Communication-Aware Collaborative Learning
This work is significant for researchers and practitioners in distributed machine learning who need to optimize communication efficiency in collaborative learning settings, especially when dealing with classification noise.
This paper addresses the challenge of reducing communication costs in collaborative PAC learning, both in noiseless and noisy environments. The authors developed communication-efficient algorithms using distributed boosting, achieving this goal with minimal impact on sample complexity.
Algorithms for noiseless collaborative PAC learning have been analyzed and optimized in recent years with respect to sample complexity. In this paper, we study collaborative PAC learning with the goal of reducing communication cost at essentially no penalty to the sample complexity. We develop communication efficient collaborative PAC learning algorithms using distributed boosting. We then consider the communication cost of collaborative learning in the presence of classification noise. As an intermediate step, we show how collaborative PAC learning algorithms can be adapted to handle classification noise. With this insight, we develop communication efficient algorithms for collaborative PAC learning robust to classification noise.