Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization
- URL: http://arxiv.org/abs/2405.17932v1
- Date: Tue, 28 May 2024 07:56:49 GMT
- Title: Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization
- Authors: Xiumei Deng, Jun Li, Kang Wei, Long Shi, Zeihui Xiong, Ming Ding, Wen Chen, Shi Jin, H. Vincent Poor,
- Abstract summary: Federated Adam (FedAdam) algorithms suffer from a threefold increase in uplink communication overhead.
We propose a novel sparse FedAdam algorithm called FedAdam-SSM, wherein distributed devices sparsify the updates local model parameters and moment estimates.
By minimizing the divergence bound between the model trained by FedAdam-SSM and centralized Adam, we optimize the SSM to mitigate the learning performance degradation caused by sparsification error.
- Score: 65.85963235502322
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Adaptive moment estimation (Adam), as a Stochastic Gradient Descent (SGD) variant, has gained widespread popularity in federated learning (FL) due to its fast convergence. However, federated Adam (FedAdam) algorithms suffer from a threefold increase in uplink communication overhead compared to federated SGD (FedSGD) algorithms, which arises from the necessity to transmit both local model updates and first and second moment estimates from distributed devices to the centralized server for aggregation. Driven by this issue, we propose a novel sparse FedAdam algorithm called FedAdam-SSM, wherein distributed devices sparsify the updates of local model parameters and moment estimates and subsequently upload the sparse representations to the centralized server. To further reduce the communication overhead, the updates of local model parameters and moment estimates incorporate a shared sparse mask (SSM) into the sparsification process, eliminating the need for three separate sparse masks. Theoretically, we develop an upper bound on the divergence between the local model trained by FedAdam-SSM and the desired model trained by centralized Adam, which is related to sparsification error and imbalanced data distribution. By minimizing the divergence bound between the model trained by FedAdam-SSM and centralized Adam, we optimize the SSM to mitigate the learning performance degradation caused by sparsification error. Additionally, we provide convergence bounds for FedAdam-SSM in both convex and non-convex objective function settings, and investigate the impact of local epoch, learning rate and sparsification ratio on the convergence rate of FedAdam-SSM. Experimental results show that FedAdam-SSM outperforms baselines in terms of convergence rate (over 1.1$\times$ faster than the sparse FedAdam baselines) and test accuracy (over 14.5\% ahead of the quantized FedAdam baselines).
Related papers
- Vanishing Variance Problem in Fully Decentralized Neural-Network Systems [0.8212195887472242]
Federated learning and gossip learning are emerging methodologies designed to mitigate data privacy concerns.
Our research introduces a variance-corrected model averaging algorithm.
Our simulation results demonstrate that our approach enables gossip learning to achieve convergence efficiency comparable to that of federated learning.
arXiv Detail & Related papers (2024-04-06T12:49:20Z) - DASA: Delay-Adaptive Multi-Agent Stochastic Approximation [64.32538247395627]
We consider a setting in which $N$ agents aim to speedup a common Approximation problem by acting in parallel and communicating with a central server.
To mitigate the effect of delays and stragglers, we propose textttDASA, a Delay-Adaptive algorithm for multi-agent Approximation.
arXiv Detail & Related papers (2024-03-25T22:49:56Z) - DFedADMM: Dual Constraints Controlled Model Inconsistency for
Decentralized Federated Learning [52.83811558753284]
Decentralized learning (DFL) discards the central server and establishes a decentralized communication network.
Existing DFL methods still suffer from two major challenges: local inconsistency and local overfitting.
arXiv Detail & Related papers (2023-08-16T11:22:36Z) - FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated
Learning with Bayesian Inference-Based Adaptive Dropout [14.72932631655587]
Federated Learning (FL) emerges as a distributed machine learning paradigm without end-user data transmission.
FedBIAD provides 2x uplink reduction with an accuracy increase of up to 2.41% even on non-Independent and Identically Distributed (non-IID) data.
arXiv Detail & Related papers (2023-07-14T05:51:04Z) - Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated
Learning Framework [82.36466358313025]
We propose a primal-dual FL algorithm, termed FedVRA, that allows one to adaptively control the variance-reduction level and biasness of the global model.
Experiments based on (semi-supervised) image classification tasks demonstrate superiority of FedVRA over the existing schemes.
arXiv Detail & Related papers (2022-12-03T03:27:51Z) - Towards Practical Adam: Non-Convexity, Convergence Theory, and
Mini-Batch Acceleration [12.744658958445024]
Adam is one of the most influential adaptive algorithms for training deep neural networks.
Existing approaches, such as decreasing an adaptive learning rate, adopting a big batch size, have tried to promote Adam-type algorithms to converge.
We introduce an alternative easy-to-check sufficient condition, which merely depends on the parameters of historical base learning rate.
arXiv Detail & Related papers (2021-01-14T06:42:29Z) - Coded Stochastic ADMM for Decentralized Consensus Optimization with Edge
Computing [113.52575069030192]
Big data, including applications with high security requirements, are often collected and stored on multiple heterogeneous devices, such as mobile devices, drones and vehicles.
Due to the limitations of communication costs and security requirements, it is of paramount importance to extract information in a decentralized manner instead of aggregating data to a fusion center.
We consider the problem of learning model parameters in a multi-agent system with data locally processed via distributed edge nodes.
A class of mini-batch alternating direction method of multipliers (ADMM) algorithms is explored to develop the distributed learning model.
arXiv Detail & Related papers (2020-10-02T10:41:59Z) - A(DP)$^2$SGD: Asynchronous Decentralized Parallel Stochastic Gradient
Descent with Differential Privacy [15.038697541988746]
A popular distributed learning strategy is federated learning, where there is a central server storing the global model and a set of local computing nodes updating the model parameters with their corresponding data.
In this paper, we present a differentially private version of asynchronous decentralized parallel SGD framework, or A(DP)$2$SGD for short, which maintains communication efficiency of ADPSGD and prevents the inference from malicious participants.
arXiv Detail & Related papers (2020-08-21T00:56:22Z) - A Unified Theory of Decentralized SGD with Changing Topology and Local
Updates [70.9701218475002]
We introduce a unified convergence analysis of decentralized communication methods.
We derive universal convergence rates for several applications.
Our proofs rely on weak assumptions.
arXiv Detail & Related papers (2020-03-23T17:49:15Z)
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.