Federated Covariate Shift Adaptation for Missing Target Output Values
- URL: http://arxiv.org/abs/2302.14427v1
- Date: Tue, 28 Feb 2023 09:15:41 GMT
- Title: Federated Covariate Shift Adaptation for Missing Target Output Values
- Authors: Yaqian Xu, Wenquan Cui, Jianjun Xu, Haoyang Cheng
- Abstract summary: In this paper, we extend the most recent multi-source co-shift algorithm to the framework of federated learning.
We construct a weighted model for the target task and propose the federated co-shift adaptation algorithm which works preferably in our setting.
- Score: 1.1374487003189466
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The most recent multi-source covariate shift algorithm is an efficient
hyperparameter optimization algorithm for missing target output. In this paper,
we extend this algorithm to the framework of federated learning. For data
islands in federated learning and covariate shift adaptation, we propose the
federated domain adaptation estimate of the target risk which is asymptotically
unbiased with a desirable asymptotic variance property. We construct a weighted
model for the target task and propose the federated covariate shift adaptation
algorithm which works preferably in our setting. The efficacy of our method is
justified both theoretically and empirically.
Related papers
- Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.
To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.
Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
arXiv Detail & Related papers (2024-05-26T05:38:50Z) - Federated Conditional Stochastic Optimization [110.513884892319]
Conditional optimization has found in a wide range of machine learning tasks, such as in-variant learning tasks, AUPRC, andAML.
This paper proposes algorithms for distributed federated learning.
arXiv Detail & Related papers (2023-10-04T01:47:37Z) - Adaptive Consensus: A network pruning approach for decentralized
optimization [0.5432724320036953]
We consider network-based decentralized optimization problems, where each node in the network possesses a local function.
The objective is to collectively attain a consensus solution that minimizes the sum of all the local functions.
We propose an adaptive randomized communication-efficient algorithmic framework that reduces the volume of communication.
arXiv Detail & Related papers (2023-09-06T00:28:10Z) - Stochastic Unrolled Federated Learning [85.6993263983062]
We introduce UnRolled Federated learning (SURF), a method that expands algorithm unrolling to federated learning.
Our proposed method tackles two challenges of this expansion, namely the need to feed whole datasets to the unrolleds and the decentralized nature of federated learning.
arXiv Detail & Related papers (2023-05-24T17:26:22Z) - Faster Adaptive Federated Learning [84.38913517122619]
Federated learning has attracted increasing attention with the emergence of distributed data.
In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on momentum-based variance reduced technique in cross-silo FL.
arXiv Detail & Related papers (2022-12-02T05:07:50Z) - Variance-Reduced Heterogeneous Federated Learning via Stratified Client
Selection [31.401919362978017]
We propose a novel stratified client selection scheme to reduce the variance for the pursuit of better convergence and higher accuracy.
We present an optimized sample size allocation scheme by considering the diversity of stratum's variability.
Experimental results confirm that our approach not only allows for better performance relative to state-of-the-art methods but also is compatible with prevalent FL algorithms.
arXiv Detail & Related papers (2022-01-15T05:41:36Z) - Distributionally Robust Federated Averaging [19.875176871167966]
We present communication efficient distributed algorithms for robust learning periodic averaging with adaptive sampling.
We give corroborating experimental evidence for our theoretical results in federated learning settings.
arXiv Detail & Related papers (2021-02-25T03:32:09Z) - Tackling the Objective Inconsistency Problem in Heterogeneous Federated
Optimization [93.78811018928583]
This paper provides a framework to analyze the convergence of federated heterogeneous optimization algorithms.
We propose FedNova, a normalized averaging method that eliminates objective inconsistency while preserving fast error convergence.
arXiv Detail & Related papers (2020-07-15T05:01:23Z) - Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization [71.03797261151605]
Adaptivity is an important yet under-studied property in modern optimization theory.
Our algorithm is proved to achieve the best-available convergence for non-PL objectives simultaneously while outperforming existing algorithms for PL objectives.
arXiv Detail & Related papers (2020-02-13T05:42:27Z)
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.