paper-with-me

홈 › Papers

Efficient and Private Federated Learning with Partially Trainable Networks

2021-10-06 · Hakim Sidahmed, Zheng Xu, Ankush Garg, Yuan Cao, Mingqing Chen

Federated learning is used for decentralized training of machine learning models on a large number (millions) of edge mobile devices. It is challenging because mobile devices often have limited communication bandwidth and local computation resources. Therefore, improving the efficiency of federated learning is critical for scalability and usability. In this paper, we propose to leverage partially trainable neural networks, which freeze a portion of the model parameters during the entire training process, to reduce the communication cost with little implications on model performance. Through extensive experiments, we empirically show that Federated learning of Partially Trainable neural networks (FedPT) can result in superior communication-accuracy trade-offs, with up to $46\times$ reduction in communication cost, at a small accuracy cost. Our approach also enables faster training, with a smaller memory footprint, and better utility for strong differential privacy guarantees. The proposed FedPT method can be particularly interesting for pushing the limitations of over-parameterization in on-device learning.

📄 PDF Abstract BibTeX arXiv:2110.03450

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FedAUXfdp: Differentially Private One-Shot Federated Distillation

2022-05-30 · Haley Hoech, Roman Rischke, Karsten Müller, Wojciech Samek

Federated learning suffers in the case of non-iid local datasets, i.e., when the distributions of the clients' data are heterogeneous. One promising approach to this challenge is the recently proposed method FedAUX, an a…

Federated Learning

Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning

2025-02-21 · Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak, Lav R. Varshney 외

Low-Rank Adaptation (LoRA) has become ubiquitous for efficiently fine-tuning foundation models. However, federated fine-tuning using LoRA is challenging due to suboptimal updates arising from traditional federated averag…

Arithmetic Reasoning

Personalized Federated Recommender Systems with Private and Partially Federated AutoEncoders

2022-12-17 · Qi Le, Enmao Diao, Xinran Wang, Ali Anwar 외

Recommender Systems (RSs) have become increasingly important in many application domains, such as digital marketing. Conventional RSs often need to collect users' data, centralize them on the server-side, and form a glob…

DecoderFederated LearningMarketingRecommendation Systems

Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity

2023-05-29 · Konstantin Mishchenko, Rustem Islamov, Eduard Gorbunov, Samuel Horváth

We present a partially personalized formulation of Federated Learning (FL) that strikes a balance between the flexibility of personalization and cooperativeness of global training. In our framework, we split the variable…

Federated LearningPersonalized Federated Learning

Implicit Federated In-context Learning For Task-Specific LLM Fine-Tuning

2025-11-10 · Dongcheng Li, Junhan Chen, Aoxiang Zhou, Chunpei Li 외 arxiv

As large language models continue to develop and expand, the extensive public data they rely on faces the risk of depletion. Consequently, leveraging private data within organizations to enhance the performance of large …

Text ClassificationFederated Learning