Delegating Data Collection in Decentralized Machine Learning

TL;DR

This paper develops contract-based mechanisms for data collection in decentralized machine learning, addressing information asymmetries and providing adaptive solutions that improve utility.

Contribution

It introduces optimal and near-optimal contract designs for decentralized ML data collection, including adaptive convex programming methods and analysis of multiple interaction settings.

Findings

Linear contracts achieve 1-1/e of optimal utility.

Convex programming efficiently computes adaptive optimal contracts.

Analysis extends to multiple interaction scenarios.

Abstract

Motivated by the emergence of decentralized machine learning (ML) ecosystems, we study the delegation of data collection. Taking the field of contract theory as our starting point, we design optimal and near-optimal contracts that deal with two fundamental information asymmetries that arise in decentralized ML: uncertainty in the assessment of model quality and uncertainty regarding the optimal performance of any model. We show that a principal can cope with such asymmetry via simple linear contracts that achieve 1-1/e fraction of the optimal utility. To address the lack of a priori knowledge regarding the optimal performance, we give a convex program that can adaptively and efficiently compute the optimal contract. We also study linear contracts and derive the optimal utility in the more complex setting of multiple interactions.