onr:"swepub:oai:DiVA.org:kth-316104"
Sökning: onr:"swepub:oai:DiVA.org:kth-316104" > Meta-reinforcement ...
- 1 av 1
- Föregående post
- Nästa post
- Till träfflistan
- Antaris, StefanosHive Streaming AB, Sweden (författare)
Meta-reinforcement learning via buffering graph signatures for live video streaming events
- Artikel/kapitelEngelska2021
Förlag, utgivningsår, omfång ...
- 2022-01-19
- New York, NY, USA :Association for Computing Machinery (ACM),2021
- printrdacarrier
Nummerbeteckningar
- LIBRIS-ID:oai:DiVA.org:kth-316104
- https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-316104URI
- https://doi.org/10.1145/3487351.3490973DOI
Kompletterande språkuppgifter
- Språk:engelska
- Sammanfattning på:engelska
Ingår i deldatabas
- SwePubSwePub
Klassifikation
Anmärkningar
- Part of ISBN 9781450391283QC 20220822
- In this study, we present a meta-learning model to adapt the predictions of the network's capacity between viewers who participate in a live video streaming event. We propose the MELANIE model, where an event is formulated as a Markov Decision Process, performing meta-learning on reinforcement learning tasks. By considering a new event as a task, we design an actor-critic learning scheme to compute the optimal policy on estimating the viewers' high-bandwidth connections. To ensure fast adaptation to new connections or changes among viewers during an event, we implement a prioritized replay memory buffer based on the Kullback-Leibler divergence of the reward/throughput of the viewers' connections. Moreover, we adopt a model-agnostic meta-learning framework to generate a global model from past events. As viewers scarcely participate in several events, the challenge resides on how to account for the low structural similarity of different events. To combat this issue, we design a graph signature buffer to calculate the structural similarities of several streaming events and adjust the training of the global model accordingly. We evaluate the proposed model on the link weight prediction task on three real-world datasets of live video streaming events. Our experiments demonstrate the effectiveness of our proposed model, with an average relative gain of 25% against state-of-the-art strategies. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://github.com/stefanosantaris/melanie
Ämnesord och genrebeteckningar
- NATURVETENSKAP Data- och informationsvetenskap Programvaruteknik hsv//swe
- NATURAL SCIENCES Computer and Information Sciences Software Engineering hsv//eng
- graph signatures
- meta-reinforcement learning
- video streaming
- Cell proliferation
- Computer vision
- Markov processes
- Reinforcement learning
- Global models
- Graph signature
- Live video streaming
- Markov Decision Processes
- Meta-learning models
- Metalearning
- Network Capacity
- Structural similarity
- Video-streaming
Biuppslag (personer, institutioner, konferenser, titlar ...)
- Rafailidis, DimitriosUniversity of Thessaly, Greece (författare)
- Girdzijauskas, SarunasKTH,Programvaruteknik och datorsystem, SCS(Swepub:kth)u1k70r02 (författare)
- Hive Streaming AB, SwedenUniversity of Thessaly, Greece (creator_code:org_t)
Sammanhörande titlar
- Ingår i:Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021New York, NY, USA : Association for Computing Machinery (ACM), s. 385-392
Internetlänk
Till lärosätets databas
- 1 av 1
- Föregående post
- Nästa post
- Till träfflistan
Hitta mer i SwePub
- Av författaren/redakt...
- Antaris, Stefano ...
- Rafailidis, Dimi ...
- Girdzijauskas, S ...
- Om ämnet
-
- NATURVETENSKAP
- NATURVETENSKAP
- och Data och informa ...
- och Programvarutekni ...
- Artiklar i publikationen
- Proceedings of t ...
- Av lärosätet
- Kungliga Tekniska Högskolan
Sök utanför SwePub
- Sök vidare i:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - Nationella bibliotekssystem
- LIBRIS.kb.se
