The paper proposes mechanisms for federated learning that both incentivize strategic data owners to contribute fully and learn a high‑quality model. The first mechanism, UPBReD, jointly updates client contributions and the model, converging to a Nash equilibrium that may involve under‑contribution. The second mechanism, 2P‑UPBReD, introduces budget‑balanced transfers to make full contribution a dominant strategy, ensuring convergence to the optimal model while guaranteeing that all clients prefer to participate. Subsequent extensions (T‑2P‑UPBReD) further enforce truthful reporting of contributions and gradients without running a deficit, and experiments on CIFAR‑10, FEMNIST, and Twitter demonstrate that 2P‑UPBReD achieves welfare comparable to FedAvg trained on all data.
arXiv:2503. 07869v4 Announce Type: replace Abstract: Critical learning periods (CLPs) in federated learning (FL) refer to early stages during which low-quality contributions (e.
The paper investigates the trade‑off between the costs of participating in federated learning (privacy, communication, compute) and the potential gains in model performance, framing this as a game‑theoretic problem of individual rationality versus autarky. It shows that clients can remain below their local‑training baseline for many rounds and that simply capping per‑round contributions harms learning. The authors propose a new mechanism that provides short‑term participation guarantees and personalized model evaluation, demonstrating theoretically and empirically that clients can avoid short‑term losses without significantly harming overall performance, even under moderate heterogeneity.
arXiv:2412.07813v4 Announce Type: replace-cross Abstract: To alleviate the training burden in federated learning while enhancing convergence speed, Split Federated Learning (SFL) has emerged as a pro...
arXiv:2507. 09473v2 Announce Type: replace-cross Abstract: We study the dynamic allocation of indivisible resources to strategic agents under long-term constraints, where the planner aims to maximize social welfare, satisfy multiple constraints, and elicit near-truthful reports.
arXiv:2610.07491v1 Announce Type: cross Abstract: When multiple agents share a cost budget, a common Lagrange multiplier can enforce the aggregate constraint but does not determine how its penalty sh...
arXiv:2606. 18384v1 Announce Type: new Abstract: Hierarchical Federated Learning (HFL) enables scalable collaborative model training across distributed devices while preserving data privacy.
arXiv:2607. 26788v1 Announce Type: cross Abstract: Clustered federated learning benefits from organizing heterogeneous participants into coalitions that train coalition-specific models, but such clustering is sustainable only if participants prefer their assigned coalition and the required transfers are affordable.
arXiv:2610.07212v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) trains a language model on problems that may themselves be confidential, and the trained model ca...
The paper introduces ProAS, a Progress‑Aware Advantage Shaping framework designed to improve critic‑free reinforcement learning for large language model agents. ProAS uses a dynamic Agentic Reference Graph to provide fine‑grained credit assignment through Masking Unreasonable Incentives and Asymmetric Penalty Redistribution, avoiding the uniform advantage broadcast that can reinforce invalid actions. Experiments on Qwen2.5‑1.5B‑Instruct and Qwen2.5‑7B‑Instruct show that ProAS raises baseline success rates to 91.9% and 94.3% on ALFWorld and 66.7% and 70.8% on WebShop, while speeding up training convergence up to 2.44× and remaining robust to imperfect reference graphs.
arXiv:2411. 11793v2 Announce Type: replace Abstract: In federated learning (FL), a central server typically allocates training efforts to clients.
The paper studies a repeated principal–agent game where the principal cannot observe the agent’s rewards and both parties learn over time. It introduces a non‑parametric estimator that uses only the history of incentives and choices, and combines it with a data‑driven incentive policy in a multi‑armed bandit setting. The authors prove finite‑sample consistency of the estimator and provide a regret bound for the principal, supported by simulations on green‑energy aggregator contracts.
arXiv:2608. 01556v1 Announce Type: new Abstract: Large language models are increasingly aligned to human preferences via reward modeling, but user preference data are sensitive and often cannot be centralized.