Optimally Improving Cooperative Learning in a Social Setting

TL;DR

This paper addresses how to optimally correct a few classifiers in a networked cooperative learning setting to maximize overall accuracy, providing polynomial algorithms for aggregate objectives and approximation methods for egalitarian goals, supported by theoretical guarantees and experiments.

Contribution

It introduces algorithms for fixing classifiers in a network to improve collective accuracy, including polynomial-time solutions for aggregate objectives and approximation algorithms for egalitarian objectives, with proven guarantees.

Findings

Polynomial-time algorithm for aggregate objective optimization.

NP-hardness of egalitarian objective optimization.

Effective approximation algorithms with proven performance.

Abstract

We consider a cooperative learning scenario where a collection of networked agents with individually owned classifiers dynamically update their predictions, for the same classification task, through communication or observations of each other's predictions. Clearly if highly influential vertices use erroneous classifiers, there will be a negative effect on the accuracy of all the agents in the network. We ask the following question: how can we optimally fix the prediction of a few classifiers so as maximize the overall accuracy in the entire network. To this end we consider an aggregate and an egalitarian objective function. We show a polynomial time algorithm for optimizing the aggregate objective function, and show that optimizing the egalitarian objective function is NP-hard. Furthermore, we develop approximation algorithms for the egalitarian improvement. The performance of all of our algorithms are guaranteed by mathematical analysis and backed by experiments on synthetic and real data.