Multi-Objective Optimization for Sparse Deep Multi-Task Learning

TL;DR

This paper introduces a multi-objective optimization algorithm for deep multi-task learning that effectively balances conflicting criteria like task performance and sparsity, enabling adaptive model sparsification during training.

Contribution

It presents a novel scalarization-based optimization method that finds all optimal solutions and facilitates sparsity in deep multi-task models using standard optimizers.

Findings

Adaptive sparsification during training is possible without significant performance loss.

The method effectively balances multiple conflicting objectives in deep learning.

Experimental results demonstrate improved model efficiency with maintained accuracy.

Abstract

Different conflicting optimization criteria arise naturally in various Deep Learning scenarios. These can address different main tasks (i.e., in the setting of Multi-Task Learning), but also main and secondary tasks such as loss minimization versus sparsity. The usual approach is a simple weighting of the criteria, which formally only works in the convex setting. In this paper, we present a Multi-Objective Optimization algorithm using a modified Weighted Chebyshev scalarization for training Deep Neural Networks (DNNs) with respect to several tasks. By employing this scalarization technique, the algorithm can identify all optimal solutions of the original problem while reducing its complexity to a sequence of single-objective problems. The simplified problems are then solved using an Augmented Lagrangian method, enabling the use of popular optimization techniques such as Adam and Stochastic Gradient Descent, while efficaciously handling constraints. Our work aims to address the (economical and also ecological) sustainability issue of DNN models, with a particular focus on Deep Multi-Task models, which are typically designed with a very large number of weights to perform equally well on multiple tasks. Through experiments conducted on two Machine Learning datasets, we demonstrate the possibility of adaptively sparsifying the model during training without significantly impacting its performance, if we are willing to apply task-specific adaptations to the network weights. Code is available at https://github.com/salomonhotegni/MDMTN