FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376643746> ?p ?o ?g. }

• W4376643746 endingPage "40" @default.
• W4376643746 startingPage "1" @default.
• W4376643746 abstract "AI models of code have made significant progress over the past few years. However, many models are actually not learning task-relevant source code features. Instead, they often fit non-relevant but correlated data, leading to a lack of robustness and generalizability, and limiting the subsequent practical use of such models. In this work, we focus on improving the model quality through signal awareness , i.e., learning the relevant signals in the input for making predictions. We do so by leveraging the heterogeneity of code samples in terms of their signal-to-noise content. We perform an end-to-end exploration of model signal awareness, comprising: (i) uncovering the reliance of AI models of code on task-irrelevant signals, via prediction-preserving input minimization; (ii) improving models’ signal awareness by incorporating the notion of code complexity during model training, via curriculum learning; (iii) improving models’ signal awareness by generating simplified signal-preserving programs and augmenting them to the training dataset; and (iv) presenting a novel interpretation of the model learning behavior from the perspective of the dataset, using its code complexity distribution. We propose a new metric to measure model signal awareness, Signal-aware Recall, which captures how much of the model’s performance is attributable to task-relevant signal learning. Using a software vulnerability detection use-case, our model probing approach uncovers a significant lack of signal awareness in the models, across three different neural network architectures and three datasets. Signal-aware Recall is observed to be in the sub-50s for models with traditional Recall in the high 90s, suggesting that the models are presumably picking up a lot of noise or dataset nuances while learning their logic. With our code-complexity-aware model learning enhancement techniques, we are able to assist the models toward more task-relevant learning, recording up-to 4.8× improvement in model signal awareness. Finally, we employ our model learning introspection approach to uncover the aspects of source code where the model is facing difficulty, and we analyze how our learning enhancement techniques alleviate it." @default.
• W4376643746 created "2023-05-17" @default.
• W4376643746 creator A5013455098 @default.
• W4376643746 creator A5034331643 @default.
• W4376643746 creator A5039824895 @default.
• W4376643746 creator A5052671723 @default.
• W4376643746 creator A5076968229 @default.
• W4376643746 creator A5090845035 @default.
• W4376643746 date "2023-09-29" @default.
• W4376643746 modified "2023-10-14" @default.
• W4376643746 title "Incorporating Signal Awareness in Source Code Modeling: an Application to Vulnerability Detection" @default.
• W4376643746 cites W2064675550 @default.
• W4376643746 cites W2148143831 @default.
• W4376643746 cites W2170224888 @default.
• W4376643746 cites W2194775991 @default.
• W4376643746 cites W2293634267 @default.
• W4376643746 cites W2806718802 @default.
• W4376643746 cites W2884614891 @default.
• W4376643746 cites W2954996726 @default.
• W4376643746 cites W2962858109 @default.
• W4376643746 cites W2963542245 @default.
• W4376643746 cites W2964268978 @default.
• W4376643746 cites W2972082064 @default.
• W4376643746 cites W2986734036 @default.
• W4376643746 cites W3086358185 @default.
• W4376643746 cites W3098605233 @default.
• W4376643746 cites W3163206498 @default.
• W4376643746 cites W3194682511 @default.
• W4376643746 cites W3195156628 @default.
• W4376643746 doi "https://doi.org/10.1145/3597202" @default.
• W4376643746 hasPublicationYear "2023" @default.
• W4376643746 type Work @default.
• W4376643746 citedByCount "0" @default.
• W4376643746 crossrefType "journal-article" @default.
• W4376643746 hasAuthorship W4376643746A5013455098 @default.
• W4376643746 hasAuthorship W4376643746A5034331643 @default.
• W4376643746 hasAuthorship W4376643746A5039824895 @default.
• W4376643746 hasAuthorship W4376643746A5052671723 @default.
• W4376643746 hasAuthorship W4376643746A5076968229 @default.
• W4376643746 hasAuthorship W4376643746A5090845035 @default.
• W4376643746 hasBestOaLocation W43766437461 @default.
• W4376643746 hasConcept C104317684 @default.
• W4376643746 hasConcept C105795698 @default.
• W4376643746 hasConcept C111919701 @default.
• W4376643746 hasConcept C119857082 @default.
• W4376643746 hasConcept C124101348 @default.
• W4376643746 hasConcept C154945302 @default.
• W4376643746 hasConcept C177264268 @default.
• W4376643746 hasConcept C185592680 @default.
• W4376643746 hasConcept C199360897 @default.
• W4376643746 hasConcept C27158222 @default.
• W4376643746 hasConcept C2776760102 @default.
• W4376643746 hasConcept C2779843651 @default.
• W4376643746 hasConcept C33923547 @default.
• W4376643746 hasConcept C41008148 @default.
• W4376643746 hasConcept C43126263 @default.
• W4376643746 hasConcept C55493867 @default.
• W4376643746 hasConcept C63479239 @default.
• W4376643746 hasConceptScore W4376643746C104317684 @default.
• W4376643746 hasConceptScore W4376643746C105795698 @default.
• W4376643746 hasConceptScore W4376643746C111919701 @default.
• W4376643746 hasConceptScore W4376643746C119857082 @default.
• W4376643746 hasConceptScore W4376643746C124101348 @default.
• W4376643746 hasConceptScore W4376643746C154945302 @default.
• W4376643746 hasConceptScore W4376643746C177264268 @default.
• W4376643746 hasConceptScore W4376643746C185592680 @default.
• W4376643746 hasConceptScore W4376643746C199360897 @default.
• W4376643746 hasConceptScore W4376643746C27158222 @default.
• W4376643746 hasConceptScore W4376643746C2776760102 @default.
• W4376643746 hasConceptScore W4376643746C2779843651 @default.
• W4376643746 hasConceptScore W4376643746C33923547 @default.
• W4376643746 hasConceptScore W4376643746C41008148 @default.
• W4376643746 hasConceptScore W4376643746C43126263 @default.
• W4376643746 hasConceptScore W4376643746C55493867 @default.
• W4376643746 hasConceptScore W4376643746C63479239 @default.
• W4376643746 hasIssue "6" @default.
• W4376643746 hasLocation W43766437461 @default.
• W4376643746 hasOpenAccess W4376643746 @default.
• W4376643746 hasPrimaryLocation W43766437461 @default.
• W4376643746 hasRelatedWork W2754401617 @default.
• W4376643746 hasRelatedWork W2795551190 @default.
• W4376643746 hasRelatedWork W2890430415 @default.
• W4376643746 hasRelatedWork W2961085424 @default.
• W4376643746 hasRelatedWork W3011915042 @default.
• W4376643746 hasRelatedWork W4200511449 @default.
• W4376643746 hasRelatedWork W4295508364 @default.
• W4376643746 hasRelatedWork W4306674287 @default.
• W4376643746 hasRelatedWork W4307415438 @default.
• W4376643746 hasRelatedWork W4385849003 @default.
• W4376643746 hasVolume "32" @default.
• W4376643746 isParatext "false" @default.
• W4376643746 isRetracted "false" @default.
• W4376643746 workType "article" @default.