mlsanityData to 7 Oct 2026

Multi-Objective GFlowNets

arXiv 2210.12765 ↗First posted 23 Oct 2022cs.LG stat.MLcited by 100

Not on the map. Why?

Abstract (arXiv)

We study the problem of generating diverse candidates in the context of Multi-Objective Optimization. In many applications of machine learning such as drug discovery and material design, the goal is to generate candidates which simultaneously optimize a set of potentially conflicting objectives. Moreover, these objectives are often imperfect evaluations of some underlying property of interest, making it important to generate diverse candidates to have multiple options for expensive downstream evaluations. We propose Multi-Objective GFlowNets (MOGFNs), a novel method for generating diverse Pareto optimal solutions, based on GFlowNets. We introduce two variants of MOGFNs: MOGFN-PC, which models a family of independent sub-problems defined by a scalarization function, with reward-conditional GFlowNets, and MOGFN-AL, which solves a sequence of sub-problems defined by an acquisition function in an active learning loop. Our experiments on wide variety of synthetic and benchmark tasks demonstrate advantages of the proposed methods in terms of the Pareto performance and importantly, improved candidate diversity, which is the main contribution of this work.

Key facts. Cited by 100 papers in the map (data through 7 Oct 2026). Builds on 33 of its 80 references that are in the map. First posted on arXiv 23 Oct 2022.

Builds on

33 of 80 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  4. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  5. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  6. 2019Graph Transformer Networkscited by 520
  7. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  8. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  9. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 240
  10. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 229
  11. 2020pymoo: Multi-objective Optimization in Pythoncited by 196
  12. 2020Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimizationcited by 176
21 more
  1. 2022Biological Sequence Design with GFlowNetscited by 172
  2. 2019A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptationcited by 166
  3. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  4. 2021Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvementcited by 115
  5. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  6. 2022Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoderscited by 99
  7. 2018A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizationscited by 98
  8. 2021Multi-Objective Bayesian Optimization over High-Dimensional Search Spacescited by 87
  9. 2020Max-value Entropy Search for Multi-Objective Bayesian Optimization with Constraintscited by 81
  10. 2020Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimizationcited by 60
  11. 2022Pareto Set Learning for Neural Multi-objective Combinatorial Optimizationcited by 56
  12. 2020A Distributional View on Multi-Objective Policy Optimizationcited by 51
  13. 2020Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structurescited by 44
  14. 2022Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomescited by 41
  15. 2021Bayesian Optimization with High-Dimensional Outputscited by 32
  16. 2022Discovering Many Diverse Solutions with Bayesian Optimizationcited by 29
  17. 2021Conditioning Sparse Variational Gaussian Processes for Online Decision-makingcited by 23
  18. 2022Pareto Conditioned Networkscited by 22
  19. 2019Multi-objective Bayesian optimisation with preferences over objectivescited by 16
  20. 2019Discrete Object Generation with Reversible Inductive Constructioncited by 16
  21. 2021Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantizationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 20; 2024: 44; 2025: 24; 2026: 12.

100 papers.

Sort:

By area:

  1. 2023Protein Design with Guided Discrete Diffusioncited by 154
  2. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 83
  3. 2024Panacea: Pareto Alignment via Preference Adaptation for LLMscited by 78
  4. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  5. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  6. 2024Smooth Tchebycheff Scalarization for Multi-Objective Optimizationcited by 50
  7. 2023Sample-efficient Multi-objective Molecular Optimization with GFlowNetscited by 48
  8. 2023Local Search GFlowNetscited by 45
  9. 2023GFlowNet-EM for learning compositional latent variable modelscited by 40
  10. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  11. 2024Discrete Probabilistic Inference as Control in Multi-path Environmentscited by 40
  12. 2025FlowRL: Matching Reward Distributions for LLM Reasoningcited by 38
38 more
  1. 2023Stochastic Generative Flow Networkscited by 32
  2. 2023Thompson sampling for improved exploration in GFlowNetscited by 31
  3. 2023Maximum entropy GFlowNets with soft Q-learningcited by 30
  4. 2023Distributional GFlowNets with Quantile Flowscited by 28
  5. 2024Improving GFlowNets for Text-to-Image Diffusion Alignmentcited by 27
  6. 2023Compositional Sculpting of Iterative Generative Processescited by 26
  7. 2023Learning to Scale Logits for Temperature-Conditional GFlowNetscited by 26
  8. 2024SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraintscited by 26
  9. 2024MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximationcited by 20
  10. 2024Generative Flows on Synthetic Pathway for Drug Designcited by 20
  11. 2024QGFN: Controllable Greediness with Action Valuescited by 18
  12. 2025Pareto Set Learning for Multi-Objective Reinforcement Learningcited by 18
  13. 2023Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Designcited by 17
  14. 2024ParetoFlow: Guided Flows in Multi-Objective Optimizationcited by 17
  15. 2025DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flowscited by 17
  16. 2023Pre-Training and Fine-Tuning Generative Flow Networkscited by 16
  17. 2023Multi-Fidelity Active Learning with GFlowNetscited by 15
  18. 2024Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimizationcited by 15
  19. 2024PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generationcited by 15
  20. 2025Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyondcited by 15
  21. 2024Offline Multi-Objective Optimizationcited by 14
  22. 2025Generative Models in Decision Making: A Surveycited by 14
  23. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 14
  24. 2023Order-Preserving GFlowNetscited by 13
  25. 2024Pessimistic Backward Policy for GFlowNetscited by 13
  26. 2024Pareto Front-Diverse Batch Multi-Objective Bayesian Optimizationcited by 13
  27. 2024Improved Off-policy Reinforcement Learning in Biological Sequence Designcited by 13
  28. 2025TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusioncited by 13
  29. 2024Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximizationcited by 12
  30. 2024RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNetscited by 10
  31. 2024Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networkscited by 9
  32. 2023Molecule Design by Latent Prompt Transformercited by 8
  33. 2024Baking Symmetry into GFlowNetscited by 7
  34. 2024ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learningcited by 7
  35. 2024GFlowNet Fine-tuning for Diverse Correct Solutions in Mathematical Reasoning Taskscited by 7
  36. 2024Investigating Generalization Behaviours of Generative Flow Networkscited by 6
  37. 2024MetaGFN: Exploring Distant Modes with Adapted Metadynamics for Continuous GFlowNetscited by 6
  38. 2024Multi-objective Deep Learning: Taxonomy and Survey of the State of the Artcited by 6

50 most cited of 100 All 100 (JSON)