FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284708930> ?p ?o ?g. }

• W4284708930 abstract "Deep learning (DL) techniques are proven effective in many challenging tasks, and become widely-adopted in practice. However, previous work has shown that DL libraries, the basis of building and executing DL models, contain bugs and can cause severe consequences. Unfortunately, existing testing approaches still cannot comprehensively exercise DL libraries. They utilize existing trained models and only detect bugs in model inference phase. In this work we propose Muffin to address these issues. To this end, Muffin applies a specifically-designed model fuzzing approach, which allows it to generate diverse DL models to explore the target library, instead of relying only on existing trained models. Muffin makes differential testing feasible in the model training phase by tailoring a set of metrics to measure the inconsistencies between different DL libraries. In this way, Muffin can best exercise the library code to detect more bugs. To evaluate the effectiveness of Muffin, we conduct experiments on three widely-used DL libraries. The results demonstrate that Muffin can detect 39 new bugs in the latest release versions of popular DL libraries, including Tensorflow, CNTK, and Theano." @default.
• W4284708930 created "2022-07-08" @default.
• W4284708930 creator A5006822602 @default.
• W4284708930 creator A5009970334 @default.
• W4284708930 creator A5020816745 @default.
• W4284708930 creator A5042468232 @default.
• W4284708930 date "2022-05-21" @default.
• W4284708930 modified "2023-10-18" @default.
• W4284708930 title "Muffin" @default.
• W4284708930 cites W179875071 @default.
• W4284708930 cites W2036816056 @default.
• W4284708930 cites W2046084401 @default.
• W4284708930 cites W2098456636 @default.
• W4284708930 cites W2132523160 @default.
• W4284708930 cites W2151481990 @default.
• W4284708930 cites W2169004268 @default.
• W4284708930 cites W2194775991 @default.
• W4284708930 cites W2414287720 @default.
• W4284708930 cites W2616028256 @default.
• W4284708930 cites W2792106437 @default.
• W4284708930 cites W2799640043 @default.
• W4284708930 cites W2859484040 @default.
• W4284708930 cites W2888307014 @default.
• W4284708930 cites W2888824816 @default.
• W4284708930 cites W2898868990 @default.
• W4284708930 cites W2899445138 @default.
• W4284708930 cites W2954629067 @default.
• W4284708930 cites W2954903132 @default.
• W4284708930 cites W2954978134 @default.
• W4284708930 cites W2955874753 @default.
• W4284708930 cites W2956152059 @default.
• W4284708930 cites W2957905354 @default.
• W4284708930 cites W2963327228 @default.
• W4284708930 cites W2963446712 @default.
• W4284708930 cites W2963451564 @default.
• W4284708930 cites W2963542740 @default.
• W4284708930 cites W2967287319 @default.
• W4284708930 cites W2968594320 @default.
• W4284708930 cites W2968940383 @default.
• W4284708930 cites W2969772318 @default.
• W4284708930 cites W2973084513 @default.
• W4284708930 cites W3040727891 @default.
• W4284708930 cites W3047008933 @default.
• W4284708930 cites W3047059392 @default.
• W4284708930 cites W3090418065 @default.
• W4284708930 cites W3099331415 @default.
• W4284708930 cites W3099444373 @default.
• W4284708930 cites W3104663419 @default.
• W4284708930 cites W3109004940 @default.
• W4284708930 cites W3130423852 @default.
• W4284708930 cites W3134796670 @default.
• W4284708930 cites W3160369295 @default.
• W4284708930 doi "https://doi.org/10.1145/3510003.3510092" @default.
• W4284708930 hasPublicationYear "2022" @default.
• W4284708930 type Work @default.
• W4284708930 citedByCount "7" @default.
• W4284708930 countsByYear W42847089302022 @default.
• W4284708930 countsByYear W42847089302023 @default.
• W4284708930 crossrefType "proceedings-article" @default.
• W4284708930 hasAuthorship W4284708930A5006822602 @default.
• W4284708930 hasAuthorship W4284708930A5009970334 @default.
• W4284708930 hasAuthorship W4284708930A5020816745 @default.
• W4284708930 hasAuthorship W4284708930A5042468232 @default.
• W4284708930 hasConcept C1009929 @default.
• W4284708930 hasConcept C111065885 @default.
• W4284708930 hasConcept C115903868 @default.
• W4284708930 hasConcept C119857082 @default.
• W4284708930 hasConcept C124101348 @default.
• W4284708930 hasConcept C154945302 @default.
• W4284708930 hasConcept C177264268 @default.
• W4284708930 hasConcept C199360897 @default.
• W4284708930 hasConcept C2776214188 @default.
• W4284708930 hasConcept C2776760102 @default.
• W4284708930 hasConcept C2777904410 @default.
• W4284708930 hasConcept C2780009758 @default.
• W4284708930 hasConcept C41008148 @default.
• W4284708930 hasConceptScore W4284708930C1009929 @default.
• W4284708930 hasConceptScore W4284708930C111065885 @default.
• W4284708930 hasConceptScore W4284708930C115903868 @default.
• W4284708930 hasConceptScore W4284708930C119857082 @default.
• W4284708930 hasConceptScore W4284708930C124101348 @default.
• W4284708930 hasConceptScore W4284708930C154945302 @default.
• W4284708930 hasConceptScore W4284708930C177264268 @default.
• W4284708930 hasConceptScore W4284708930C199360897 @default.
• W4284708930 hasConceptScore W4284708930C2776214188 @default.
• W4284708930 hasConceptScore W4284708930C2776760102 @default.
• W4284708930 hasConceptScore W4284708930C2777904410 @default.
• W4284708930 hasConceptScore W4284708930C2780009758 @default.
• W4284708930 hasConceptScore W4284708930C41008148 @default.
• W4284708930 hasFunder F4320335777 @default.
• W4284708930 hasLocation W42847089301 @default.
• W4284708930 hasOpenAccess W4284708930 @default.
• W4284708930 hasPrimaryLocation W42847089301 @default.
• W4284708930 hasRelatedWork W2547155723 @default.
• W4284708930 hasRelatedWork W3170526652 @default.
• W4284708930 hasRelatedWork W3173990398 @default.
• W4284708930 hasRelatedWork W4205454537 @default.
• W4284708930 hasRelatedWork W4226494072 @default.
• W4284708930 hasRelatedWork W4287849816 @default.
• W4284708930 hasRelatedWork W4378192144 @default.

• next