A Multi-Task Gradient Descent Method for Multi-Label Learning

TL;DR

This paper introduces a Multi-task Gradient Descent algorithm for multi-label learning, enabling simultaneous task optimization with effective parameter transfer, theoretical convergence, and improved performance on multi-label datasets.

Contribution

It proposes a novel multi-task gradient descent method that efficiently handles related tasks in multi-label learning, with theoretical guarantees and practical advantages over existing methods.

Findings

Algorithm converges under proper transfer mechanisms

Achieves competitive results on multi-label datasets

Supports parallel computing for large task sets

Abstract

Multi-label learning studies the problem where an instance is associated with a set of labels. By treating single-label learning problem as one task, the multi-label learning problem can be casted as solving multiple related tasks simultaneously. In this paper, we propose a novel Multi-task Gradient Descent (MGD) algorithm to solve a group of related tasks simultaneously. In the proposed algorithm, each task minimizes its individual cost function using reformative gradient descent, where the relations among the tasks are facilitated through effectively transferring model parameter values across multiple tasks. Theoretical analysis shows that the proposed algorithm is convergent with a proper transfer mechanism. Compared with the existing approaches, MGD is easy to implement, has less requirement on the training model, can achieve seamless asymmetric transformation such that negative transfer is mitigated, and can benefit from parallel computing when the number of tasks is large. The competitive experimental results on multi-label learning datasets validate the effectiveness of the proposed algorithm.