FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning

• URL: http://arxiv.org/abs/2409.15898v4
• Date: Thu, 10 Oct 2024 07:29:24 GMT
• Title: FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning
• Abstract summary: Federated learning (FL) has emerged as a privacy-preserving method for training machine learning models in a distributed manner on edge devices. As the model's size increases, the frequency of gradient updates on edge devices decreases, leading to suboptimal training outcomes. We propose FedRepOpt, a gradient re- parameterized for FL, to address this issue.
• Score: 17.642826635563946
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Learning (FL) has emerged as a privacy-preserving method for training machine learning models in a distributed manner on edge devices. However, on-device models face inherent computational power and memory limitations, potentially resulting in constrained gradient updates. As the model's size increases, the frequency of gradient updates on edge devices decreases, ultimately leading to suboptimal training outcomes during any particular FL round. This limits the feasibility of deploying advanced and large-scale models on edge devices, hindering the potential for performance enhancements. To address this issue, we propose FedRepOpt, a gradient re-parameterized optimizer for FL. The gradient re-parameterized method allows training a simple local model with a similar performance as a complex model by modifying the optimizer's gradients according to a set of model-specific hyperparameters obtained from the complex models. In this work, we focus on VGG-style and Ghost-style models in the FL environment. Extensive experiments demonstrate that models using FedRepOpt obtain a significant boost in performance of 16.7% and 11.4% compared to the RepGhost-style and RepVGG-style networks, while also demonstrating a faster convergence time of 11.7% and 57.4% compared to their complex structure.

Related papers

• Scaling Reinforcement Learning for Diffusion Models via Velocity Matching [66.34541945134916]
  RewardBench fine-tuning is an important tool for adapting diffusion models to human preferences and task-specific objectives.<n>Unlike autoregressive models, diffusion models do not provide tractable likelihoods for generated samples.<n>We propose reward-based velocity matching (RVM), a simple trajectory-free update that acts directly on the velocity field.
  arXiv  Detail & Related papers  (2026-08-24T17:13:43Z)
• Feasible Learning [78.6167929413604]
  We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample. Our empirical analysis, spanning image classification, age regression, and preference optimization in large language models, demonstrates that models trained via FL can learn from data while displaying improved tail behavior compared to ERM, with only a marginal impact on average performance.
  arXiv  Detail & Related papers  (2025-01-24T20:39:38Z)
• SPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning [18.917283498639442]
  We propose the Step-wise.<n>Dropout for Continual Federated Learning (SPD-CFL) approach.<n>It allows users to specify the target level of performance and then attempts to find the most suitable dropout rate for the given FL model.<n>It achieves a 2.07% higher test AUC while reducing communication overhead by 29.53%.
  arXiv  Detail & Related papers  (2024-05-15T14:50:46Z)
• Straggler-resilient Federated Learning: Tackling Computation Heterogeneity with Layer-wise Partial Model Training in Mobile Edge Network [4.1813760301635705]
  We propose Federated Partial Model Training (FedPMT), where devices with smaller computational capabilities work on partial models and contribute to the global model. As such, all devices in FedPMT prioritize the most crucial parts of the global model. Empirical results show that FedPMT significantly outperforms the existing benchmark FedDrop.
  arXiv  Detail & Related papers  (2023-11-16T16:30:04Z)
• Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR [12.108696564200052]
  We start by training End-to-End Automatic Speech Recognition (ASR) models using Federated Learning (FL) We examine the fundamental considerations that can be pivotal in minimizing the performance gap in terms of word error rate between models trained using FL versus their centralized counterpart.
  arXiv  Detail & Related papers  (2023-09-22T17:23:01Z)
• 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)
• FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout [1.8262547855491458]
  Federated Learning allows machine learning models to train locally on individual mobile devices, synchronizing model updates via a shared server. As a result, straggler devices with lower performance often dictate the overall training time in FL. We introduce Invariant Dropout, a method that extracts a sub-model based on the weight update threshold. We develop an adaptive training framework, Federated Learning using Invariant Dropout.
  arXiv  Detail & Related papers  (2023-07-05T19:53:38Z)
• Re-parameterizing Your Optimizers rather than Architectures [119.08740698936633]
  We propose a novel paradigm of incorporating model-specific prior knowledge into Structurals and using them to train generic (simple) models. As an implementation, we propose a novel methodology to add prior knowledge by modifying the gradients according to a set of model-specific hyper- parameters. For a simple model trained with a Repr, we focus on a VGG-style plain model and showcase that such a simple model trained with a Repr, which is referred to as Rep-VGG, performs on par with the recent well-designed models.
  arXiv  Detail & Related papers  (2022-05-30T16:55:59Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• Towards More Efficient Federated Learning with Better Optimization Objects [1.126965032229697]
  Federated Learning (FL) is a privacy-protected machine learning paradigm that allows model to be trained directly at the edge without uploading data. One of the biggest challenges faced by FL in practical applications is the heterogeneity of edge node data, which will slow down the convergence speed and degrade the performance of the model. We propose to use the aggregation of all models obtained in the past as new constraint target to further improve the performance of such algorithms.
  arXiv  Detail & Related papers  (2021-08-19T09:29:17Z)
• GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training [59.160154997555956]
  We present GradInit, an automated and architecture method for initializing neural networks. It is based on a simple agnostic; the variance of each network layer is adjusted so that a single step of SGD or Adam results in the smallest possible loss value. It also enables training the original Post-LN Transformer for machine translation without learning rate warmup.
  arXiv  Detail & Related papers  (2021-02-16T11:45:35Z)
• Dynamic Model Pruning with Feedback [64.019079257231]
  We propose a novel model compression method that generates a sparse trained model without additional overhead. We evaluate our method on CIFAR-10 and ImageNet, and show that the obtained sparse models can reach the state-of-the-art performance of dense models.
  arXiv  Detail & Related papers  (2020-06-12T15:07:08Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.