REVIEW 5 cited by
A Comprehensive Survey of Incentive Mechanism for Federated Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Federated learning utilizes various resources provided by participants to collaboratively train a global model, which potentially address the data privacy issue of machine learning. In such promising paradigm, the performance will be deteriorated without sufficient training data and other resources in the learning process. Thus, it is quite crucial to inspire more participants to contribute their valuable resources with some payments for federated learning. In this paper, we present a comprehensive survey of incentive schemes for federate learning. Specifically, we identify the incentive problem in federated learning and then provide a taxonomy for various schemes. Subsequently, we summarize the existing incentive mechanisms in terms of the main techniques, such as Stackelberg game, auction, contract theory, Shapley value, reinforcement learning, blockchain. By reviewing and comparing some impressive results, we figure out three directions for the future study.
Forward citations
Cited by 5 Pith papers
-
From Compensation Design to Budget-Feasible Mechanisms: A Constant Approximation for Subadditive Valuations
Universally truthful budget-feasible mechanisms with constants 3, e+1, and 2e+1 for submodular, XOS, and subadditive valuations, plus a polynomial-time demand-query mechanism with approximation C+epsilon (C<86.399) fo...
-
Compensation Design
Under monotone submodular platform value and private agent costs, the marginal-contribution payment rule admits pure Nash equilibria and a tight price of anarchy of 2+o(1), while Shapley-value payments can have no pur...
-
DICE: Data Influence Cascade in Decentralized Learning
DICE defines and approximates multi-hop data influence in decentralized learning, showing that influence is shaped by data, topology, and loss curvature.
-
Reputation-driven Cooperation in Lattice-based Decentralized Federated Learning through Evolutionary Game Theory
In a lattice-based simulation of decentralized federated learning, a reputation mechanism that rewards cooperators and penalizes defectors raises average accuracy from 70% to 82% and drives cooperation to near 100%.
-
Incentivizing Inclusive Contributions in Model Sharing Markets
iPFL combines graph-based personalized federated learning with a game-theoretic payment rule, proving non-negative utility and one-sided truthfulness, and showing higher economic utility in simulated markets.
Discussion (0). Continue with ORCID to comment.