A Unifying Framework for Typical Multi-Task Multiple Kernel Learning Problems

TL;DR

This paper introduces a comprehensive framework for Multi-Task Multi-Kernel Learning that unifies existing formulations and proposes a new problem, demonstrating its flexibility and effectiveness through experiments.

Contribution

It presents a unifying Multi-Task MKL framework that encompasses various existing formulations and introduces a new PSCS-MKL approach.

Findings

The framework effectively subsumes well-known Multi-Task MKL formulations.

A simple algorithm can solve the unifying framework efficiently.

The new PSCS-MKL approach shows promising experimental results.

Abstract

Over the past few years, Multi-Kernel Learning (MKL) has received significant attention among data-driven feature selection techniques in the context of kernel-based learning. MKL formulations have been devised and solved for a broad spectrum of machine learning problems, including Multi-Task Learning (MTL). Solving different MKL formulations usually involves designing algorithms that are tailored to the problem at hand, which is, typically, a non-trivial accomplishment. In this paper we present a general Multi-Task Multi-Kernel Learning (Multi-Task MKL) framework that subsumes well-known Multi-Task MKL formulations, as well as several important MKL approaches on single-task problems. We then derive a simple algorithm that can solve the unifying framework. To demonstrate the flexibility of the proposed framework, we formulate a new learning problem, namely Partially-Shared Common Space (PSCS) Multi-Task MKL, and demonstrate its merits through experimentation.