mlsanityData to 7 Oct 2026

Improving Pareto Front Learning via Multi-Sample Hypernetworks

arXiv 2212.01130 ↗First posted 2 Dec 2022cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to the inherent trade-off between conflicting objectives, PFL offers a flexible approach in many scenarios in which the decision makers can not specify the preference of one Pareto solution over another, and must switch between them depending on the situation. However, existing PFL methods ignore the relationship between the solutions during the optimization process, which hinders the quality of the obtained front. To overcome this issue, we propose a novel PFL framework namely PHN-HVI, which employs a hypernetwork to generate multiple solutions from a set of diverse trade-off preferences and enhance the quality of the Pareto front by maximizing the Hypervolume indicator defined by these solutions. The experimental results on several MOO machine learning tasks show that the proposed framework significantly outperforms the baselines in producing the trade-off Pareto front.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 2 Dec 2022.

Builds on

18 of 41 references.

References · 18

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  3. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  4. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  5. 2016HyperNetworkscited by 1,003
  6. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  7. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  8. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  9. 2019Pareto Multi-Task Learningcited by 224
  10. 2020Learning the Pareto Front with Hypernetworkscited by 122
  11. 2020Efficient Continuous Pareto Exploration in Multi-Task Learningcited by 57
  12. 2020Controllable Pareto Multi-Task Learningcited by 51
6 more
  1. 2021Scalable Pareto Front Approximation for Deep Multi-Objective Learningcited by 45
  2. 2019Multi-Gradient Descent for Multi-Objective Recommender Systemscited by 20
  3. 2021Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximizationcited by 16
  4. 2018Rank and Rate: Multi-task Learning for Recommender Systemscited by 12
  5. 2020A Monotonic Optimization Approach for Solving Strictly Quasiconvex Multiobjective Programming Problemscited by 4
  6. 2020Multi-objective Optimization by Uncrowded Hypervolume Gradient Ascentcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 10; 2025: 2.

16 papers.

Sort:

By area:

  1. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  2. 2025Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyondcited by 15
  3. 2024Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferencescited by 13
  4. 2024A Survey of Controllable Learning: Methods and Applications in Information Retrievalcited by 12
  5. 2024Efficient Pareto Manifold Learning with Low-Rank Structurecited by 9
  6. 2024COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Frameworkcited by 5
  7. 2023Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flowcited by 3
  8. 2024A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraintscited by 3
  9. 2024Pareto Front Approximation for Multi-Objective Session-Based Recommender Systemscited by 3
  10. 2024Collaborative Pareto Set Learning in Multiple Multi-Objective Optimization Problemscited by 1
  11. 2024Data-Driven Preference Sampling for Pareto Front Learningcited by 1
  12. 2024The Fairness-Quality Trade-off in Clusteringcited by 1
4 more
  1. 2023An approach to extract information from academic transcripts of HUSTcited by 0
  2. 2023Multiobjective Logistics Optimization for Automated ATM Cash Replenishment Processcited by 0
  3. 2024Multi-objective Differentiable Neural Architecture Searchcited by 0
  4. 2025A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworkscited by 0