FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378647935> ?p ?o ?g. }

• W4378647935 endingPage "3492" @default.
• W4378647935 startingPage "3479" @default.
• W4378647935 abstract "Detecting anomalies in logs is crucial for service and system management, since logs are widely used to record the runtime status, and are often the only data available for postmortem analysis. Since anomalies are usually rare in real-world services and systems, a common and feasible practice is to mine or learn normal patterns from logs, and deem those violating the normal patterns as anomalies. As log sequences are a kind of time series data, RNN (Recurrent Neural Network) and its variants have been extensively employed to capture the normal patterns. Nevertheless, the sequential nature of RNN and its variants makes them hard to parallelize and capture long-term dependencies, which may hinder their performance. To address this issue, in this paper we propose Loader, a novel semi-supervised <underline xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><b>lo</b></u> g <underline xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><b>a</b></u> nomaly <underline xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><b>d</b></u> etector based on Transform <underline xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><b>er</b></u> , because the Transformer architecture eschews recurrence and is able to draw global dependencies. Loader leverages the Transformer encoder to capture normal patterns from normal log sequences. When detecting, it gives a set of candidate log templates, that may appear after the input log substring under normal conditions. If the template of the actual next log message is not within the candidate set, this implies an anomaly. Previous similar methods select the most possible <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$k$</tex-math></inline-formula> log templates as candidates in any case, so the performance is sensitive to <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$k$</tex-math></inline-formula> , and it is nontrivial to pick a proper <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$k$</tex-math></inline-formula> . To alleviate this, we design a more flexible and robust ‘top- <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$p$</tex-math></inline-formula> ’ algorithm, which determines the candidate set based on the cumulative probability of the most possible log templates. Extensive experiments are conducted based on three public log datasets, the experimental results validate the effectiveness and competitiveness of our approach." @default.
• W4378647935 created "2023-05-30" @default.
• W4378647935 creator A5000688713 @default.
• W4378647935 creator A5007434394 @default.
• W4378647935 creator A5021932264 @default.
• W4378647935 creator A5034405338 @default.
• W4378647935 creator A5037730132 @default.
• W4378647935 creator A5039639491 @default.
• W4378647935 creator A5068638985 @default.
• W4378647935 creator A5091496905 @default.
• W4378647935 date "2023-09-01" @default.
• W4378647935 modified "2023-10-12" @default.
• W4378647935 title "Loader: A Log Anomaly Detector Based on Transformer" @default.
• W4378647935 cites W1661413208 @default.
• W4378647935 cites W2039157918 @default.
• W4378647935 cites W2094924503 @default.
• W4378647935 cites W2105454049 @default.
• W4378647935 cites W2107263349 @default.
• W4378647935 cites W2115056012 @default.
• W4378647935 cites W2141041105 @default.
• W4378647935 cites W2142804492 @default.
• W4378647935 cites W2169953282 @default.
• W4378647935 cites W2194775991 @default.
• W4378647935 cites W2208211896 @default.
• W4378647935 cites W2560021099 @default.
• W4378647935 cites W2583874385 @default.
• W4378647935 cites W2585367509 @default.
• W4378647935 cites W2754665629 @default.
• W4378647935 cites W2767094836 @default.
• W4378647935 cites W2884697754 @default.
• W4378647935 cites W2895810692 @default.
• W4378647935 cites W2947815220 @default.
• W4378647935 cites W2963999143 @default.
• W4378647935 cites W2965838158 @default.
• W4378647935 cites W2966971704 @default.
• W4378647935 cites W2972150249 @default.
• W4378647935 cites W2972818416 @default.
• W4378647935 cites W3007523155 @default.
• W4378647935 cites W3041215671 @default.
• W4378647935 cites W3095840026 @default.
• W4378647935 cites W3117426595 @default.
• W4378647935 cites W3127995892 @default.
• W4378647935 cites W3169066865 @default.
• W4378647935 cites W3183619936 @default.
• W4378647935 cites W4207017921 @default.
• W4378647935 cites W4255845613 @default.
• W4378647935 cites W4361807675 @default.
• W4378647935 doi "https://doi.org/10.1109/tsc.2023.3280575" @default.
• W4378647935 hasPublicationYear "2023" @default.
• W4378647935 type Work @default.
• W4378647935 citedByCount "0" @default.
• W4378647935 crossrefType "journal-article" @default.
• W4378647935 hasAuthorship W4378647935A5000688713 @default.
• W4378647935 hasAuthorship W4378647935A5007434394 @default.
• W4378647935 hasAuthorship W4378647935A5021932264 @default.
• W4378647935 hasAuthorship W4378647935A5034405338 @default.
• W4378647935 hasAuthorship W4378647935A5037730132 @default.
• W4378647935 hasAuthorship W4378647935A5039639491 @default.
• W4378647935 hasAuthorship W4378647935A5068638985 @default.
• W4378647935 hasAuthorship W4378647935A5091496905 @default.
• W4378647935 hasConcept C111919701 @default.
• W4378647935 hasConcept C118505674 @default.
• W4378647935 hasConcept C119599485 @default.
• W4378647935 hasConcept C124101348 @default.
• W4378647935 hasConcept C127413603 @default.
• W4378647935 hasConcept C154945302 @default.
• W4378647935 hasConcept C165801399 @default.
• W4378647935 hasConcept C41008148 @default.
• W4378647935 hasConcept C66322947 @default.
• W4378647935 hasConceptScore W4378647935C111919701 @default.
• W4378647935 hasConceptScore W4378647935C118505674 @default.
• W4378647935 hasConceptScore W4378647935C119599485 @default.
• W4378647935 hasConceptScore W4378647935C124101348 @default.
• W4378647935 hasConceptScore W4378647935C127413603 @default.
• W4378647935 hasConceptScore W4378647935C154945302 @default.
• W4378647935 hasConceptScore W4378647935C165801399 @default.
• W4378647935 hasConceptScore W4378647935C41008148 @default.
• W4378647935 hasConceptScore W4378647935C66322947 @default.
• W4378647935 hasFunder F4320321001 @default.
• W4378647935 hasIssue "5" @default.
• W4378647935 hasLocation W43786479351 @default.
• W4378647935 hasOpenAccess W4378647935 @default.
• W4378647935 hasPrimaryLocation W43786479351 @default.
• W4378647935 hasRelatedWork W1596801655 @default.
• W4378647935 hasRelatedWork W2130043461 @default.
• W4378647935 hasRelatedWork W2350741829 @default.
• W4378647935 hasRelatedWork W2358668433 @default.
• W4378647935 hasRelatedWork W2376932109 @default.
• W4378647935 hasRelatedWork W2382290278 @default.
• W4378647935 hasRelatedWork W2390279801 @default.
• W4378647935 hasRelatedWork W2748952813 @default.
• W4378647935 hasRelatedWork W2899084033 @default.
• W4378647935 hasRelatedWork W2530322880 @default.
• W4378647935 hasVolume "16" @default.
• W4378647935 isParatext "false" @default.
• W4378647935 isRetracted "false" @default.
• W4378647935 workType "article" @default.