Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners

Drashthi Doshi; Avishek Ghosh; Swaprava Nath

cs.GTMay 17, 2025

Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners

Authors: Drashthi Doshi, Avishek Ghosh, Swaprava Nath

Organizations: IIT Bombay

Abstract

In federated learning (FL), a center trains a shared model from updates that clients compute on their private data. Collecting and training on data is costly, so a strategic client may contribute little data and free-ride on the model trained by the others. We study mechanisms that incentivize data contribution and learn the model at the same time. Our first mechanism, UPBReD, updates the clients ' contributions and the model jointly, and converges at a geometric rate to a Nash equilibrium of the contribution game together with the welfare-maximizing model for those contributions. This equilibrium can involve under-contribution, so our second mechanism, 2P-UPBReD, adds budget-balanced transfers that make full contribution a dominant strategy, after which training converges to the optimal model; we also give conditions under which every client prefers to participate. Both mechanisms trust what clients report about the data they use and the gradients they compute. We show that no payment rule can reward unverifiable contributions unless something the center observes depends on the data actually used. Building on this, T-2P-UPBReD checks each client's reported contribution against the other clients ' realized valuations of the trained model, and prices gradient reports with a budget-balanced charge. It elicits truthful contribution reports, makes gradient reports approximately truthful, still reaches full contribution and the optimal model, and never runs a deficit. Experiments on CIFAR-10, FEMNIST, and Twitter show that 2P-UPBReD matches the welfare of FedAvg trained on all data, while strategic clients without incentives lower the welfare of the learned model.

Figures & tables

	Eq.	Learn.	Transfers	Reports	Truthful	Contrib.	Private
Procaccia et al. [42]	E	✗	BB	D	DSIC	P	✗
Bornstein et al. [3]	E	✗	✓	C	DSIC	F	✓
Blum et al. [2]	E	✗	✗	S	✗	P	✓
Murhekar et al. [38]	C	✗	BB	S,C	✗	P	✓
Karimireddy et al. [27]	E	✗	✓	S,C	✗	F	✓
UPBReD (Thm. 1 )	C	J	✗	S,G	✗	P	✓

Table 1: Comparison with incentive mechanisms for FL; our mechanisms are in the last four rows. Eq. : existence (E) of, or convergence (C) to, a Nash equilibrium. Learn. : joint convergence of the model and the contributions (J), or convergence to the optimal parameter

w^{\texttt{{OPT}}}

(OPT). Transfers : budget balanced (BB), budget balanced on the truthful path and never in deficit (BB ∗ ), individually rational (IR). Reports : data distribution (D), cost (C), contribution (S), gradient (G). Truthful : guarantee for the reported quantity;

\varepsilon

denotes

\varepsilon

-truthfulness with a vanishing gain from misreporting, and † marks guarantees that rely on agents observing realized valuations ( Assumption 5 ); Proposition 2 shows that evidence of this kind is necessary. Contrib. : partial (P) or full (F) contribution at equilibrium. Private : data are not shared with the center.

Panel of Figure 1 — Figure 1: Shaded regions show the feasible choices of $\gamma$ in Theorem 1 for $n=2$ and $L=2$ : (a) as a function of $\lambda$ for the values of $\tilde{P}$ shown, and (b) as a function of $\tilde{P}$ for the values of $\lambda$ shown. Dashed lines mark the boundary $\gamma=2(\lambda-\tilde{P})/(n^{2}L^{2}-\tilde{P}^{2})$ . The region is empty when $\lambda\leqslant\tilde{P}$ . The feasible choices of $\eta$ are obtained by replacing $(n,L,\lambda,\tilde{P})$ with $(m,\tilde{L},\tilde{\lambda},P)$ .

Panel of Figure 2 — Figure 2: The three rows in this figure correspond to the experiments with the datasets CIFAR-10, FEMNIST, and Twitter, respectively. The y-axis in every plot is the social welfare (computed using $10-L_{i}(w)$ , where $L_{i}(w)$ is the test loss for agent $i$ ). The x-axis corresponds to the number of agents in the first plot, the choice of $\beta$ in the second, and the time taken (in minutes) in the third plot, respectively, in every row.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 3 — Figure 3: The three rows in this figure correspond to the experiments with the datasets CIFAR-10, FEMNIST, and Twitter, respectively. The y-axis in every plot is the social welfare (computed using test accuracy for each agent). The x-axis corresponds to the number of agents in the first plot, the choice of $\beta$ in the second, and the time taken (in minutes) in the third plot, respectively, in every row.

