Matches in SemOpenAlex for { <https://semopenalex.org/work/W3179699704> ?p ?o ?g. }
- W3179699704 abstract "The recent popularity growth of Deep Learning (DL) re-ignited the interest towards traffic classification, with several studies demonstrating the accuracy of DL-based classifiers to identify Internet applications' traffic. Even with the aid of hardware accelerators (GPUs, TPUs), DL model training remains expensive, and limits the ability to operate frequent model updates necessary to fit to the ever evolving nature of Internet traffic, and mobile traffic in particular. To address this pain point, in this work we explore Incremental Learning (IL) techniques to add new classes to models without a full retraining, hence speeding up model's updates cycle. We consider iCarl, a state of the art IL method, and MIRAGE-2019, a public dataset with traffic from 40 Android apps, aiming to understand if there is a case for incremental learning in traffic classification. By dissecting iCarl internals, we discuss ways to improve its design, contributing a revised version, namely iCarl+. Despite our analysis reveals their infancy, IL techniques are a promising research area on the roadmap towards automated DL-based traffic analysis systems." @default.
- W3179699704 created "2021-07-19" @default.
- W3179699704 creator A5002388358 @default.
- W3179699704 creator A5005807223 @default.
- W3179699704 creator A5031204317 @default.
- W3179699704 creator A5059880462 @default.
- W3179699704 creator A5062538316 @default.
- W3179699704 creator A5064292700 @default.
- W3179699704 creator A5068466049 @default.
- W3179699704 date "2021-07-09" @default.
- W3179699704 modified "2023-10-18" @default.
- W3179699704 title "A First Look at Class Incremental Learning in Deep Learning Mobile Traffic Classification" @default.
- W3179699704 cites W1525647652 @default.
- W3179699704 cites W1682403713 @default.
- W3179699704 cites W1821462560 @default.
- W3179699704 cites W1997865285 @default.
- W3179699704 cites W2007556421 @default.
- W3179699704 cites W2009727399 @default.
- W3179699704 cites W2015563892 @default.
- W3179699704 cites W2096118443 @default.
- W3179699704 cites W2106100348 @default.
- W3179699704 cites W2119271160 @default.
- W3179699704 cites W2143991132 @default.
- W3179699704 cites W2157349061 @default.
- W3179699704 cites W2267727210 @default.
- W3179699704 cites W2275741344 @default.
- W3179699704 cites W2284008484 @default.
- W3179699704 cites W2473930607 @default.
- W3179699704 cites W2554616628 @default.
- W3179699704 cites W2613715541 @default.
- W3179699704 cites W2618767506 @default.
- W3179699704 cites W2750674396 @default.
- W3179699704 cites W277886906 @default.
- W3179699704 cites W2785889759 @default.
- W3179699704 cites W2867167548 @default.
- W3179699704 cites W2884282566 @default.
- W3179699704 cites W2898413119 @default.
- W3179699704 cites W2900853407 @default.
- W3179699704 cites W2921165530 @default.
- W3179699704 cites W2939137134 @default.
- W3179699704 cites W2949072481 @default.
- W3179699704 cites W2954929116 @default.
- W3179699704 cites W2963038864 @default.
- W3179699704 cites W2963072899 @default.
- W3179699704 cites W2963516518 @default.
- W3179699704 cites W2964067969 @default.
- W3179699704 cites W2964189064 @default.
- W3179699704 cites W2965713461 @default.
- W3179699704 cites W2982309555 @default.
- W3179699704 cites W3024202154 @default.
- W3179699704 cites W3032949543 @default.
- W3179699704 cites W3047014424 @default.
- W3179699704 cites W3099396445 @default.
- W3179699704 cites W3108280718 @default.
- W3179699704 cites W3112858938 @default.
- W3179699704 cites W34738725 @default.
- W3179699704 hasPublicationYear "2021" @default.
- W3179699704 type Work @default.
- W3179699704 sameAs 3179699704 @default.
- W3179699704 citedByCount "0" @default.
- W3179699704 crossrefType "posted-content" @default.
- W3179699704 hasAuthorship W3179699704A5002388358 @default.
- W3179699704 hasAuthorship W3179699704A5005807223 @default.
- W3179699704 hasAuthorship W3179699704A5031204317 @default.
- W3179699704 hasAuthorship W3179699704A5059880462 @default.
- W3179699704 hasAuthorship W3179699704A5062538316 @default.
- W3179699704 hasAuthorship W3179699704A5064292700 @default.
- W3179699704 hasAuthorship W3179699704A5068466049 @default.
- W3179699704 hasConcept C108583219 @default.
- W3179699704 hasConcept C110875604 @default.
- W3179699704 hasConcept C111919701 @default.
- W3179699704 hasConcept C119857082 @default.
- W3179699704 hasConcept C136764020 @default.
- W3179699704 hasConcept C144133560 @default.
- W3179699704 hasConcept C154945302 @default.
- W3179699704 hasConcept C155202549 @default.
- W3179699704 hasConcept C15744967 @default.
- W3179699704 hasConcept C169988225 @default.
- W3179699704 hasConcept C2778712577 @default.
- W3179699704 hasConcept C2780586970 @default.
- W3179699704 hasConcept C41008148 @default.
- W3179699704 hasConcept C557433098 @default.
- W3179699704 hasConcept C63969886 @default.
- W3179699704 hasConcept C77805123 @default.
- W3179699704 hasConceptScore W3179699704C108583219 @default.
- W3179699704 hasConceptScore W3179699704C110875604 @default.
- W3179699704 hasConceptScore W3179699704C111919701 @default.
- W3179699704 hasConceptScore W3179699704C119857082 @default.
- W3179699704 hasConceptScore W3179699704C136764020 @default.
- W3179699704 hasConceptScore W3179699704C144133560 @default.
- W3179699704 hasConceptScore W3179699704C154945302 @default.
- W3179699704 hasConceptScore W3179699704C155202549 @default.
- W3179699704 hasConceptScore W3179699704C15744967 @default.
- W3179699704 hasConceptScore W3179699704C169988225 @default.
- W3179699704 hasConceptScore W3179699704C2778712577 @default.
- W3179699704 hasConceptScore W3179699704C2780586970 @default.
- W3179699704 hasConceptScore W3179699704C41008148 @default.
- W3179699704 hasConceptScore W3179699704C557433098 @default.
- W3179699704 hasConceptScore W3179699704C63969886 @default.
- W3179699704 hasConceptScore W3179699704C77805123 @default.