mlsanityData to 7 Oct 2026

Learning to Scale Logits for Temperature-Conditional GFlowNets

arXiv 2310.02823 ↗First posted 4 Oct 2023cs.LG stat.MLcited by 26

Not on the map. Why?

Abstract (arXiv)

GFlowNets are probabilistic models that sequentially generate compositional structures through a stochastic policy. Among GFlowNets, temperature-conditional GFlowNets can introduce temperature-based controllability for exploration and exploitation. We propose textitLogit-scaling GFlowNets (Logit-GFN), a novel architectural design that greatly accelerates the training of temperature-conditional GFlowNets. It is based on the idea that previously proposed approaches introduced numerical challenges in the deep network training, since different temperatures may give rise to very different gradient profiles as well as magnitudes of the policy's logits. We find that the challenge is greatly reduced if a learned function of the temperature is used to scale the policy's logits directly. Also, using Logit-GFN, GFlowNets can be improved by having better generalization capabilities in offline learning and mode discovery capabilities in online learning, which is empirically verified in various biological and chemical tasks. Our code is available at urlhttps://github.com/dbsxodud-11/logit-gfn

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 37 of its 49 references that are in the map. First posted on arXiv 4 Oct 2023.

Builds on

37 of 49 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  6. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  7. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  8. 2016Deep Exploration via Bootstrapped DQNcited by 518
  9. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  10. 2021GFlowNet Foundationscited by 286
  11. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  12. 2022Biological Sequence Design with GFlowNetscited by 172
25 more
  1. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  2. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 129
  3. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  4. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  5. 2022GFlowNets and variational inferencecited by 103
  6. 2022Multi-Objective GFlowNetscited by 100
  7. 2023A theory of continuous generative flow networkscited by 98
  8. 2022Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimizationcited by 96
  9. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 83
  10. 2023Towards Understanding and Improving GFlowNet Trainingcited by 74
  11. 2023Robust Scheduling with GFlowNetscited by 67
  12. 2020AdaLead: A simple and robust adaptive greedy search algorithm for sequence designcited by 63
  13. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  14. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
  15. 2022Generative Augmented Flow Networkscited by 48
  16. 2020Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structurescited by 44
  17. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  18. 2023Stochastic Generative Flow Networkscited by 32
  19. 2023Thompson sampling for improved exploration in GFlowNetscited by 31
  20. 2023Distributional GFlowNets with Quantile Flowscited by 28
  21. 2023Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualizationcited by 25
  22. 2022Unifying Generative Models with GFlowNets and Beyondcited by 24
  23. 2023Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequencescited by 23
  24. 2022Neural Topological Ordering for Computation Graphscited by 12
  25. 2023Delta-AI: Local objectives for amortized inference in sparse graphical modelscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 5; 2026: 5.

26 papers.

Sort:

By area:

  1. 2024Ant Colony Sampling with GFlowNets for Combinatorial Optimizationcited by 53
  2. 2024Improved off-policy training of diffusion samplerscited by 47
  3. 2025FlowRL: Matching Reward Distributions for LLM Reasoningcited by 38
  4. 2024Genetic-guided GFlowNets for Sample Efficient Molecular Optimizationcited by 36
  5. 2024Improving GFlowNets for Text-to-Image Diffusion Alignmentcited by 27
  6. 2024Adaptive teachers for amortized samplerscited by 23
  7. 2024QGFN: Controllable Greediness with Action Valuescited by 18
  8. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 14
  9. 2024Pessimistic Backward Policy for GFlowNetscited by 13
  10. 2024Improved Off-policy Reinforcement Learning in Biological Sequence Designcited by 13
  11. 2024Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplerscited by 10
  12. 2024RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNetscited by 10
14 more
  1. 2024Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networkscited by 9
  2. 2024Entropy Reweighted Conformal Classificationcited by 8
  3. 2024Random Policy Evaluation Uncovers Policies of Generative Flow Networkscited by 5
  4. 2024GFlowNet Training by Policy Gradientscited by 4
  5. 2024Evolution Guided Generative Flow Networkscited by 3
  6. 2025NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimizationcited by 3
  7. 2025Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learningcited by 2
  8. 2025A Generative Neural Annealer for Black-Box Combinatorial Optimizationcited by 1
  9. 2026Evaluating GFlowNet from partial episodes for stable and flexible policy-based trainingcited by 1
  10. 2024Dynamic Backtracking in GFlowNets: Enhancing Decision Steps with Reward-Dependent Adjustment Mechanismscited by 0
  11. 2026Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectivescited by 0
  12. 2026Stable GFlowNets with TV Monitoring and Probabilistic Guaranteescited by 0
  13. 2026Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmarkcited by 0
  14. 2026Path-dependent Discrete Amortized Inferencecited by 0