A Distributed Asynchronous Deep Reinforcement Learning Framework for Recommender Systems
Files in This Item:
|A Distributed Asynchronous Deep Reinforcement Learning Framework for Recommender Systems.pdf||471.81 kB||Adobe PDF||Download|
|Title:||A Distributed Asynchronous Deep Reinforcement Learning Framework for Recommender Systems||Authors:||Shi, Bichen; Tragos, Elias; Ozsoy, Makbule Gulcin; Dong, Ruihai; Smyth, Barry; Hurley, Neil J.; Lawlor, Aonghus||Permanent link:||http://hdl.handle.net/10197/12220||Date:||26-Sep-2020||Online since:||2021-05-27T11:57:43Z||Abstract:||In this paper we propose DADRL, a distributed, asynchronous reinforcement learning recommender system based on the asynchronous advantage actor-critic model (A3C), which combines ideas from A3C and federated learning (FL). The proposed algorithm keeps the user preferences or interactions on local devices and uses a combination of on-device, local recommendation models and a complementary global model. The global model is trained only by the loss gradients of the local models, rather than directly using user preferences or interactions data. We demonstrate, using well-known datasets and benchmark algorithms, how this approach can deliver performance that is comparable with the current state-of-the-art while enhancing user privacy.||Funding Details:||Science Foundation Ireland||Funding Details:||Insight Research Centre||Type of material:||Conference Publication||Publisher:||ACM||Copyright (published version):||2018 Association for Computing Machinery||Keywords:||Novel personal sensing; Reinforcement learning; Recommender systems; Distributed learning||DOI:||10.1145/3383313||Other versions:||https://recsys.acm.org/recsys20/||Language:||en||Status of Item:||Peer reviewed||Conference Details:||The 14th ACM Conference on Recommender Systems (RecSys 2020), Online, 22-26 September 2020||This item is made available under a Creative Commons License:||https://creativecommons.org/licenses/by-nc-nd/3.0/ie/|
|Appears in Collections:||Insight Research Collection|
Show full item record
If you are a publisher or author and have copyright concerns for any item, please email email@example.com and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.