On Sample Selection for Continual Learning: a Video Streaming Case Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dietmüller, Alexander, Jacob, Romain, Vanbever, Laurent
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913353080766464
author Dietmüller, Alexander
Jacob, Romain
Vanbever, Laurent
author_facet Dietmüller, Alexander
Jacob, Romain
Vanbever, Laurent
contents Machine learning (ML) is a powerful tool to model the complexity of communication networks. As networks evolve, we cannot only train once and deploy. Retraining models, known as continual learning, is necessary. Yet, to date, there is no established methodology to answer the key questions: With which samples to retrain? When should we retrain? We address these questions with the sample selection system Memento, which maintains a training set with the "most useful" samples to maximize sample space coverage. Memento particularly benefits rare patterns -- the notoriously long "tail" in networking -- and allows assessing rationally when retraining may help, i.e., when the coverage changes. We deployed Memento on Puffer, the live-TV streaming project, and achieved a 14% reduction of stall time, 3.5x the improvement of random sample selection. Finally, Memento does not depend on a specific model architecture; it is likely to yield benefits in other ML-based networking applications.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10290
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On Sample Selection for Continual Learning: a Video Streaming Case Study
Dietmüller, Alexander
Jacob, Romain
Vanbever, Laurent
Networking and Internet Architecture
Machine learning (ML) is a powerful tool to model the complexity of communication networks. As networks evolve, we cannot only train once and deploy. Retraining models, known as continual learning, is necessary. Yet, to date, there is no established methodology to answer the key questions: With which samples to retrain? When should we retrain? We address these questions with the sample selection system Memento, which maintains a training set with the "most useful" samples to maximize sample space coverage. Memento particularly benefits rare patterns -- the notoriously long "tail" in networking -- and allows assessing rationally when retraining may help, i.e., when the coverage changes. We deployed Memento on Puffer, the live-TV streaming project, and achieved a 14% reduction of stall time, 3.5x the improvement of random sample selection. Finally, Memento does not depend on a specific model architecture; it is likely to yield benefits in other ML-based networking applications.
title On Sample Selection for Continual Learning: a Video Streaming Case Study
topic Networking and Internet Architecture
url https://arxiv.org/abs/2405.10290