TY - GEN
T1 - FedMCP
T2 - 30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024
AU - Zhao, Qianyi
AU - Qu, Chen
AU - Chen, Cen
AU - Fan, Mingyuan
AU - Wang, Yanhao
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - With increasing concerns and regulations on data privacy, fine-tuning pretrained language models (PLMs) in federated learning (FL) has become a common paradigm for NLP tasks. Despite being extensively studied, the existing methods for this problem still face two primary challenges. First, the huge number of parameters in large-scale PLMs leads to excessive communication and computational overhead. Second, the heterogeneity of data and tasks across clients poses a significant obstacle to achieving the desired fine-tuning performance. To address the above problems, we propose FedMCP, a novel parameter-efficient fine-tuning method with model-contrastive personalization for FL. Specifically, FedMCP adds two lightweight adapter modules, i.e., the global adapter and the private adapter, to the frozen PLMs within clients. In a communication round, each client sends only the global adapter to the server for federated aggregation. Furthermore, FedMCP introduces a model-contrastive regularization term between the two adapters. This, on the one hand, encourages the global adapter to assimilate universal knowledge and, on the other hand, the private adapter to capture client-specific knowledge. By leveraging both adapters, FedMCP can effectively provide fine-tuned personalized models tailored to individual clients. Extensive experiments on highly heterogeneous cross-task, cross-silo datasets show that FedMCP achieves substantial performance improvements over state-of-the-art FL fine-tuning approaches for PLMs.
AB - With increasing concerns and regulations on data privacy, fine-tuning pretrained language models (PLMs) in federated learning (FL) has become a common paradigm for NLP tasks. Despite being extensively studied, the existing methods for this problem still face two primary challenges. First, the huge number of parameters in large-scale PLMs leads to excessive communication and computational overhead. Second, the heterogeneity of data and tasks across clients poses a significant obstacle to achieving the desired fine-tuning performance. To address the above problems, we propose FedMCP, a novel parameter-efficient fine-tuning method with model-contrastive personalization for FL. Specifically, FedMCP adds two lightweight adapter modules, i.e., the global adapter and the private adapter, to the frozen PLMs within clients. In a communication round, each client sends only the global adapter to the server for federated aggregation. Furthermore, FedMCP introduces a model-contrastive regularization term between the two adapters. This, on the one hand, encourages the global adapter to assimilate universal knowledge and, on the other hand, the private adapter to capture client-specific knowledge. By leveraging both adapters, FedMCP can effectively provide fine-tuned personalized models tailored to individual clients. Extensive experiments on highly heterogeneous cross-task, cross-silo datasets show that FedMCP achieves substantial performance improvements over state-of-the-art FL fine-tuning approaches for PLMs.
KW - Parameter-Efficient Fine-Tuning
KW - Personalized Federated Learning
KW - Pretrained Language Models
UR - https://www.scopus.com/pages/publications/85212498119
U2 - 10.1109/ICPADS63350.2024.00040
DO - 10.1109/ICPADS63350.2024.00040
M3 - 会议稿件
AN - SCOPUS:85212498119
T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS
SP - 246
EP - 253
BT - Proceedings - 2024 IEEE 30th International Conference on Parallel and Distributed Systems, ICPADS 2024
PB - IEEE Computer Society
Y2 - 10 October 2024 through 14 October 2024
ER -