We make a case for in-network Continual Learning as a solution for seamless adaptation to evolving network conditions without forgetting past experiences. We propose implementing Active Learning-based selective data filtering in the data plane, allowing for data-efficient continual updates. We explore relevant challenges and propose future research directions.

Poster: Continual Network Learning

Di Cicco N.;Antichi G.;Tornatore M.
2023-01-01

Abstract

We make a case for in-network Continual Learning as a solution for seamless adaptation to evolving network conditions without forgetting past experiences. We propose implementing Active Learning-based selective data filtering in the data plane, allowing for data-efficient continual updates. We explore relevant challenges and propose future research directions.
2023
9798400702365
active learning
continual learning
in-network machine learning
programmable data planes
File in questo prodotto:
File Dimensione Formato  
_SIGCOMM_2023__Poster__Continual_Network_Learning.pdf

accesso aperto

: Pre-Print (o Pre-Refereeing)
Dimensione 482.16 kB
Formato Adobe PDF
482.16 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1253585
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact