Training Mixed-Domain Translation Models via Federated Learning

被引:0
|
作者
Passban, Peyman [1 ]
Roosta, Tanya [1 ]
Gupta, Rahul [1 ]
Chadha, Ankit [1 ]
Chung, Clement [1 ]
机构
[1] Amazon, Seattle, WA 98121 USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques. In this work, we leverage federated learning (FL) in order to tackle the problem. Our investigation demonstrates that with slight modifications in the training process, neural machine translation (NMT) engines can be easily adapted when an FL-based aggregation is applied to fuse different domains. Experimental results also show that engines built via FL are able to perform on par with state-of-the-art baselines that rely on centralized training techniques. We evaluate our hypothesis in the presence of five datasets with different sizes, from different domains, to translate from German into English and discuss how FL and NMT can mutually benefit from each other. In addition to providing benchmarking results on the union of FL and NMT, we also propose a novel technique to dynamically control the communication bandwidth by selecting impactful parameters during FL updates. This is a significant achievement considering the large size of NMT engines that need to be exchanged between FL parties.
引用
收藏
页码:2576 / 2586
页数:11
相关论文
共 50 条
  • [21] Corrected Mixed-Domain Measurements for Software Defined Radios
    Ribeiro, Diogo C.
    Cruz, Pedro Miguel
    Carvalho, Nuno Borges
    2012 42ND EUROPEAN MICROWAVE CONFERENCE (EUMC), 2012, : 554 - 557
  • [22] Multilevel and mixed-domain simulation of analog circuits and systems
    Saleh, RA
    Antao, BAA
    Singh, J
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 1996, 15 (01) : 68 - 82
  • [23] On-Device Training of Machine Learning Models on Microcontrollers with Federated Learning
    Llisterri Gimenez, Nil
    Monfort Grau, Marc
    Pueyo Centelles, Roger
    Freitag, Felix
    ELECTRONICS, 2022, 11 (04)
  • [24] Mixed-Domain Edge-Aware Image Manipulation
    Li, Xian-Ying
    Gu, Yan
    Hu, Shi-Min
    Martin, Ralph R.
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (05) : 1915 - 1925
  • [25] Mixed-domain coding of speech at 3 kb/s
    DeMartin, JC
    Gersho, A
    1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 216 - 219
  • [26] Extraction and LVS for mixed-domain integrated MEMS layouts
    Baidya, B
    Mukherjee, T
    IEEE/ACM INTERNATIONAL CONFERENCE ON CAD-02, DIGEST OF TECHNICAL PAPERS, 2002, : 361 - 366
  • [27] An Optimal Control Based Motion Planner in Mixed-domain
    Hu, Jia
    Wang, Hao-Ran
    Feng, Yong-Wei
    Li, Xin
    Zhongguo Gonglu Xuebao/China Journal of Highway and Transport, 2022, 35 (03): : 43 - 54
  • [28] Reliability enhancement of mixed-domain seismic inversion with bounding constraints
    Li, Kun
    Yin, Xing-Yao
    Zong, Zhao-Yun
    INVERSE PROBLEMS IN SCIENCE AND ENGINEERING, 2019, 27 (02) : 255 - 277
  • [29] Federated learning via reweighting information bottleneck with domain generalization
    Li, Fangyu
    Chen, Xuqiang
    Han, Zhu
    Du, Yongping
    Han, Honggui
    INFORMATION SCIENCES, 2024, 677
  • [30] Privacy Leakage of Adversarial Training Models in Federated Learning Systems
    Zhang, Jingyang
    Chen, Yiran
    Li, Hai
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 107 - 113