FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310551411> ?p ?o ?g. }

• W4310551411 endingPage "357" @default.
• W4310551411 startingPage "346" @default.
• W4310551411 abstract "Dependency-aware jobs, such as the big data analytic workflows, are commonly executed on the cloud. They are compiled to directed acyclic graphs, with tasks linked in regarding the dependency. The cloud scheduler, which maintains a large number of resources, is responsible to execute tasks in parallel. To resolve the complex dependencies, Deep Reinforcement Learning (DRL) based schedulers are widely applied. However, we find that the DRL-based schedulers are vulnerable to the perturbations in the input jobs and may generate falsified decisions to benefit a particular job while delaying the others. By perturbation, we mean a slight adjustment to the job's node features or dependencies, while not changing its functionality. In this paper, we first explore the vulnerability of DRL-based schedulers to job perturbations without accessing the information of the DRL models used in the scheduler. We devise the black-box perturbation system, in which, a proxy model is trained to mimic the DRL-based scheduling policy. We show that the high-faith proxy model can help to craft effective perturbations. The DRL-based schedulers can be as high as 60% likely to be badly affected by the perturbations. Then, we investigate the solution to improve the robustness of DRL-based schedulers to such perturbations. We propose an adversarial training framework to force the neural model to adapt to the perturbation patterns during training so as to eliminate the potential damage during applications. Experiments show that the adversarial-trained scheduler is more robust, reducing the chance of being affected to 3-fold less and the potential bad effects halved." @default.
• W4310551411 created "2022-12-12" @default.
• W4310551411 creator A5006382771 @default.
• W4310551411 creator A5015993565 @default.
• W4310551411 creator A5036601222 @default.
• W4310551411 date "2023-01-01" @default.
• W4310551411 modified "2023-10-09" @default.
• W4310551411 title "Robustness Analysis and Enhancement of Deep Reinforcement Learning-Based Schedulers" @default.
• W4310551411 cites W2001420671 @default.
• W4310551411 cites W2079245724 @default.
• W4310551411 cites W2102558581 @default.
• W4310551411 cites W2119717200 @default.
• W4310551411 cites W2145339207 @default.
• W4310551411 cites W2151298633 @default.
• W4310551411 cites W2180612164 @default.
• W4310551411 cites W2257979135 @default.
• W4310551411 cites W2344786740 @default.
• W4310551411 cites W2515330476 @default.
• W4310551411 cites W2574978968 @default.
• W4310551411 cites W2603766943 @default.
• W4310551411 cites W2766641608 @default.
• W4310551411 cites W2773691349 @default.
• W4310551411 cites W2808663279 @default.
• W4310551411 cites W2905057216 @default.
• W4310551411 cites W2962755762 @default.
• W4310551411 cites W2962977206 @default.
• W4310551411 cites W2964583308 @default.
• W4310551411 cites W2968986602 @default.
• W4310551411 cites W2982539992 @default.
• W4310551411 cites W3007318395 @default.
• W4310551411 cites W9657784 @default.
• W4310551411 doi "https://doi.org/10.1109/tpds.2022.3218649" @default.
• W4310551411 hasPublicationYear "2023" @default.
• W4310551411 type Work @default.
• W4310551411 citedByCount "1" @default.
• W4310551411 countsByYear W43105514112023 @default.
• W4310551411 crossrefType "journal-article" @default.
• W4310551411 hasAuthorship W4310551411A5006382771 @default.
• W4310551411 hasAuthorship W4310551411A5015993565 @default.
• W4310551411 hasAuthorship W4310551411A5036601222 @default.
• W4310551411 hasConcept C104317684 @default.
• W4310551411 hasConcept C111919701 @default.
• W4310551411 hasConcept C119857082 @default.
• W4310551411 hasConcept C120314980 @default.
• W4310551411 hasConcept C126255220 @default.
• W4310551411 hasConcept C154945302 @default.
• W4310551411 hasConcept C185592680 @default.
• W4310551411 hasConcept C206729178 @default.
• W4310551411 hasConcept C33923547 @default.
• W4310551411 hasConcept C41008148 @default.
• W4310551411 hasConcept C55493867 @default.
• W4310551411 hasConcept C63479239 @default.
• W4310551411 hasConcept C79974875 @default.
• W4310551411 hasConcept C97541855 @default.
• W4310551411 hasConceptScore W4310551411C104317684 @default.
• W4310551411 hasConceptScore W4310551411C111919701 @default.
• W4310551411 hasConceptScore W4310551411C119857082 @default.
• W4310551411 hasConceptScore W4310551411C120314980 @default.
• W4310551411 hasConceptScore W4310551411C126255220 @default.
• W4310551411 hasConceptScore W4310551411C154945302 @default.
• W4310551411 hasConceptScore W4310551411C185592680 @default.
• W4310551411 hasConceptScore W4310551411C206729178 @default.
• W4310551411 hasConceptScore W4310551411C33923547 @default.
• W4310551411 hasConceptScore W4310551411C41008148 @default.
• W4310551411 hasConceptScore W4310551411C55493867 @default.
• W4310551411 hasConceptScore W4310551411C63479239 @default.
• W4310551411 hasConceptScore W4310551411C79974875 @default.
• W4310551411 hasConceptScore W4310551411C97541855 @default.
• W4310551411 hasFunder F4320334704 @default.
• W4310551411 hasIssue "1" @default.
• W4310551411 hasLocation W43105514111 @default.
• W4310551411 hasOpenAccess W4310551411 @default.
• W4310551411 hasPrimaryLocation W43105514111 @default.
• W4310551411 hasRelatedWork W1882733036 @default.
• W4310551411 hasRelatedWork W1992741870 @default.
• W4310551411 hasRelatedWork W2109998134 @default.
• W4310551411 hasRelatedWork W2157044008 @default.
• W4310551411 hasRelatedWork W2160425906 @default.
• W4310551411 hasRelatedWork W2546696010 @default.
• W4310551411 hasRelatedWork W2576563092 @default.
• W4310551411 hasRelatedWork W4232352653 @default.
• W4310551411 hasRelatedWork W4318020486 @default.
• W4310551411 hasRelatedWork W4319083788 @default.
• W4310551411 hasVolume "34" @default.
• W4310551411 isParatext "false" @default.
• W4310551411 isRetracted "false" @default.
• W4310551411 workType "article" @default.