Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385482705> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4385482705 abstract "Detecting whether a distribution shift has occurred in the dataset is a critical aspect when implementing machine learning models, as even a small shift in the data distribution may largely affect the performance of a machine learning model and thus cause the deployed model to fail. In this work, we focus on detecting harmful dataset shifts, i.e., shifts that are detrimental to the performance of the machine learning model. The existing methods usually detect whether there is a shift between two datasets according to the following framework: first carrying out dimensionality reduction on the datasets, then determining whether dataset shift exists according to the two-sample statistical test(s) on the reduced datasets. The knowledge contained in the model trained on the dataset is not utilized in the above described dataset shift detection framework. To address this, this paper proposes to take advantage of explainable artificial intelligence (XAI) techniques to exploit the knowledge in trained models when detecting harmful dataset shifts. Specifically, we employ the feature attribution explanation (FAE) method to capture the knowledge in the model and combine it with a widely-used two-sample test method, i.e., maximum mean difference (MMD), to detect harmful dataset shifts. The experimental results on more than twenty different shifts in three widely used image datasets demonstrate that the proposed method is more effective in identifying harmful dataset shifts than existing methods. Moreover, experiments on several different models show that the method is robust and effective over different models, i.e., its detection performance is not sensitive to the model used." @default.
- W4385482705 created "2023-08-03" @default.
- W4385482705 creator A5030356525 @default.
- W4385482705 creator A5049590622 @default.
- W4385482705 creator A5084120665 @default.
- W4385482705 date "2023-06-18" @default.
- W4385482705 modified "2023-09-26" @default.
- W4385482705 title "Feature Attribution Explanation to Detect Harmful Dataset Shift" @default.
- W4385482705 cites W2028138594 @default.
- W4385482705 cites W2112796928 @default.
- W4385482705 cites W2183341477 @default.
- W4385482705 cites W2194775991 @default.
- W4385482705 cites W2963446712 @default.
- W4385482705 cites W2964340499 @default.
- W4385482705 cites W2981731882 @default.
- W4385482705 cites W3013149459 @default.
- W4385482705 cites W3035264434 @default.
- W4385482705 cites W3207466963 @default.
- W4385482705 cites W4288391568 @default.
- W4385482705 cites W4297095629 @default.
- W4385482705 doi "https://doi.org/10.1109/ijcnn54540.2023.10191221" @default.
- W4385482705 hasPublicationYear "2023" @default.
- W4385482705 type Work @default.
- W4385482705 citedByCount "0" @default.
- W4385482705 crossrefType "proceedings-article" @default.
- W4385482705 hasAuthorship W4385482705A5030356525 @default.
- W4385482705 hasAuthorship W4385482705A5049590622 @default.
- W4385482705 hasAuthorship W4385482705A5084120665 @default.
- W4385482705 hasConcept C111030470 @default.
- W4385482705 hasConcept C119857082 @default.
- W4385482705 hasConcept C120665830 @default.
- W4385482705 hasConcept C121332964 @default.
- W4385482705 hasConcept C124101348 @default.
- W4385482705 hasConcept C138885662 @default.
- W4385482705 hasConcept C153180895 @default.
- W4385482705 hasConcept C154945302 @default.
- W4385482705 hasConcept C165696696 @default.
- W4385482705 hasConcept C185592680 @default.
- W4385482705 hasConcept C192209626 @default.
- W4385482705 hasConcept C198531522 @default.
- W4385482705 hasConcept C2776401178 @default.
- W4385482705 hasConcept C38652104 @default.
- W4385482705 hasConcept C41008148 @default.
- W4385482705 hasConcept C41895202 @default.
- W4385482705 hasConcept C43617362 @default.
- W4385482705 hasConcept C70518039 @default.
- W4385482705 hasConceptScore W4385482705C111030470 @default.
- W4385482705 hasConceptScore W4385482705C119857082 @default.
- W4385482705 hasConceptScore W4385482705C120665830 @default.
- W4385482705 hasConceptScore W4385482705C121332964 @default.
- W4385482705 hasConceptScore W4385482705C124101348 @default.
- W4385482705 hasConceptScore W4385482705C138885662 @default.
- W4385482705 hasConceptScore W4385482705C153180895 @default.
- W4385482705 hasConceptScore W4385482705C154945302 @default.
- W4385482705 hasConceptScore W4385482705C165696696 @default.
- W4385482705 hasConceptScore W4385482705C185592680 @default.
- W4385482705 hasConceptScore W4385482705C192209626 @default.
- W4385482705 hasConceptScore W4385482705C198531522 @default.
- W4385482705 hasConceptScore W4385482705C2776401178 @default.
- W4385482705 hasConceptScore W4385482705C38652104 @default.
- W4385482705 hasConceptScore W4385482705C41008148 @default.
- W4385482705 hasConceptScore W4385482705C41895202 @default.
- W4385482705 hasConceptScore W4385482705C43617362 @default.
- W4385482705 hasConceptScore W4385482705C70518039 @default.
- W4385482705 hasFunder F4320321001 @default.
- W4385482705 hasLocation W43854827051 @default.
- W4385482705 hasOpenAccess W4385482705 @default.
- W4385482705 hasPrimaryLocation W43854827051 @default.
- W4385482705 hasRelatedWork W1520675566 @default.
- W4385482705 hasRelatedWork W1965275221 @default.
- W4385482705 hasRelatedWork W2066259560 @default.
- W4385482705 hasRelatedWork W2110350792 @default.
- W4385482705 hasRelatedWork W2172836935 @default.
- W4385482705 hasRelatedWork W2546942002 @default.
- W4385482705 hasRelatedWork W2883447302 @default.
- W4385482705 hasRelatedWork W2970216048 @default.
- W4385482705 hasRelatedWork W3110687914 @default.
- W4385482705 hasRelatedWork W4214747999 @default.
- W4385482705 isParatext "false" @default.
- W4385482705 isRetracted "false" @default.
- W4385482705 workType "article" @default.