Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning

• URL: http://arxiv.org/abs/2608.07157v1
• Date: Fri, 07 Aug 2026 12:26:03 GMT
• Title: Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning
• Abstract summary: Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone.<n>We ask whether that step is possible, using HAS-FL, an adaptive capacity-allocation framework, as a test case.
• Score: 5.586191108738563
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone. A natural next step, allocating capacity by each client's data heterogeneity as estimated from the updates the server already observes, has been repeatedly suggested. We ask whether that step is possible, using HAS-FL, an adaptive capacity-allocation framework, as a test case. Our findings are threefold. First, validated against ground-truth label-distribution divergence on reproducible partitions, update-divergence estimates of client heterogeneity are dominated by capacity rather than data: across two corrected estimators, multiple datasets, and all seeds, the estimates correlate strongly and negatively with device capacity, and no data signal remains once capacity is controlled for. This previously undocumented confound affects any method estimating client statistics from sub-model updates. Second, adaptive allocation has a hidden failure mode: when every client is capped below full width, the uncovered parameters stay at random initialization and progressively corrupt the global model. A simple coverage guarantee removes the failure and explains why uniform allocation collapses. Third, a matched-budget control settles what adaptivity contributes: random allocation to the same average budget performs no differently on both image benchmarks, and on the naturally partitioned text benchmark the adaptive policy is the weakest of the three strategies while consuming the most capacity. Sub-model training remains valuable because it admits constrained clients at quadratically reduced cost, but what protects accuracy is parameter coverage rather than allocation intelligence. Its apparent benefits come from capacity budgeting and coverage, and future designs need heterogeneity signals separable from capacity effects.

Related papers

• How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings? [58.740078141879984]
  Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on.<n>Recent work in causality-based domain generalization has shown how shared causal structure can induce invariant predictors.<n>In this paper, we study when full or partial causal knowledge can provably improve supervised domain adaptation.
  arXiv  Detail & Related papers  (2026-06-10T21:07:49Z)
• HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning [6.169964580735435]
  Edge services increasingly use federated learning to personalize on-device models while keeping sensitive data local.<n>In practice, deployments must handle in both client resources and local data distributions.<n>This paper proposes Heterogeneity-Aware Subnet Allocation (HASA), a train-only rule that assigns widths based on client heterogeneity scores.
  arXiv  Detail & Related papers  (2026-05-30T11:21:48Z)
• Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning [1.4610038284393168]
  Federated learning on edge devices must cope with non-IID client data and tight memory budgets.<n>We propose textbfQ-LocalAdam, which applies distribution-aware 8-bit quantization block-wise linear encoding for momentum and log-space encoding for variance.
  arXiv  Detail & Related papers  (2026-05-17T17:23:23Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• Perfectly-Private Analog Secure Aggregation in Federated Learning [51.61616734974475]
  In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model.<n>In this paper, a novel secure parameter aggregation method is proposed that employs the torus rather than a finite field.
  arXiv  Detail & Related papers  (2025-09-10T15:22:40Z)
• Enhancing Federated Learning with Adaptive Differential Privacy and Priority-Based Aggregation [0.0]
  Federated learning (FL) develops global models without direct access to local datasets. It is possible to access the model updates transferred between clients and servers, potentially revealing sensitive local information to adversaries. Differential privacy (DP) offers a promising approach to addressing this issue by adding noise to the parameters. We propose a personalized DP framework that injects noise based on clients' relative impact factors and aggregates parameters.
  arXiv  Detail & Related papers  (2024-06-26T16:55:07Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• 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)
• Holistic Robust Data-Driven Decisions [0.0]
  Practical overfitting can typically not be attributed to a single cause but is caused by several factors simultaneously.<n>We consider here three overfitting sources: (i) statistical error as a result of working with finite sample data, (ii) data noise, which occurs when the data points are measured only with finite precision, and finally, (iii) data misspecification in which a small fraction of all data may be wholly corrupted.<n>We design a novel data-driven formulation that guarantees such holistic protection and is computationally viable.
  arXiv  Detail & Related papers  (2022-07-19T21:28:51Z)
• Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer [46.68586555288172]
  We propose a novel task named Semi-supervised Source Hypothesis Transfer (SSHT), which performs domain adaptation based on source trained model, to generalize well in target domain with a few supervisions. We propose Consistency and Diversity Learning (CDL), a simple but effective framework for SSHT by facilitating prediction consistency between two randomly augmented unlabeled data. Experimental results show that our method outperforms existing SSDA methods and unsupervised model adaptation methods on DomainNet, Office-Home and Office-31 datasets.
  arXiv  Detail & Related papers  (2021-07-07T04:14:24Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

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.