{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T07:03:14Z","timestamp":1763794994617,"version":"3.45.0"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"12","funder":[{"name":"Higher Education (MoHE) Malaysia","award":["FRGS\/1\/2023\/ICT08\/UTAR\/02\/1"],"award-info":[{"award-number":["FRGS\/1\/2023\/ICT08\/UTAR\/02\/1"]}]},{"name":"scholarship of Campus France","award":["143528Q"],"award-info":[{"award-number":["143528Q"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62171188"],"award-info":[{"award-number":["62171188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Foreign Expert Project of China","award":["H20241004"],"award-info":[{"award-number":["H20241004"]}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>Recently, Deep Reinforcement Learning (DRL) has been applied to enhance the Quality of Experience (QoE) of Adaptive Bitrate Streaming (ABR) by adjusting the video quality level in real time based on instantaneous network conditions. To build a state-of-the-art DRL-based ABR (DRLABR) algorithm, it must learn from the clients\u2019 actual network and video streaming behavior. However, collecting such data directly from clients introduces several challenges, including privacy concerns, high bandwidth consumption, and the straggler effect\u2014where poor network conditions of certain clients delay the training process, as DRLABR\u2019s performance is highly dependent on network interactions. To overcome these limitations, we propose a decentralized training approach for DRLABR using a Federated Learning (FL) framework. Instead of gathering raw data, clients train their local DRLABR models independently and send only model updates to the central server. To address the straggler issue, we propose to desynchronize the FL update rules, allowing clients to contribute their model updates at their own pace, regardless of varying network conditions. In addition, we design a DRL-based client selection mechanism to prevent oversampling of high-bandwidth clients, which could lead to model divergence, thereby ensuring balanced participation and improving the overall training efficiency. We validate our approach through a comprehensive simulation encompassing diverse video content and real-world network traces, simulating a wide range of streaming activities. Our results show that the proposed framework significantly outperforms conventional FedAvg and FedAsync methods, achieving the highest average QoE score of 2.02 and reducing the total training latency by 21.26%.<\/jats:p>","DOI":"10.1145\/3765759","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T15:34:16Z","timestamp":1757000056000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Client Selection for Asynchronous Federated Learning for Adaptive Bitrate Streaming"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4598-2653","authenticated-orcid":false,"given":"Yi Jie","family":"Wong","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Sungai Long Campus, Selangor, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4600-9839","authenticated-orcid":false,"given":"Mau-Luen","family":"Tham","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Sungai Long Campus, Selangor, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7094-8612","authenticated-orcid":false,"given":"Ban-Hoe","family":"Kwan","sequence":"additional","affiliation":[{"name":"Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Sungai Long Campus, Selangor, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4065-1639","authenticated-orcid":false,"given":"Yoong Choon","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Sungai Long Campus, Selangor, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-8722","authenticated-orcid":false,"given":"Anissa","family":"Mokraoui","sequence":"additional","affiliation":[{"name":"L2TI Laboratory, University Sorbonne Paris Nord, Villetaneuse, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0043-1655","authenticated-orcid":false,"given":"Feng","family":"Ke","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,21]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_1_2_2","DOI":"10.1109\/TIP.2017.2729891"},{"doi-asserted-by":"publisher","key":"e_1_3_1_3_2","DOI":"10.48550\/arxiv.1602.05629"},{"unstructured":"Dash-Industry-Forum. 