Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learning

• URL: http://arxiv.org/abs/2303.06155v1
• Date: Fri, 10 Mar 2023 15:14:24 GMT
• Title: Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learning
• Authors: Xiucheng Wang, Nan Cheng, Longfei Ma, Ruijin Sun, Rong Chai, Ning Lu
• Abstract summary: knowledge distillation (KD) driven training framework for federated learning is proposed. Each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset. Digital twin (DT) is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources.
• Score: 14.003355837801879
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, to deal with the heterogeneity in federated learning (FL) systems, a knowledge distillation (KD) driven training framework for FL is proposed, where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset. To overcome the challenge of train the big teacher model in resource limited user devices, the digital twin (DT) is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources. Then, during model distillation, each user can update the parameters of its model at either the physical entity or the digital agent. The joint problem of model selection and training offloading and resource allocation for users is formulated as a mixed integer programming (MIP) problem. To solve the problem, Q-learning and optimization are jointly used, where Q-learning selects models for users and determines whether to train locally or on the server, and optimization is used to allocate resources for users based on the output of Q-learning. Simulation results show the proposed DT-assisted KD framework and joint optimization method can significantly improve the average accuracy of users while reducing the total delay.

Related papers

• Online Client Scheduling and Resource Allocation for Efficient Federated Edge Learning [9.451084740123198]
  Federated learning (FL) enables edge devices to collaboratively train a machine learning model without sharing their raw data. However, deploying FL over mobile edge networks with constrained resources such as power, bandwidth, and suffers from high training latency and low model accuracy. This paper investigates the optimal client scheduling and resource allocation for FL over mobile edge networks under resource constraints and uncertainty.
  arXiv  Detail & Related papers  (2024-09-29T01:56:45Z)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• 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)
• Speed Up Federated Learning in Heterogeneous Environment: A Dynamic Tiering Approach [5.504000607257414]
  Federated learning (FL) enables collaboratively training a model while keeping the training data decentralized and private. One significant impediment to training a model using FL, especially large models, is the resource constraints of devices with heterogeneous computation and communication capacities as well as varying task sizes. We propose the Dynamic Tiering-based Federated Learning (DTFL) system where slower clients dynamically offload part of the model to the server to alleviate resource constraints and speed up training.
  arXiv  Detail & Related papers  (2023-12-09T19:09:19Z)
• 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)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Training Deep Surrogate Models with Large Scale Online Learning [48.7576911714538]
  Deep learning algorithms have emerged as a viable alternative for obtaining fast solutions for PDEs. Models are usually trained on synthetic data generated by solvers, stored on disk and read back for training. It proposes an open source online training framework for deep surrogate models.
  arXiv  Detail & Related papers  (2023-06-28T12:02:27Z)
• Time-sensitive Learning for Heterogeneous Federated Edge Intelligence [52.83633954857744]
  We investigate real-time machine learning in a federated edge intelligence (FEI) system. FEI systems exhibit heterogenous communication and computational resource distribution. We propose a time-sensitive federated learning (TS-FL) framework to minimize the overall run-time for collaboratively training a shared ML model.
  arXiv  Detail & Related papers  (2023-01-26T08:13:22Z)
• Efficient Federated Learning for AIoT Applications Using Knowledge Distillation [2.5892786553124085]
  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.
  arXiv  Detail & Related papers  (2021-11-29T06:40:42Z)
• Communication-Efficient Hierarchical Federated Learning for IoT Heterogeneous Systems with Imbalanced Data [42.26599494940002]
  Federated learning (FL) is a distributed learning methodology that allows multiple nodes to cooperatively train a deep learning model. This paper studies the potential of hierarchical FL in IoT heterogeneous systems. It proposes an optimized solution for user assignment and resource allocation on multiple edge nodes.
  arXiv  Detail & Related papers  (2021-07-14T08:32:39Z)

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.