Panel of Figure 4 — Figure 4: Social welfare vs. number of clients for different CIFAR-10 dataset splits using the Flower framework.

Panel of Figure 5 — Figure 5: Label distributions for different data partitioning strategies using Flower with $10$ agents. The x-axis represents the client ID and the y-axis represents the number of data points of the given label.

Figure 6: Utilities and payments received by agents for 2P-UPBReD based on their data contributions for FEMNIST (averaged over 10 runs).

Layer (type:depth-idx)	Output Shape	Param #
Cifar10ResNet	[1, 10]	–
Conv2d: 1-1	[1, 64, 32, 32]	1,728
BatchNorm2d: 1-2	[1, 64, 32, 32]	128
ReLU: 1-3	[1, 64, 32, 32]	–
Identity: 1-4	[1, 64, 32, 32]	–
Sequential (layer1): 1-5	[1, 64, 32, 32]	147,968

Appendix

Table 2: Layer-wise Summary of Cifar10ResNet for CIFAR-10

Layer (type:depth-idx)	Output Shape	Param #
FemnistCNN	[1, 62]	–
Conv2d: 1-1	[1, 32, 28, 28]	832
MaxPool2d: 1-2	[1, 32, 14, 14]	–
Conv2d: 1-3	[1, 64, 14, 14]	51,264
MaxPool2d: 1-4	[1, 64, 7, 7]	–
Linear: 1-5	[1, 2048]	6,424,576

Appendix

Table 3: Layer-wise Summary of the CNN for FEMNIST

Panel of Figure 7 — Figure 7: Ratio of social welfare with adversaries and without adversaries.

Incentive Mechanisms for Federated Learning

See all 10 papers

Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation
Mar 21, 2026Fateme Maleki, Krishnan Raghavan, Farzad YousefianIncentive Mechanisms for Federated Learning Federated Learning
Department of Industrial and Systems Engineering, Rutgers University, USA. · Argonne National Laboratory, Lemont, IL, USA.
FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning
Apr 12, 2026Tao Liu, Xuehe WangIncentive Mechanisms for Federated Learning Federated Learning
School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519082, China
Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design
Sep 13, 2026Amin Meghrazi, Srinivasan Parthasarathy, Andrew PerraultFederated Learning Incentive Mechanisms for Federated Learning
The Ohio State University

Mar 21, 2026J/K move · Enter open · S save

Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation

Fateme Maleki, Krishnan Raghavan, Farzad Yousefian

Department of Industrial and Systems Engineering, Rutgers University, USA. · Argonne National Laboratory, Lemont, IL, USA.

Incentive Mechanisms for Federated Learning Federated Learning Federated Learning Aggregation

Open paper AskPDF arXiv

Federated learning (FL) is a communication-efficient collaborative learning framework that enables model training across multiple agents with private local datasets. While the benefits of FL in improving global model performance are well established, individual agents may behave strategically, balancing the learning payoff against the cost of contributing their local data. Motivated by the need for FL frameworks that successfully retain participating agents, we propose an incentive-aware federated averaging method in which, at each communication round, clients transmit both their local model parameters and their updated training dataset sizes to the server. The dataset sizes are dynamically adjusted via a Nash equilibrium (NE)-seeking update rule that captures strategic data participation. We analyze the proposed method under convex and nonconvex global objective settings and establish performance guarantees for the resulting incentive-aware FL algorithm. Furthermore, under a merely monotone game setting, we consider a welfare loss minimization framework and establish asymptotic convergence of the scheme. Numerical experiments on the MNIST and CIFAR-10 datasets demonstrate that agents achieve competitive global model performance while converging to stable data participation strategies.

Abstract

Incentive Mechanisms for Federated Learning

Explore similar work

Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation

FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning

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