Robust Model Evaluation over Large-scale Federated Networks

• URL: http://arxiv.org/abs/2410.20250v1
• Date: Sat, 26 Oct 2024 18:45:15 GMT
• Title: Robust Model Evaluation over Large-scale Federated Networks
• Authors: Amir Najafi, Samin Mahdizadeh Sani, Farzan Farnia,
• Abstract summary: We address the challenge of certifying the performance of a machine learning model on an unseen target network. We derive theoretical guarantees for the model's empirical average loss and provide uniform bounds on the risk CDF. Our bounds are computable in time with a number of queries to the $K$ clients, preserving client privacy by querying only the model's loss on private data.
• Score: 8.700087812420687
• License:
• Abstract: In this paper, we address the challenge of certifying the performance of a machine learning model on an unseen target network, using measurements from an available source network. We focus on a scenario where heterogeneous datasets are distributed across a source network of clients, all connected to a central server. Specifically, consider a source network "A" composed of $K$ clients, each holding private data from unique and heterogeneous distributions, which are assumed to be independent samples from a broader meta-distribution $\mu$. Our goal is to provide certified guarantees for the model's performance on a different, unseen target network "B," governed by another meta-distribution $\mu'$, assuming the deviation between $\mu$ and $\mu'$ is bounded by either the Wasserstein distance or an $f$-divergence. We derive theoretical guarantees for the model's empirical average loss and provide uniform bounds on the risk CDF, where the latter correspond to novel and adversarially robust versions of the Glivenko-Cantelli theorem and the Dvoretzky-Kiefer-Wolfowitz (DKW) inequality. Our bounds are computable in polynomial time with a polynomial number of queries to the $K$ clients, preserving client privacy by querying only the model's (potentially adversarial) loss on private data. We also establish non-asymptotic generalization bounds that consistently converge to zero as both $K$ and the minimum client sample size grow. Extensive empirical evaluations validate the robustness and practicality of our bounds across real-world tasks.

Related papers

• A Federated Distributionally Robust Support Vector Machine with Mixture of Wasserstein Balls Ambiguity Set for Distributed Fault Diagnosis [3.662364375995991]
  We study the problem of training a distributionally robust (DR) support vector machine (SVM) in a federated fashion over a network comprised of a central server and $G$ clients without sharing data. We propose two distributed optimization algorithms for training the global FDR-SVM.
  arXiv  Detail & Related papers  (2024-10-04T19:21:45Z)
• Minimal Communication-Cost Statistical Learning [14.453654853392619]
  We propose a joint training and source coding scheme with provable in-expectation guarantees. We show that by imposing a constraint on a suitable Kullback-Leibler divergence between the conditional distribution induced by a compressed learning model $widehatW$ given $W$ and the prior, one guarantees simultaneously small average empirical risk. We also consider a one-shot scenario in which the guarantees on the empirical risk and generalization error are obtained for every encoder's output message.
  arXiv  Detail & Related papers  (2024-06-12T13:22:26Z)
• Empowering Federated Learning with Implicit Gossiping: Mitigating Connection Unreliability Amidst Unknown and Arbitrary Dynamics [23.466997173249034]
  Federated learning is a popular approach for training a machine learning model without disclosing raw data. We show that when the $p_it$'s vary across clients, the most widely adopted federated learning algorithm, Federated Average (FedAvg), experiences significant bias. We propose Federated Postponed Broadcast (FedPBC), a simple variant of FedAvg.
  arXiv  Detail & Related papers  (2024-04-15T18:58:39Z)
• Collaborative non-parametric two-sample testing [55.98760097296213]
  The goal is to identify nodes where the null hypothesis $p_v = q_v$ should be rejected. We propose the non-parametric collaborative two-sample testing (CTST) framework that efficiently leverages the graph structure. Our methodology integrates elements from f-divergence estimation, Kernel Methods, and Multitask Learning.
  arXiv  Detail & Related papers  (2024-02-08T14:43:56Z)
• FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients [50.13097183691517]
  In real-world federated scenarios, there often exist a multitude of heterogeneous clients with varying computation and communication resources. We propose a novel federated tuning algorithm, FedRA. In each communication round, FedRA randomly generates an allocation matrix. It reorganizes a small number of layers from the original model based on the allocation matrix and fine-tunes using adapters.
  arXiv  Detail & Related papers  (2023-11-19T04:43:16Z)
• Delta-AI: Local objectives for amortized inference in sparse graphical models [64.5938437823851]
  We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs) Our approach is based on the observation that when the sampling of variables in a PGM is seen as a sequence of actions taken by an agent, sparsity of the PGM enables local credit assignment in the agent's policy learning objective. We illustrate $Delta$-AI's effectiveness for sampling from synthetic PGMs and training latent variable models with sparse factor structure.
  arXiv  Detail & Related papers  (2023-10-03T20:37:03Z)
• The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning [34.630300910399036]
  We characterize the fundamental communication cost required to obtain the best accuracy under $varepsilon$ central DP. Our results show that $tildeOleft( min(n2varepsilon2, d) right)$ bits per client are both sufficient and necessary. This provides a significant improvement relative to state-of-the-art SecAgg distributed DP schemes.
  arXiv  Detail & Related papers  (2022-03-07T22:56:09Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Self-Ensembling GAN for Cross-Domain Semantic Segmentation [107.27377745720243]
  This paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation. In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN. Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model.
  arXiv  Detail & Related papers  (2021-12-15T09:50:25Z)
• Distributed Sparse Feature Selection in Communication-Restricted Networks [6.9257380648471765]
  We propose and theoretically analyze a new distributed scheme for sparse linear regression and feature selection. In order to infer the causal dimensions from the whole dataset, we propose a simple, yet effective method for information sharing in the network.
  arXiv  Detail & Related papers  (2021-11-02T05:02:24Z)
• Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model [50.38446482252857]
  This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator) We first consider $gamma$-discounted infinite-horizon Markov decision processes (MDPs) with state space $mathcalS$ and action space $mathcalA$. We prove that a plain model-based planning algorithm suffices to achieve minimax-optimal sample complexity given any target accuracy level.
  arXiv  Detail & Related papers  (2020-05-26T17:53:18Z)

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.