Learning the Pareto Front with Hypernetworks

Abstract

Multi-objective optimization (MOO) problems are prevalent in machine learning. These problems have a set of optimal solutions, called the Pareto front, where each point on the front represents a different trade-off between possibly conflicting objectives. Recent MOO methods can target a specific desired ray in loss space however, most approaches still face two grave limitations: (i) A separate model has to be trained for each point on the front; and (ii) The exact trade-off must be known before the optimization process. Here, we tackle the problem of learning the entire Pareto front, with the capability of selecting a desired operating point on the front after training. We call this new setup Pareto-Front Learning (PFL). We describe an approach to PFL implemented using HyperNetworks, which we term Pareto HyperNetworks (PHNs). PHN learns the entire Pareto front simultaneously using a single hypernetwork, which receives as input a desired preference vector and returns a Pareto-optimal model whose loss vector is in the desired ray. The unified model is runtime efficient compared to training multiple models and generalizes to new operating points not used during training. We evaluate our method on a wide set of problems, from multi-task regression and classification to fairness. PHNs learn the entire Pareto front at roughly the same time as learning a single point on the front and at the same time reach a better solution set. Furthermore, we show that PHNs can scale to generate large models like ResNet18. PFL opens the door to new applications where models are selected based on preferences that are only available at run time.

arXiv commentAccepted to ICLR 2021

References in corpus (20)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• An Overview of Multi-Task Learning in Deep Neural Networks
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• A Survey on Multi-Task Learning
• Gabor Convolutional Networks
• Multi-Task Learning as Multi-Objective Optimization
• MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
• Predictive Entropy Search for Multi-objective Bayesian Optimization
• Monocular Depth Estimation: A Survey
• Stochastic Hyperparameter Optimization through Hypernetworks
• Penalizing Unfairness in Binary Classification
• Hypernetwork functional image representation
• Minimax Pareto Fairness: A Multi Objective Perspective
• Pareto Multi-Task Learning
• Personalized Federated Learning using Hypernetworks
• Efficient Continuous Pareto Exploration in Multi-Task Learning
• Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions
• Hyper-Graph-Network Decoders for Block Codes
• Controllable Pareto Multi-Task Learning
• Auxiliary Learning by Implicit Differentiation

Cited by in corpus (8)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Controllable Multi-Objective Re-ranking with Policy Hypernetworks
• Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
• HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials
• Pareto-optimal clustering with the primal deterministic information bottleneck
• Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
• Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training
• Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set