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

arXiv: https://arxiv.org/abs/2609.14591 · HTML: https://mlsanity.com/paper/2609.14591/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning](https://mlsanity.com/paper/2103.03228/) (2021)
- [Mechanisms that Incentivize Data Sharing in Federated Learning](https://mlsanity.com/paper/2207.04557/) (2022)
- [Sequential Mechanisms with ex-post Participation Guarantees](https://mlsanity.com/paper/1603.07229/) (2016)
- [Online Truthful Mechanisms for Multi-sided Markets](https://mlsanity.com/paper/1604.04859/) (2016)
- [Optimal dynamic mechanisms with ex-post IR via bank accounts](https://mlsanity.com/paper/1605.08840/) (2016)
- [Dynamic Rental Games with Stagewise Individual Rationality](https://mlsanity.com/paper/2505.07579/) (2025)

## Abstract (arXiv)

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 rather than only an asymptotic equilibrium guarantee under different degrees of client data heterogeneity. Along the learning 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. We prove that such a cap drives all contributions to zero, with high probability, when its tolerance is small relative to the warm-up deficit, and we observe learning collapse under it even at low heterogeneity. We then propose a design that combines a short-term participation guarantee, enforced after an announced grace window, with personalized model evaluation, while preserving the incentive properties of the underlying mechanism. We provide a theoretical basis for this approach and empirically demonstrate that, after the grace window, clients meet IR on nearly all rounds without harming overall performance under low to moderate heterogeneity; under severe heterogeneity, the design shows promising outcomes for clients compared to their local baseline at some cost in accuracy.