A Multiple Gradient Descent Design for Multi-Task Learning on Edge Computing: Multi-Objective Machine Learning Approach

Multi-task learning technique is widely utilized in machine learning modeling where commonalities and differences across multiple tasks are exploited. However, multiple conflicting objectives often occur in multi-task learning. Conventionally, a common compromise is to minimize the weighted sum of multiple objectives which may be invalid if the objectives are competing. In this paper, a novel multi-objective machine learning approach is proposed to solve this challenging issue, which reformulates the multi-task learning as multi-objective optimization. To address the issues contributed by existing multi-objective optimization algorithms, a multi-gradient descent algorithm is introduced for the multi-objective machine learning problem by which an innovative gradient-based optimization is leveraged to converge to an optimal solution of the Pareto set. Moreover, the gradient surgery for the multi-gradient descent algorithm is proposed to obtain a stable Pareto optimal solution. As most of the edge computing devices are computational resource-constrained, the proposed method is implemented for optimizing the edge device's memory, computation and communication demands. The proposed method is applied to the multiple license plate recognition problem. The experimental results show that the proposed method outperforms state-of-the-art learning methods and can successfully find solutions that balance multiple objectives of the learning task over different datasets.

Automated summary

This paper proposes a novel multi-objective machine learning approach to solve the challenge of multiple conflicting objectives in multi-task learning. The proposed method outperforms existing learning methods and successfully balances multiple learning tasks.