Mechanisms that Incentivize Data Sharing in Federated Learning
- URL: http://arxiv.org/abs/2207.04557v1
- Date: Sun, 10 Jul 2022 22:36:52 GMT
- Title: Mechanisms that Incentivize Data Sharing in Federated Learning
- Authors: Sai Praneeth Karimireddy, Wenshuo Guo, Michael I. Jordan
- Abstract summary: We show how a naive scheme leads to catastrophic levels of free-riding where the benefits of data sharing are completely eroded.
We then introduce accuracy shaping based mechanisms to maximize the amount of data generated by each agent.
- Score: 90.74337749137432
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Federated learning is typically considered a beneficial technology which
allows multiple agents to collaborate with each other, improve the accuracy of
their models, and solve problems which are otherwise too data-intensive /
expensive to be solved individually. However, under the expectation that other
agents will share their data, rational agents may be tempted to engage in
detrimental behavior such as free-riding where they contribute no data but
still enjoy an improved model. In this work, we propose a framework to analyze
the behavior of such rational data generators. We first show how a naive scheme
leads to catastrophic levels of free-riding where the benefits of data sharing
are completely eroded. Then, using ideas from contract theory, we introduce
accuracy shaping based mechanisms to maximize the amount of data generated by
each agent. These provably prevent free-riding without needing any payment
mechanism.
Related papers
- Efficient Core-selecting Incentive Mechanism for Data Sharing in
Federated Learning [0.12289361708127873]
Federated learning is a distributed machine learning system that uses participants' data to train an improved global model.
How to establish an incentive mechanism that both incentivizes inputting data truthfully and promotes stable cooperation has become an important issue to consider.
We propose an efficient core-selecting mechanism based on sampling approximation that only aggregates models on sampled coalitions to approximate the exact result.
arXiv Detail & Related papers (2023-09-21T01:47:39Z) - No Bidding, No Regret: Pairwise-Feedback Mechanisms for Digital Goods
and Data Auctions [14.87136964827431]
This study presents a novel mechanism design addressing a general repeated-auction setting.
The mechanism's novelty lies in using pairwise comparisons for eliciting information from the bidder.
Our focus on human factors contributes to the development of more human-aware and efficient mechanism design.
arXiv Detail & Related papers (2023-06-02T18:29:07Z) - Towards Generalizable Data Protection With Transferable Unlearnable
Examples [50.628011208660645]
We present a novel, generalizable data protection method by generating transferable unlearnable examples.
To the best of our knowledge, this is the first solution that examines data privacy from the perspective of data distribution.
arXiv Detail & Related papers (2023-05-18T04:17:01Z) - Investigating Bias with a Synthetic Data Generator: Empirical Evidence
and Philosophical Interpretation [66.64736150040093]
Machine learning applications are becoming increasingly pervasive in our society.
Risk is that they will systematically spread the bias embedded in data.
We propose to analyze biases by introducing a framework for generating synthetic data with specific types of bias and their combinations.
arXiv Detail & Related papers (2022-09-13T11:18:50Z) - Data Sharing Markets [95.13209326119153]
We study a setup where each agent can be both buyer and seller of data.
We consider two cases: bilateral data exchange (trading data with data) and unilateral data exchange (trading data with money)
arXiv Detail & Related papers (2021-07-19T06:00:34Z) - Test-time Collective Prediction [73.74982509510961]
Multiple parties in machine learning want to jointly make predictions on future test points.
Agents wish to benefit from the collective expertise of the full set of agents, but may not be willing to release their data or model parameters.
We explore a decentralized mechanism to make collective predictions at test time, leveraging each agent's pre-trained model.
arXiv Detail & Related papers (2021-06-22T18:29:58Z) - Representative & Fair Synthetic Data [68.8204255655161]
We present a framework to incorporate fairness constraints into the self-supervised learning process.
We generate a representative as well as fair version of the UCI Adult census data set.
We consider representative & fair synthetic data a promising future building block to teach algorithms not on historic worlds, but rather on the worlds that we strive to live in.
arXiv Detail & Related papers (2021-04-07T09:19:46Z) - ASCII: ASsisted Classification with Ignorance Interchange [17.413989127493622]
We propose a method named ASCII for an agent to improve its classification performance through assistance from other agents.
The main idea is to iteratively interchange an ignorance value between 0 and 1 for each collated sample among agents.
The method is naturally suitable for privacy-aware, transmission-economical, and decentralized learning scenarios.
arXiv Detail & Related papers (2020-10-21T03:57:36Z)
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.