Efficient Federated Learning for AIoT Applications Using Knowledge Distillation

• URL: http://arxiv.org/abs/2111.14347v1
• Date: Mon, 29 Nov 2021 06:40:42 GMT
• Title: Efficient Federated Learning for AIoT Applications Using Knowledge Distillation
• Authors: Tian Liua, Jun Xiaa, Xian Weia, Ting Wanga, Xin Fub, Mingsong Chen
• Abstract summary: Federated Learning (FL) trains a central model with decentralized data without compromising user privacy. Traditional FL suffers from model inaccuracy since it trains local models using hard labels of data. This paper presents a novel Distillation-based Federated Learning architecture that enables efficient and accurate FL for AIoT applications.
• Score: 2.5892786553124085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As a promising distributed machine learning paradigm, Federated Learning (FL) trains a central model with decentralized data without compromising user privacy, which has made it widely used by Artificial Intelligence Internet of Things (AIoT) applications. However, the traditional FL suffers from model inaccuracy since it trains local models using hard labels of data and ignores useful information of incorrect predictions with small probabilities. Although various solutions try to tackle the bottleneck of the traditional FL, most of them introduce significant communication and memory overhead, making the deployment of large-scale AIoT devices a great challenge. To address the above problem, this paper presents a novel Distillation-based Federated Learning (DFL) architecture that enables efficient and accurate FL for AIoT applications. Inspired by Knowledge Distillation (KD) that can increase the model accuracy, our approach adds the soft targets used by KD to the FL model training, which occupies negligible network resources. The soft targets are generated by local sample predictions of each AIoT device after each round of local training and used for the next round of model training. During the local training of DFL, both soft targets and hard labels are used as approximation objectives of model predictions to improve model accuracy by supplementing the knowledge of soft targets. To further improve the performance of our DFL model, we design a dynamic adjustment strategy for tuning the ratio of two loss functions used in KD, which can maximize the use of both soft targets and hard labels. Comprehensive experimental results on well-known benchmarks show that our approach can significantly improve the model accuracy of FL with both Independent and Identically Distributed (IID) and non-IID data.

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)
• Towards Robust Federated Learning via Logits Calibration on Non-IID Data [49.286558007937856]
  Federated learning (FL) is a privacy-preserving distributed management framework based on collaborative model training of distributed devices in edge networks. Recent studies have shown that FL is vulnerable to adversarial examples, leading to a significant drop in its performance. In this work, we adopt the adversarial training (AT) framework to improve the robustness of FL models against adversarial example (AE) attacks.
  arXiv  Detail & Related papers  (2024-03-05T09:18:29Z)
• 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)
• 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)
• Knowledge Distillation for Federated Learning: a Practical Guide [8.2791533759453]
  Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. The most used algorithms for FL are parameter-averaging based schemes (e.g., Federated Averaging) that, however, have well known limits. We provide a review of KD-based algorithms tailored for specific FL issues.
  arXiv  Detail & Related papers  (2022-11-09T08:31:23Z)
• Online Data Selection for Federated Learning with Limited Storage [53.46789303416799]
  Federated Learning (FL) has been proposed to achieve distributed machine learning among networked devices. The impact of on-device storage on the performance of FL is still not explored. In this work, we take the first step to consider the online data selection for FL with limited on-device storage.
  arXiv  Detail & Related papers  (2022-09-01T03:27:33Z)
• 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)
• On the Importance and Applicability of Pre-Training for Federated Learning [28.238484580662785]
  We conduct a systematic study to explore pre-training for federated learning. We find that pre-training can improve FL, but also close its accuracy gap to the counterpart centralized learning. We conclude our paper with an attempt to understand the effect of pre-training on FL.
  arXiv  Detail & Related papers  (2022-06-23T06:02:33Z)
• 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)
• FedCAT: Towards Accurate Federated Learning via Device Concatenation [4.416919766772866]
  Federated Learning (FL) enables all the involved devices to train a global model collaboratively without exposing their local data privacy. For non-IID scenarios, the classification accuracy of FL models decreases drastically due to the weight divergence caused by data heterogeneity. We introduce a novel FL approach named Fed-Cat that can achieve high model accuracy based on our proposed device selection strategy and device concatenation-based local training method.
  arXiv  Detail & Related papers  (2022-02-23T10:08:43Z)
• DearFSAC: An Approach to Optimizing Unreliable Federated Learning via Deep Reinforcement Learning [3.516494777812123]
  We propose the DEfect-AwaRe federated soft actor-critic (DearFSAC) to dynamically assign weights to local models to improve the robustness of federated learning. DearFSAC outperforms three existing approaches on four datasets for both independent and identically distributed (IID) and non-IID settings.
  arXiv  Detail & Related papers  (2022-01-30T01:47:43Z)

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.