Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data

• URL: http://arxiv.org/abs/2008.06180v2
• Date: Wed, 20 Jan 2021 08:35:43 GMT
• Title: Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data
• Authors: Sohei Itahara, Takayuki Nishio, Yusuke Koda, Masahiro Morikura and Koji Yamamoto
• Abstract summary: This study develops a federated learning (FL) framework overcoming largely incremental communication costs. We propose a distillation-based semi-supervised FL algorithm that exchanges the outputs of local models among mobile devices. In DS-FL, the communication cost depends only on the output dimensions of the models and does not scale up according to the model size.
• Score: 8.935169114460663
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This study develops a federated learning (FL) framework overcoming largely incremental communication costs due to model sizes in typical frameworks without compromising model performance. To this end, based on the idea of leveraging an unlabeled open dataset, we propose a distillation-based semi-supervised FL (DS-FL) algorithm that exchanges the outputs of local models among mobile devices, instead of model parameter exchange employed by the typical frameworks. In DS-FL, the communication cost depends only on the output dimensions of the models and does not scale up according to the model size. The exchanged model outputs are used to label each sample of the open dataset, which creates an additionally labeled dataset. Based on the new dataset, local models are further trained, and model performance is enhanced owing to the data augmentation effect. We further highlight that in DS-FL, the heterogeneity of the devices' dataset leads to ambiguous of each data sample and lowing of the training convergence. To prevent this, we propose entropy reduction averaging, where the aggregated model outputs are intentionally sharpened. Moreover, extensive experiments show that DS-FL reduces communication costs up to 99% relative to those of the FL benchmark while achieving similar or higher classification accuracy.

Related papers

• FedMAP: Unlocking Potential in Personalized Federated Learning through Bi-Level MAP Optimization [11.040916982022978]
  Federated Learning (FL) enables collaborative training of machine learning models on decentralized data. Data across clients often differs significantly due to class imbalance, feature distribution skew, sample size imbalance, and other phenomena. We propose a novel Bayesian PFL framework using bi-level optimization to tackle the data heterogeneity challenges.
  arXiv  Detail & Related papers  (2024-05-29T11:28:06Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity [26.09617693587105]
  We improve the one-shot sequential federated learning for non-IID data by proposing a local model diversity-enhancing strategy. Our method exhibits superior performance to existing one-shot PFL methods and achieves better accuracy compared with state-of-the-art one-shot SFL methods.
  arXiv  Detail & Related papers  (2024-04-18T12:31:48Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Fake It Till Make It: Federated Learning with Consensus-Oriented Generation [52.82176415223988]
  We propose federated learning with consensus-oriented generation (FedCOG) FedCOG consists of two key components at the client side: complementary data generation and knowledge-distillation-based model training. Experiments on classical and real-world FL datasets show that FedCOG consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-10T18:49:59Z)
• Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networks [72.59891661768177]
  Federated learning (FL) enables distributed learning across edge devices while protecting data privacy. We consider a FL framework with partial model pruning and personalization to overcome these challenges. This framework splits the learning model into a global part with model pruning shared with all devices to learn data representations and a personalized part to be fine-tuned for a specific device.
  arXiv  Detail & Related papers  (2023-09-04T21:10:45Z)
• ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated Data [5.210280120905009]
  "ConDistFL" is a framework to combine Federated Learning (FL) with knowledge distillation. We validate our framework on four distinct partially annotated abdominal CT datasets from the MSD and KiTS19 challenges. Our ablation study suggests that ConDistFL can perform well without frequent aggregation, reducing the communication cost of FL.
  arXiv  Detail & Related papers  (2023-08-08T06:07:49Z)
• Tensor Decomposition based Personalized Federated Learning [12.420951968273574]
  Federated learning (FL) is a new distributed machine learning framework that can achieve reliably collaborative training without collecting users' private data. Due to FL's frequent communication and average aggregation strategy, they experience challenges scaling to statistical diversity data and large-scale models. We propose a personalized FL framework, named Decomposition based Personalized learning (TDPFed), in which we design a novel tensorized local model with tensorized linear layers and convolutional layers to reduce the communication cost.
  arXiv  Detail & Related papers  (2022-08-27T08:09:14Z)
• FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning [87.08902493524556]
  Federated learning(FL) has recently attracted increasing attention from academia and industry. We propose FedDM to build the global training objective from multiple local surrogate functions. In detail, we construct synthetic sets of data on each client to locally match the loss landscape from original data.
  arXiv  Detail & Related papers  (2022-07-20T04:55:18Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.