MLSP-P4.5
NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning
Zhen Fang, Miao Yang, Zehang Lin, Xiamen University of Technology, China; Zheng Lin, The University of Hong Kong, China; Zihan Fang, City University of Hong Kong, China; Zongyuan Zhang, Tianyang Duan, The University of Hong Kong, China; Dong Huang, National University of Singapore, Singapore; Shunzhi Zhu, Xiamen University of Technology, China
Session:
MLSP-P4: Federated and Distributed Machine Learning Systems I Poster
Track:
Machine Learning for Signal Processing [ML]
Location:
Poster Area 7
Presentation Time:
Tue, 5 May, 14:00 - 16:00
Presentation
Discussion
Resources
No resources available.
Session MLSP-P4
MLSP-P4.1: PGFed: Prompt-Guided Distillation for Personalized Federated Learning with Model Heterogeneity
Xu Yang, Jiyuan Feng, Lin Zhong, Lingzhi Wang, Binxin Fang, Qing Liao, Harbin Institute of Technology (Shenzhen), China
MLSP-P4.2: DFMAD: DATA-FREE BACKDOOR DEFENSE FOR FEDERATED LEARNING VIA MULTI-TEACHER ADVERSARIAL DISTILLATION
Kai Zhong, Qiao Yan, Weimin Lai, Shenzhen University, China
MLSP-P4.3: ONE-SHOT SEQUENTIAL FEDERATED LEARNING WITH DUAL-DISTILLATION
Haotian Xu, Jinrui Zhou, Xichong Zhang, Mingjun Xiao, University of Science and Technology of China, China
MLSP-P4.4: ACCELERATING FEDERATED LEARNING THROUGH DROPOUT OF RENEWABLE NEURON PARAMETERS
Hong Liao, College of Computer Science and Technology, Harbin Engineering University, China; Zimu Guo, State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, CAS, China; Yuncong Shao, Qiao Tian, College of Computer Science and Technology, Harbin Engineering University, China; Yuhui Zhang, Lutan Zhao, Rui Hou, State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, CAS, China
MLSP-P4.5: NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning
Zhen Fang, Miao Yang, Zehang Lin, Xiamen University of Technology, China; Zheng Lin, The University of Hong Kong, China; Zihan Fang, City University of Hong Kong, China; Zongyuan Zhang, Tianyang Duan, The University of Hong Kong, China; Dong Huang, National University of Singapore, Singapore; Shunzhi Zhu, Xiamen University of Technology, China
MLSP-P4.6: FED-MET: MEMORY-EFFICIENT ELASTIC TRAINING IN FEDERATED LEARNING
Cui Miao, Tao Chang, National University of Defense Technology, China; Meihan Wu, Pengcheng Laboratory, China; Yongfu Zha, Jie Peng, Xiaodong Wang, National University of Defense Technology, China
MLSP-P4.7: SUSTAINABLE INCENTIVE FOR MODEL TRADING IN DECENTRALIZED AND PERSONALIZED FEDERATED LEARNING VIA DAG-BLOCKCHAIN CONSENSUS
Puhe Hao, Zihan Liu, Nanjing University of Posts and Telecommunications, China; Jinfei Liu, Zhejiang Univeristy, China; Guozi Sun, Nanjing University of Posts and Telecommunications, China
MLSP-P4.8: TOP-1 COMPRESSION SUFFICES FOR FEDERATED UNLEARNING WITH THE HELP OF ADAPTIVE ERROR FEEDBACK
Boxu Xiao, Sun Yat-sen University, China; Sijia Liu, Michigan State University, United States of America; Qing Ling, Sun Yat-sen University, China
MLSP-P4.9: PERSONALIZED FEDERATED LEARNING VIA DECOUPLED VISUAL PROMPTS AND ADAPTIVE CLASSIFIER FUSION
Tianpeng Deng, South China University of Technology, China; Ming Cai, Guangdong Provincial People’s Hospital, China; Zaiyi Liu, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), China; Guoqiang Han, South China University of Technology, China; Chu Han, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), China
MLSP-P4.10: DeMoFL: Efficient and Effective Decentralized Model-Heterogeneous Federated Learning
Yuanchun Guo, Bingyan Liu, Beijing University of Post and Communications, China
Contacts