Controllable Pareto Multi-Task Learning

Abstract

A multi-task learning (MTL) system aims at solving multiple related tasks at the same time. With a fixed model capacity, the tasks would be conflicted with each other, and the system usually has to make a trade-off among learning all of them together. For many real-world applications where the trade-off has to be made online, multiple models with different preferences over tasks have to be trained and stored. This work proposes a novel controllable Pareto multi-task learning framework, to enable the system to make real-time trade-off control among different tasks with a single model. To be specific, we formulate the MTL as a preference-conditioned multiobjective optimization problem, with a parametric mapping from preferences to the corresponding trade-off solutions. A single hypernetwork-based multi-task neural network is built to learn all tasks with different trade-off preferences among them, where the hypernetwork generates the model parameters conditioned on the preference. For inference, MTL practitioners can easily control the model performance based on different trade-off preferences in real-time. Experiments on different applications demonstrate that the proposed model is efficient for solving various MTL problems.

References in corpus (17)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• An Overview of Multi-Task Learning in Deep Neural Networks
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• A Survey on Multi-Task Learning
• Multi-Task Learning as Multi-Objective Optimization
• Which Tasks Should Be Learned Together in Multi-task Learning?
• Learning Multiple Tasks with Multilinear Relationship Networks
• Neural Architecture Transfer
• Deep Multi-task Representation Learning: A Tensor Factorisation Approach
• Pareto Multi-Task Learning
• Principled Weight Initialization for Hypernetworks
• Efficient Continuous Pareto Exploration in Multi-Task Learning
• Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions
• Multi-Gradient Descent for Multi-Objective Recommender Systems
• Hypermodels for Exploration
• On Infinite-Width Hypernetworks

Cited by in corpus (6)

• Learning the Pareto Front with Hypernetworks
• Controllable Multi-Objective Re-ranking with Policy Hypernetworks
• Pareto-optimal clustering with the primal deterministic information bottleneck
• Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
• Multi-task problems are not multi-objective
• Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set