Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design

• URL: http://arxiv.org/abs/2609.14591v1
• Date: Sun, 13 Sep 2026 15:18:02 GMT
• Title: Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design
• Abstract summary: Clients trade off privacy, communication, and compute costs for greater gains in model efficacy.<n>This paper explores this tradeoff under the aegis of individual rationality (IR) versus autarky.<n>We propose a novel design that combines short-term participation guarantees with personalized model evaluation.
• Score: 13.821738908770982
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Participation in federated learning (FL) comes at a cost. Clients trade off privacy, communication, and compute costs for potentially greater gains in model efficacy. This paper explores this tradeoff under the aegis of individual rationality (IR) versus autarky, the basic game-theoretic requirement that the federation provide utility no worse than local training. Using the above as the design target, we examine pathwise performance of FL, as a per-round bound on cumulative surplus, not just as an asymptotic equilibrium guarantee under different models of client data distribution heterogeneity. Along this path, clients can remain below their local-training baseline for hundreds of rounds. The natural remedy is to cap each client's per-round contribution so that this shortfall stays bounded, and we prove that it backfires, collapsing learning even at low-to-modest heterogeneity. We then propose a novel design that combines short-term participation guarantees with personalized model evaluation, while maintaining fair incentives. We provide a theoretical basis for this new approach and empirically demonstrate that clients can avoid short-term losses without harming overall performance, even under moderate data distribution heterogeneity; under severe heterogeneity, the design shows promising outcomes for clients compared to their local baseline at some cost in accuracy.

Related papers

• Federated Ensemble Learning with Progressive Model Personalization [1.1045253485823572]
  Federated Learning provides a privacy-preserving paradigm for distributed learning, but suffers from statistical heterogeneity across clients.<n>A widely adopted approach in PFL decomposes neural networks into a shared feature extractor and client-specific heads.<n>Most existing methods rely on rigid, shallow heads, and therefore fail to navigate this tradeoff in a principled manner.<n>We propose a boosting-inspired framework that enables a smooth control of this tradeoff.
  arXiv  Detail & Related papers  (2026-02-15T17:35:52Z)
• Whom to Trust? Adaptive Collaboration in Personalized Federated Learning [11.923664505655026]
  We show that adaptivity in collaboration and fine-grained trust, at the level of individual examples, can be achieved within federated semi-supervised learning.<n>We develop FEDMOSAIC, a personalized co-training method where clients reweight their loss and their contribution to pseudo-labels based on per-example agreement and confidence.
  arXiv  Detail & Related papers  (2025-06-30T20:53:01Z)
• FedImpro: Measuring and Improving Client Update in Federated Learning [77.68805026788836]
  Federated Learning (FL) models often experience client drift caused by heterogeneous data. We present an alternative perspective on client drift and aim to mitigate it by generating improved local models.
  arXiv  Detail & Related papers  (2024-02-10T18:14:57Z)
• 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)
• Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation [31.2017942327673]
  This paper proposes a game theoretic incentive mechanism for federated learning (FL) with randomized client participation. We show that our mechanism achieves higher model performance for the server as well as higher profits for the clients.
  arXiv  Detail & Related papers  (2023-04-17T04:05:57Z)
• Adaptive Federated Learning via New Entropy Approach [14.595709494370372]
  Federated Learning (FL) has emerged as a prominent distributed machine learning framework. In this paper, we propose an adaptive FEDerated learning algorithm based on ENTropy theory (FedEnt) to alleviate the parameter deviation among heterogeneous clients.
  arXiv  Detail & Related papers  (2023-03-27T07:57:04Z)
• FedABC: Targeting Fair Competition in Personalized Federated Learning [76.9646903596757]
  Federated learning aims to collaboratively train models without accessing their client's local private data. We propose a novel and generic PFL framework termed Federated Averaging via Binary Classification, dubbed FedABC. In particular, we adopt the one-vs-all'' training strategy in each client to alleviate the unfair competition between classes.
  arXiv  Detail & Related papers  (2023-02-15T03:42:59Z)
• Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction [76.26710990597498]
  We show that the class-imbalance of the grouped data from randomly selected clients can lead to significant performance degradation. Based on our key observation, we design an efficient client sampling mechanism, i.e., Federated Class-balanced Sampling (Fed-CBS) In particular, we propose a measure of class-imbalance and then employ homomorphic encryption to derive this measure in a privacy-preserving way.
  arXiv  Detail & Related papers  (2022-09-30T05:42:56Z)
• A Contract Theory based Incentive Mechanism for Federated Learning [52.24418084256517]
  Federated learning (FL) serves as a data privacy-preserved machine learning paradigm, and realizes the collaborative model trained by distributed clients. To accomplish an FL task, the task publisher needs to pay financial incentives to the FL server and FL server offloads the task to the contributing FL clients. It is challenging to design proper incentives for the FL clients due to the fact that the task is privately trained by the clients.
  arXiv  Detail & Related papers  (2021-08-12T07:30:42Z)
• Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocation [119.19061102064497]
  We propose a decentralized FL framework by integrating blockchain into FL, namely, blockchain assisted decentralized federated learning (BLADE-FL) In a round of the proposed BLADE-FL, each client broadcasts its trained model to other clients, competes to generate a block based on the received models, and then aggregates the models from the generated block before its local training of the next round. We explore the impact of lazy clients on the learning performance of BLADE-FL, and characterize the relationship among the optimal K, the learning parameters, and the proportion of lazy clients.
  arXiv  Detail & Related papers  (2021-01-18T07:19:08Z)
• An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee [36.07970788489]
  Federated Learning is a new paradigm to cope with the privacy issue by allowing clients to perform model training locally. The client selection policy is critical to an FL process in terms of training efficiency, the final model's quality as well as fairness. In this paper, we will model the fairness guaranteed client selection as a Lyapunov optimization problem and then a C2MAB-based method is proposed for estimation of the model exchange time.
  arXiv  Detail & Related papers  (2020-11-03T15:27:02Z)

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.