Global Knowledge Distillation in Federated Learning

• URL: http://arxiv.org/abs/2107.00051v1
• Date: Wed, 30 Jun 2021 18:14:24 GMT
• Title: Global Knowledge Distillation in Federated Learning
• Authors: Wanning Pan, Lichao Sun
• Abstract summary: We propose a novel global knowledge distillation method, named FedGKD, which learns the knowledge from past global models to tackle down the local bias training problem. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on various CV datasets (CIFAR-10/100) and settings (non-i.i.d data)
• Score: 3.7311680121118345
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge distillation has caught a lot of attention in Federated Learning (FL) recently. It has the advantage for FL to train on heterogeneous clients which have different data size and data structure. However, data samples across all devices are usually not independent and identically distributed (non-i.i.d), posing additional challenges to the convergence and speed of federated learning. As FL randomly asks the clients to join the training process and each client only learns from local non-i.i.d data, which makes learning processing even slower. In order to solve this problem, an intuitive idea is using the global model to guide local training. In this paper, we propose a novel global knowledge distillation method, named FedGKD, which learns the knowledge from past global models to tackle down the local bias training problem. By learning from global knowledge and consistent with current local models, FedGKD learns a global knowledge model in FL. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on various CV datasets (CIFAR-10/100) and settings (non-i.i.d data). The evaluation results show that FedGKD outperforms previous state-of-the-art methods.

Related papers

• Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
  Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. We find that the difference in logits between the local and global models increases as the model is continuously updated. We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
  arXiv  Detail & Related papers  (2023-08-20T04:41:01Z)
• Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning [14.063276595895049]
  Federated Learning (FL) is a paradigm to train a global machine learning model across distributed clients without sharing raw data. We propose FedLU, a novel FL framework for heterogeneous KG embedding learning and unlearning. We show that FedLU achieves superior results in both link prediction and knowledge forgetting.
  arXiv  Detail & Related papers  (2023-02-04T02:44:48Z)
• The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation [17.570719572024608]
  FedHKD (Federated Hyper-Knowledge Distillation) is a novel FL algorithm in which clients rely on knowledge distillation to train local models. Unlike other KD-based pFL methods, FedHKD does not rely on a public dataset nor it deploys a generative model at the server. We conduct extensive experiments on visual datasets in a variety of scenarios, demonstrating that FedHKD provides significant improvement in both personalized as well as global model performance.
  arXiv  Detail & Related papers  (2023-01-21T16:20:57Z)
• When Do Curricula Work in Federated Learning? [56.88941905240137]
  We find that curriculum learning largely alleviates non-IIDness. The more disparate the data distributions across clients the more they benefit from learning. We propose a novel client selection technique that benefits from the real-world disparity in the clients.
  arXiv  Detail & Related papers  (2022-12-24T11:02:35Z)
• Knowledge-Aware Federated Active Learning with Non-IID Data [75.98707107158175]
  We propose a federated active learning paradigm to efficiently learn a global model with limited annotation budget. The main challenge faced by federated active learning is the mismatch between the active sampling goal of the global model on the server and that of the local clients. We propose Knowledge-Aware Federated Active Learning (KAFAL), which consists of Knowledge-Specialized Active Sampling (KSAS) and Knowledge-Compensatory Federated Update (KCFU)
  arXiv  Detail & Related papers  (2022-11-24T13:08:43Z)
• Federated Learning and Meta Learning: Approaches, Applications, and Directions [94.68423258028285]
  In this tutorial, we present a comprehensive review of FL, meta learning, and federated meta learning (FedMeta) Unlike other tutorial papers, our objective is to explore how FL, meta learning, and FedMeta methodologies can be designed, optimized, and evolved, and their applications over wireless networks.
  arXiv  Detail & Related papers  (2022-10-24T10:59:29Z)
• Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and Fusion [20.150635780778384]
  Federated learning (FL) supports distributed training of a global machine learning model across multiple devices with the help of a central server. To address the issue, we design Federated learning with global-local Knowledge Fusion scheme. Key idea in FedKF is to let the server return the global knowledge to be fused with the local knowledge in each training round.
  arXiv  Detail & Related papers  (2022-07-23T07:20:22Z)
• 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)
• Acceleration of Federated Learning with Alleviated Forgetting in Local Training [61.231021417674235]
  Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy. We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage. Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
  arXiv  Detail & Related papers  (2022-03-05T02:31:32Z)
• Preservation of the Global Knowledge by Not-True Self Knowledge Distillation in Federated Learning [8.474470736998136]
  In Federated Learning (FL), a strong global model is collaboratively learned by aggregating the clients' locally trained models. We observe that fitting on biased local distribution shifts the feature on global distribution and results in forgetting of global knowledge. We propose a simple yet effective framework Federated Local Self-Distillation (FedLSD), which utilizes the global knowledge on locally available data.
  arXiv  Detail & Related papers  (2021-06-06T11:51:47Z)
• Data-Free Knowledge Distillation for Heterogeneous Federated Learning [31.364314540525218]
  Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users. We propose a data-free knowledge distillation approach to address heterogeneous FL, where the server learns a lightweight generator to ensemble user information in a data-free manner.
  arXiv  Detail & Related papers  (2021-05-20T22:30:45Z)

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.