Federated Learning for Discrete Optimal Transport with Large Population under Incomplete Information

• URL: http://arxiv.org/abs/2411.07841v1
• Date: Tue, 12 Nov 2024 14:46:31 GMT
• Title: Federated Learning for Discrete Optimal Transport with Large Population under Incomplete Information
• Authors: Navpreet Kaur, Juntao Chen, Yingdong Lu,
• Abstract summary: We introduce a discrete optimal transport framework to handle large-scale, heterogeneous target populations. We address two scenarios: one where the type distribution of targets is known, and one where it is unknown. In the case of unknown distribution, we develop a federated learning-based approach that enables efficient computation of the optimal transport scheme.
• Score: 7.004936173632888
• License:
• Abstract: Optimal transport is a powerful framework for the efficient allocation of resources between sources and targets. However, traditional models often struggle to scale effectively in the presence of large and heterogeneous populations. In this work, we introduce a discrete optimal transport framework designed to handle large-scale, heterogeneous target populations, characterized by type distributions. We address two scenarios: one where the type distribution of targets is known, and one where it is unknown. For the known distribution, we propose a fully distributed algorithm to achieve optimal resource allocation. In the case of unknown distribution, we develop a federated learning-based approach that enables efficient computation of the optimal transport scheme while preserving privacy. Case studies are provided to evaluate the performance of our learning algorithm.

Related papers

• Estimating Barycenters of Distributions with Neural Optimal Transport [93.28746685008093]
  We propose a new scalable approach for solving the Wasserstein barycenter problem. Our methodology is based on the recent Neural OT solver. We also establish theoretical error bounds for our proposed approach.
  arXiv  Detail & Related papers  (2024-02-06T09:17:07Z)
• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• Distributionally Robust Machine Learning with Multi-source Data [6.383451076043423]
  We introduce a group distributionally robust prediction model to optimize an adversarial reward about explained variance with respect to a class of target distributions. Compared to classical empirical risk minimization, the proposed robust prediction model improves the prediction accuracy for target populations with distribution shifts. We demonstrate the performance of our proposed group distributionally robust method on simulated and real data with random forests and neural networks as base-learning algorithms.
  arXiv  Detail & Related papers  (2023-09-05T13:19:40Z)
• Scaff-PD: Communication Efficient Fair and Robust Federated Learning [92.61502701658732]
  Scaff-PD is a fast and communication-efficient algorithm for distributionally robust federated learning. Our results suggest that Scaff-PD is a promising approach for federated learning in resource-constrained and heterogeneous settings.
  arXiv  Detail & Related papers  (2023-07-25T10:04:33Z)
• Scalable Optimal Margin Distribution Machine [50.281535710689795]
  Optimal margin Distribution Machine (ODM) is a newly proposed statistical learning framework rooting in the novel margin theory. This paper proposes a scalable ODM, which can achieve nearly ten times speedup compared to the original ODM training method.
  arXiv  Detail & Related papers  (2023-05-08T16:34:04Z)
• An Optimal Transport Approach to Personalized Federated Learning [41.27887358989414]
  Federated learning aims to train a model using the local data of many distributed clients. A key challenge in federated learning is that the data samples across the clients may not be identically distributed. We propose a novel personalized Federated Learning scheme based on Optimal Transport (FedOT)
  arXiv  Detail & Related papers  (2022-06-06T10:05:49Z)
• KL Guided Domain Adaptation [88.19298405363452]
  Domain adaptation is an important problem and often needed for real-world applications. A common approach in the domain adaptation literature is to learn a representation of the input that has the same distributions over the source and the target domain. We show that with a probabilistic representation network, the KL term can be estimated efficiently via minibatch samples.
  arXiv  Detail & Related papers  (2021-06-14T22:24:23Z)
• Optimal transport framework for efficient prototype selection [21.620708125860066]
  We develop an optimal transport (OT) based framework to select informative examples that best represent a given target dataset. We show that our objective function enjoys a key property of submodularity and propose a parallelizable greedy method that is both computationally fast and possess deterministic approximation guarantees.
  arXiv  Detail & Related papers  (2021-03-18T10:50:14Z)
• Open Set Domain Adaptation using Optimal Transport [8.076841611508486]
  We present a 2-step optimal transport approach that performs a mapping from a source distribution to a target distribution. The first step aims at rejecting the samples issued from these new classes using an optimal transport plan. The second step solves the target (class ratio) shift still as an optimal transport problem.
  arXiv  Detail & Related papers  (2020-10-02T15:20:05Z)
• Resource Allocation via Model-Free Deep Learning in Free Space Optical Communications [119.81868223344173]
  The paper investigates the general problem of resource allocation for mitigating channel fading effects in Free Space Optical (FSO) communications. Under this framework, we propose two algorithms that solve FSO resource allocation problems.
  arXiv  Detail & Related papers  (2020-07-27T17:38:51Z)
• Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport [35.37752209765114]
  We propose a new approach to domain adaptation on unlabeled target datasets. We exploit the diversity of source distributions by tuning their weights to the target task at hand. Our method, named Weighted Joint Distribution Optimal Transport (WJDOT), aims at finding simultaneously an Optimal Transport-based alignment between the source and target distributions.
  arXiv  Detail & Related papers  (2020-06-23T12:33:30Z)

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.