{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:38:22Z","timestamp":1778258302071,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T00:00:00Z","timestamp":1717977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,10]]},"DOI":"10.1145\/3643488.3660293","type":"proceedings-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T12:21:00Z","timestamp":1718108460000},"page":"37-42","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["A Survey of Model Compression and Its Feedback Mechanism in Federated Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7987-6627","authenticated-orcid":false,"given":"Duy-Dong","family":"Le","sequence":"first","affiliation":[{"name":"Industrial University of Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4649-8417","authenticated-orcid":false,"given":"Anh-Khoa","family":"Tran","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-4366","authenticated-orcid":false,"given":"The-Bao","family":"Pham","sequence":"additional","affiliation":[{"name":"Saigon University, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6592-4480","authenticated-orcid":false,"given":"Tuong-Nguyen","family":"Huynh","sequence":"additional","affiliation":[{"name":"Industrial University of Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-015-2350-1"},{"key":"e_1_3_2_1_2_1","volume-title":"Combining Weight Pruning and Knowledge Distillation For CNN Compression. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Aghli Nima","year":"2021","unstructured":"Nima Aghli and Eraldo Ribeiro. 2021. Combining Weight Pruning and Knowledge Distillation For CNN Compression. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2021), 3185\u20133192."},{"key":"e_1_3_2_1_3_1","volume-title":"Optimal gradient compression for distributed and federated learning. arXiv preprint arXiv:2010.03246","author":"Albasyoni Alyazeed","year":"2020","unstructured":"Alyazeed Albasyoni, Mher Safaryan, Laurent Condat, and Peter Richt\u00e1rik. 2020. Optimal gradient compression for distributed and federated learning. arXiv preprint arXiv:2010.03246 (2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-020-01596-1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2021EDL8026"},{"key":"e_1_3_2_1_7_1","volume-title":"Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","author":"Chollet Fran\u00e7ois","year":"2016","unstructured":"Fran\u00e7ois Chollet. 2016. Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 1800\u20131807."},{"key":"e_1_3_2_1_8_1","volume-title":"Guaranteed Quantization Error Computation for Neural Network Model Compression. 2023 IEEE International Conference on Industrial Technology (ICIT)","author":"Cooke Wesley","year":"2023","unstructured":"Wesley Cooke, Zihao Mo, and Weiming Xiang. 2023. Guaranteed Quantization Error Computation for Neural Network Model Compression. 2023 IEEE International Conference on Industrial Technology (ICIT) (2023), 1\u20134."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Diamos Greg","year":"2016","unstructured":"Greg Diamos, Shubho Sengupta, Bryan Catanzaro, Mike Chrzanowski, Adam Coates, Erich Elsen, Jesse Engel, Awni Hannun, and Sanjeev Satheesh. 2016. Persistent rnns: Stashing recurrent weights on-chip. In International Conference on Machine Learning. PMLR, 2024\u20132033."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019465"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_12_1","volume-title":"Mlpinit: Embarrassingly simple gnn training acceleration with mlp initialization. arXiv preprint arXiv:2210.00102","author":"Han Xiaotian","year":"2022","unstructured":"Xiaotian Han, Tong Zhao, Yozen Liu, Xia Hu, and Neil Shah. 2022. Mlpinit: Embarrassingly simple gnn training acceleration with mlp initialization. arXiv preprint arXiv:2210.00102 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard G","year":"2017","unstructured":"Andrew\u00a0G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_14_1","volume-title":"Fedsynth: Gradient compression via synthetic data in federated learning. arXiv preprint arXiv:2204.01273","author":"Hu Shengyuan","year":"2022","unstructured":"Shengyuan Hu, Jack Goetz, Kshitiz Malik, Hongyuan Zhan, Zhe Liu, and Yue Liu. 2022. Fedsynth: Gradient compression via synthetic data in federated learning. arXiv preprint arXiv:2204.01273 (2022)."},{"key":"e_1_3_2_1_15_1","unstructured":"Berivan Isik Albert No and Tsachy Weissman. 2021. Rate-Distortion Theoretic Model Compression: Successive Refinement for Pruning."},{"key":"e_1_3_2_1_16_1","unstructured":"Qinjun Jiang and Matthew\u00a0D. Sinclair. 2021. Reducing Synchronization Overhead for Persistent RNNs."