations) is significantly influenced by their visual presentation. While many techniques exist to generate explanations, it remains unclear how to select and visually present AI explanations based on the characteristics of domain users. This paper aims to understand this question through a multidisciplinary design study for a specific problem: explaining graph neural network (GNN) predictions to domain experts in drug repurposing, i.e., reuse of existing drugs for new diseases. Building on the nested design model of visualization, we incorporate XAI design considerations from a literature review and from our collaborators' feedback into the design process. Specifically, we discuss XAI-related design considerations for usable visual explanations at each design layer: target user, usage context, domain explanation, and XAI goal at the domain layer; format, granularity, and operation of explanations at the abstraction layer; encodings and interactions at the visualization layer; and XAI and rendering algorithm at the algorithm layer. We present how the extended nested model motivates and informs the design of DrugExplorer, an XAI tool for drug repurposing. Based on our domain characterization, DrugExplorer provides path-based explanations and presents them both as individual paths and meta-paths for two key XAI operations, why and what else. DrugExplorer offers a novel visualization design called MetaMatrix with a set of interactions to help domain users organize and compare explanation paths at different levels of granularity to generate domain-meaningful insights. We demonstrate the effectiveness of the selected visual presentation and DrugExplorer as a whole via a usage scenario, a user study, and expert interviews. From these evaluations, we derive insightful observations and reflections that can inform the design of XAI visualizations for other scientific applications." @default.
• W4304757966 created "2022-10-13" @default.
• W4304757966 creator A5005039651 @default.
• W4304757966 creator A5037842761 @default.
• W4304757966 creator A5049086940 @default.
• W4304757966 creator A5066335313 @default.
• W4304757966 creator A5086052373 @default.
• W4304757966 date "2023-01-01" @default.
• W4304757966 modified "2023-10-17" @default.
• W4304757966 title "Extending the Nested Model for User-Centric XAI: A Design Study on GNN-based Drug Repurposing" @default.
• W4304757966 cites W1970569592 @default.
• W4304757966 cites W2025806111 @default.
• W4304757966 cites W2045034548 @default.
• W4304757966 cites W2046311907 @default.
• W4304757966 cites W2088290398 @default.
• W4304757966 cites W2135306251 @default.
• W4304757966 cites W2135415614 @default.
• W4304757966 cites W2140131793 @default.
• W4304757966 cites W2142493242 @default.
• W4304757966 cites W2154435142 @default.
• W4304757966 cites W2166365305 @default.
• W4304757966 cites W2444690946 @default.
• W4304757966 cites W2468565665 @default.
• W4304757966 cites W2522925973 @default.
• W4304757966 cites W2613791735 @default.
• W4304757966 cites W2767891136 @default.
• W4304757966 cites W2790505917 @default.
• W4304757966 cites W2804604520 @default.
• W4304757966 cites W2883424428 @default.
• W4304757966 cites W2892741787 @default.
• W4304757966 cites W2911286998 @default.
• W4304757966 cites W2923421605 @default.
• W4304757966 cites W2942073295 @default.
• W4304757966 cites W2942444880 @default.
• W4304757966 cites W2943775605 @default.
• W4304757966 cites W2945976633 @default.
• W4304757966 cites W2963095307 @default.
• W4304757966 cites W2969980980 @default.
• W4304757966 cites W2970837303 @default.
• W4304757966 cites W2972236817 @default.
• W4304757966 cites W2998922495 @default.
• W4304757966 cites W3005984470 @default.
• W4304757966 cites W3010300896 @default.
• W4304757966 cites W3011560571 @default.
• W4304757966 cites W3016099278 @default.
• W4304757966 cites W3019489177 @default.
• W4304757966 cites W3041288499 @default.
• W4304757966 cites W3041467169 @default.
• W4304757966 cites W3080718665 @default.
• W4304757966 cites W3092273406 @default.
• W4304757966 cites W3093687066 @default.
• W4304757966 cites W3104847483 @default.
• W4304757966 cites W3106372104 @default.
• W4304757966 cites W3107856351 @default.
• W4304757966 cites W3118244215 @default.
• W4304757966 cites W3131457744 @default.
• W4304757966 cites W3137864305 @default.
• W4304757966 cites W3197347140 @default.
• W4304757966 cites W3214883276 @default.
• W4304757966 cites W4237375617 @default.
• W4304757966 cites W4245217443 @default.
• W4304757966 cites W4252087024 @default.
• W4304757966 cites W4288083797 @default.
• W4304757966 doi "https://doi.org/10.1109/tvcg.2022.3209435" @default.
• W4304757966 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36223348" @default.
• W4304757966 hasPublicationYear "2023" @default.
• W4304757966 type Work @default.
• W4304757966 citedByCount "7" @default.
• W4304757966 countsByYear W43047579662023 @default.
• W4304757966 crossrefType "journal-article" @default.
• W4304757966 hasAuthorship W4304757966A5005039651 @default.
• W4304757966 hasAuthorship W4304757966A5037842761 @default.
• W4304757966 hasAuthorship W4304757966A5049086940 @default.
• W4304757966 hasAuthorship W4304757966A5066335313 @default.
• W4304757966 hasAuthorship W4304757966A5086052373 @default.
• W4304757966 hasBestOaLocation W43047579661 @default.
• W4304757966 hasConcept C124101348 @default.
• W4304757966 hasConcept C134306372 @default.
• W4304757966 hasConcept C136764020 @default.
• W4304757966 hasConcept C154945302 @default.
• W4304757966 hasConcept C2780615836 @default.
• W4304757966 hasConcept C33923547 @default.
• W4304757966 hasConcept C36464697 @default.
• W4304757966 hasConcept C36503486 @default.
• W4304757966 hasConcept C41008148 @default.
• W4304757966 hasConceptScore W4304757966C124101348 @default.
• W4304757966 hasConceptScore W4304757966C134306372 @default.
• W4304757966 hasConceptScore W4304757966C136764020 @default.
• W4304757966 hasConceptScore W4304757966C154945302 @default.
• W4304757966 hasConceptScore W4304757966C2780615836 @default.
• W4304757966 hasConceptScore W4304757966C33923547 @default.
• W4304757966 hasConceptScore W4304757966C36464697 @default.
• W4304757966 hasConceptScore W4304757966C36503486 @default.
• W4304757966 hasConceptScore W4304757966C41008148 @default.
• W4304757966 hasFunder F4320306076 @default.
• W4304757966 hasIssue "1" @default.
• W4304757966 hasLocation W43047579661 @default.
• W4304757966 hasLocation W43047579662 @default.

• next