2023. dash.js\/test\/unit\/data\/dash\/manifest.xml at v5.0.0. Dash-Industry-Forum\/dash.js. Retrieved January 7 2024 from https:\/\/github.com\/Dash-Industry-Forum\/dash.js\/blob\/v5.0.0\/test\/unit\/data\/dash\/manifest.xml","key":"e_1_3_1_4_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_5_2","DOI":"10.1145\/2428556.2428577"},{"doi-asserted-by":"publisher","key":"e_1_3_1_6_2","DOI":"10.1109\/TBC.2019.2954064"},{"unstructured":"Yu Gao Pengyuan Zhou Zhi Liu Senior Member Bo Han and Pan Hui. 2022. FRAS: Federated reinforcement learning empowered adaptive point cloud video streaming. arXiv:2207.07394v4. Retrieved from https:\/\/arxiv.org\/abs\/2207.07394v4","key":"e_1_3_1_7_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_8_2","DOI":"10.1609\/aaai.v30i1.10295"},{"doi-asserted-by":"publisher","key":"e_1_3_1_9_2","DOI":"10.1145\/2619239.2626296"},{"doi-asserted-by":"publisher","key":"e_1_3_1_10_2","DOI":"10.1109\/JSAC.2020.3000363"},{"doi-asserted-by":"publisher","key":"e_1_3_1_11_2","DOI":"10.1145\/3343031.3351014"},{"doi-asserted-by":"publisher","key":"e_1_3_1_12_2","DOI":"10.1109\/ACCESS.2021.3054909"},{"doi-asserted-by":"publisher","key":"e_1_3_1_13_2","DOI":"10.1109\/ACCESS.2023.3314732"},{"doi-asserted-by":"publisher","key":"e_1_3_1_14_2","DOI":"10.1109\/TNET.2013.2291681"},{"doi-asserted-by":"publisher","key":"e_1_3_1_15_2","DOI":"10.48550\/arxiv.1610.05492"},{"doi-asserted-by":"publisher","key":"e_1_3_1_16_2","DOI":"10.1145\/2155555.2155570"},{"doi-asserted-by":"publisher","key":"e_1_3_1_17_2","DOI":"10.48550\/arxiv.2102.02079"},{"doi-asserted-by":"publisher","key":"e_1_3_1_18_2","DOI":"10.3390\/ELECTRONICS11233968"},{"doi-asserted-by":"publisher","key":"e_1_3_1_19_2","DOI":"10.1109\/TCSVT.2023.3243901"},{"doi-asserted-by":"publisher","key":"e_1_3_1_20_2","DOI":"10.1145\/3098822.3098843"},{"doi-asserted-by":"publisher","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. DOI: 10.48550\/arxiv.1312.5602","key":"e_1_3_1_21_2","DOI":"10.48550\/arxiv.1312.5602"},{"doi-asserted-by":"publisher","key":"e_1_3_1_22_2","DOI":"10.23919\/SPA50552.2020.9241250"},{"doi-asserted-by":"publisher","key":"e_1_3_1_23_2","DOI":"10.1145\/3204949.3208123"},{"doi-asserted-by":"publisher","key":"e_1_3_1_24_2","DOI":"10.1145\/3336497"},{"doi-asserted-by":"publisher","key":"e_1_3_1_25_2","DOI":"10.1109\/TNET.2020.2996964"},{"doi-asserted-by":"publisher","key":"e_1_3_1_26_2","DOI":"10.1145\/1943552.1943572"},{"doi-asserted-by":"publisher","key":"e_1_3_1_27_2","DOI":"10.1109\/WCNC55385.2023.10118891"},{"unstructured":"Phuong L. Vo Nghia T. Nguyen Long Luu Canh T. Dinh Nguyen H. Tran and Tuan-Anh Le. 2023. Federated deep reinforcement learning-based bitrate adaptation for dynamic adaptive streaming over HTTP. arXiv:2306.15860v1. Retrieved from https:\/\/arxiv.org\/abs\/2306.15860v1","key":"e_1_3_1_28_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_29_2","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"doi-asserted-by":"publisher","key":"e_1_3_1_30_2","DOI":"10.3390\/S23052494"},{"doi-asserted-by":"publisher","key":"e_1_3_1_31_2","DOI":"10.1016\/J.IOT.2024.101270"},{"unstructured":"Cong Xie Oluwasanmi Koyejo and Indranil Gupta. 2019. Asynchronous federated optimization. arXiv:1903.03934v5. Retrieved from https:\/\/arxiv.org\/abs\/1903.03934v5","key":"e_1_3_1_32_2"},{"doi-asserted-by":"publisher","key":"e_1_3_1_33_2","DOI":"10.23919\/IFIPNETWORKING57963.2023.10186404"},{"doi-asserted-by":"publisher","key":"e_1_3_1_34_2","DOI":"10.1109\/LWC.2021.3106945"},{"doi-asserted-by":"publisher","key":"e_1_3_1_35_2","DOI":"10.1145\/2785956.2787486"},{"doi-asserted-by":"publisher","key":"e_1_3_1_36_2","DOI":"10.1609\/AAAI.V36I8.20894"},{"unstructured":"UMass-LIDS\/sabre: Sabre: simulating ABR environments. Retrieved March 6 2024 from https:\/\/github.com\/UMass-LIDS\/sabre","key":"e_1_3_1_37_2"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3765759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T06:58:48Z","timestamp":1763794728000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3765759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,21]]},"references-count":36,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3765759"],"URL":"https:\/\/doi.org\/10.1145\/3765759","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2025,11,21]]},"assertion":[{"value":"2025-01-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}