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-023-01271-1"},{"key":"e_1_3_2_1_18_1","volume-title":"Advances and open problems in federated learning. Foundations and Trends\u00ae in Machine Learning 14, 1\u20132","author":"Kairouz Peter","year":"2021","unstructured":"Peter Kairouz, H\u00a0Brendan McMahan, Brendan Avent, Aur\u00e9lien Bellet, Mehdi Bennis, Arjun\u00a0Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, 2021. Advances and open problems in federated learning. Foundations and Trends\u00ae in Machine Learning 14, 1\u20132 (2021), 1\u2013210."},{"key":"e_1_3_2_1_19_1","unstructured":"Sai\u00a0Praneeth Karimireddy Quentin Rebjock Sebastian Stich and Martin Jaggi. 2019. Error feedback fixes signsgd and other gradient compression schemes. (2019) 3252\u20133261."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10139-6"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Petros Katsileros Nikiforos Mandilaras Dimitrios Mallis Vassilis Pitsikalis Stavros Theodorakis and Gil Chamiel. 2022. An Incremental Learning framework for Large-scale CTR Prediction. (2022) 490\u2013493.","DOI":"10.1145\/3523227.3547390"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/a15110434"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/computers12030060"},{"key":"e_1_3_2_1_24_1","volume-title":"Wyner-Ziv gradient compression for federated learning. arXiv preprint arXiv:2111.08277","author":"Liang Kai","year":"2021","unstructured":"Kai Liang, Huiru Zhong, Haoning Chen, and Youlong Wu. 2021. Wyner-Ziv gradient compression for federated learning. arXiv preprint arXiv:2111.08277 (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Zero-shot Adversarial Quantization. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu Yuang","year":"2021","unstructured":"Yuang Liu, Wei Zhang, and Jun Wang. 2021. Zero-shot Adversarial Quantization. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 1512\u20131521."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3084813"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661900"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Xiaojun Ma Qin Chen Yuanyi Ren Guojie Song and Liang Wang. 2022. Meta-weight graph neural network: Push the limits beyond global homophily. (2022) 1270\u20131280.","DOI":"10.1145\/3485447.3512100"},{"key":"e_1_3_2_1_29_1","unstructured":"Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise\u00a0Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics. PMLR 1273\u20131282."},{"key":"e_1_3_2_1_30_1","volume-title":"Intrinisic Gradient Compression for Federated Learning. arXiv preprint arXiv:2112.02656","author":"Melas-Kyriazi Luke","year":"2021","unstructured":"Luke Melas-Kyriazi and Franklyn Wang. 2021. Intrinisic Gradient Compression for Federated Learning. arXiv preprint arXiv:2112.02656 (2021)."},{"key":"e_1_3_2_1_31_1","unstructured":"Georgii\u00a0Sergeevich Novikov Daniel Bershatsky Julia Gusak Alex Shonenkov Denis\u00a0Valerievich Dimitrov and Ivan Oseledets. 2023. Few-bit backward: Quantized gradients of activation functions for memory footprint reduction. (2023) 26363\u201326381."},{"key":"e_1_3_2_1_32_1","volume-title":"Model compression via distillation and quantization. ArXiv abs\/1802.05668","author":"Polino Antonio","year":"2018","unstructured":"Antonio Polino, Razvan Pascanu, and Dan Alistarh. 2018. Model compression via distillation and quantization. ArXiv abs\/1802.05668 (2018)."},{"key":"e_1_3_2_1_33_1","volume-title":"Conference of the European Chapter of the Association for Computational Linguistics.","author":"Press Ofir","year":"2016","unstructured":"Ofir Press and Lior Wolf. 2016. Using the Output Embedding to Improve Language Models. In Conference of the European Chapter of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.336"},{"key":"e_1_3_2_1_36_1","volume-title":"Model compression for communication efficient federated learning","author":"Shah Suhail\u00a0Mohmad","year":"2021","unstructured":"Suhail\u00a0Mohmad Shah and Vincent\u00a0KN Lau. 2021. Model compression for communication efficient federated learning. IEEE Transactions on Neural Networks and Learning Systems (2021)."},{"key":"e_1_3_2_1_37_1","volume-title":"Neural network quantization with ai model efficiency toolkit (aimet). arXiv preprint arXiv:2201.08442","author":"Siddegowda Sangeetha","year":"2022","unstructured":"Sangeetha Siddegowda, Marios Fournarakis, Markus Nagel, Tijmen Blankevoort, Chirag Patel, and Abhijit Khobare. 2022. Neural network quantization with ai model efficiency toolkit (aimet). arXiv preprint arXiv:2201.08442 (2022)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Suraj Srinivas Andrey Kuzmin Markus Nagel Mart van Baalen Andrii Skliar and Tijmen Blankevoort. 2022. Cyclical pruning for sparse neural networks. (2022) 2762\u20132771.","DOI":"10.1109\/CVPRW56347.2022.00312"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455953"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02287-z"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3182659"},{"key":"e_1_3_2_1_42_1","unstructured":"Mitchell Wortsman Gabriel Ilharco Samir\u00a0Ya Gadre Rebecca Roelofs Raphael Gontijo-Lopes Ari\u00a0S Morcos Hongseok Namkoong Ali Farhadi Yair Carmon Simon Kornblith 2022. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. (2022) 23965\u201323998."},{"key":"e_1_3_2_1_43_1","volume-title":"Quantized Convolutional Neural Networks for Mobile Devices. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wu Jiaxiang","year":"2015","unstructured":"Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, and Jian Cheng. 2015. Quantized Convolutional Neural Networks for Mobile Devices. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), 4820\u20134828."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01286-x"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3473330"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3165268"},{"key":"e_1_3_2_1_47_1","first-page":"582","article-title":"Task-specific Compression for Multi-task Language Models using Attribution-based Pruning","volume":"2023","author":"Yang Nakyeong","year":"2023","unstructured":"Nakyeong Yang, Yunah Jang, Hwanhee Lee, Seohyeong Jeong, and Kyomin Jung. 2023. Task-specific Compression for Multi-task Language Models using Attribution-based Pruning. In Findings of the Association for Computational Linguistics: EACL 2023. 582\u2013592.","journal-title":"Findings of the Association for Computational Linguistics: EACL"},{"key":"e_1_3_2_1_48_1","volume-title":"Online Model Compression for Federated Learning with Large Models. ArXiv abs\/2205.03494","author":"Yang TJ","year":"2022","unstructured":"TJ Yang, Y Xiao, G Motta, F Beaufays, R Mathews, and M Chen. 2022. Online Model Compression for Federated Learning with Large Models. ArXiv abs\/2205.03494 (2022)."},{"key":"e_1_3_2_1_49_1","volume-title":"Student-friendly Knowledge Distillation. ArXiv abs\/2305.10893","author":"Yuan Mengyang","year":"2023","unstructured":"Mengyang Yuan, Bo Lang, and Fengnan Quan. 2023. Student-friendly Knowledge Distillation. ArXiv abs\/2305.10893 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02802-8"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Tunhou Zhang Dehua Cheng Yuchen He Zhengxing Chen Xiaoliang Dai Liang Xiong Feng Yan Hai Li Yiran Chen and Wei Wen. 2023. NASRec: weight sharing neural architecture search for recommender systems. (2023) 1199\u20131207.","DOI":"10.1145\/3543507.3583446"},{"key":"e_1_3_2_1_52_1","volume-title":"Learn by Oneself: Exploiting Weight-Sharing Potential in Knowledge Distillation Guided Ensemble Network","author":"Zhao Qi","year":"2023","unstructured":"Qi Zhao, Shuchang Lyu, Lijiang Chen, Binghao Liu, Ting-Bing Xu, Guangliang Cheng, and Wenquan Feng. 2023. Learn by Oneself: Exploiting Weight-Sharing Potential in Knowledge Distillation Guided Ensemble Network. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Kai Zhen Hieu\u00a0Duy Nguyen Raviteja Chinta Nathan Susanj Athanasios Mouchtaris Tariq Afzal and Ariya Rastrow. 2022. Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition. In Interspeech.","DOI":"10.21437\/Interspeech.2022-874"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11045-019-00686-z"},{"key":"e_1_3_2_1_55_1","volume-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression. ArXiv abs\/1710.01878","author":"Zhu Michael","year":"2017","unstructured":"Michael Zhu and Suyog Gupta. 2017. To prune, or not to prune: exploring the efficacy of pruning for model compression. ArXiv abs\/1710.01878 (2017)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["The Fifth Workshop on Intelligent Cross-Data Analysis and Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643488.3660293","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3643488.3660293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T12:49:10Z","timestamp":1756212550000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643488.3660293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,10]]},"references-count":55,"alternative-id":["10.1145\/3643488.3660293","10.1145\/3643488"],"URL":"https:\/\/doi.org\/10.1145\/3643488.3660293","relation":{},"subject":[],"published":{"date-parts":[[2024,6,10]]},"assertion":[{"value":"2024-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}