← Back to all news
arXiv Machine Learning

On the Generation Order in GFlowNets

The paper investigates how the order in which components are generated in GFlowNets affects learning and convergence. It shows that existing GFlowNet algorithms often fail to discover useful generation orders, and introduces a new training recipe—Learning-Order GFlowNet—that learns interpretable orders without explicit annotations. Experiments demonstrate that the new method improves convergence, and analysis of gradient signal-to-noise ratio suggests that higher SNR correlates with faster convergence and better generation orders.

Related stories

arXiv Machine Learning
Aug 31

Trajectory balance: Improved credit assignment in GFlowNets

The paper introduces a new learning objective called trajectory balance for Generative Flow Networks (GFlowNets), aiming to improve credit assignment across long action sequences. It demonstrates that minimizing this objective yields a policy that samples exactly from the target distribution. Experiments on four domains show that trajectory balance enhances convergence, sample diversity, and robustness to long sequences and large action spaces.

By Esmeralda S. Whitammer, Moksh Jain, Emmanuel Bengio, Chen Sun, Yoshua Bengio
diffusion
More like this →
arXiv Machine Learning
Aug 6

Stable GFlowNets with TV Monitoring and Probabilistic Guarantees

arXiv:2605. 01729v2 Announce Type: replace Abstract: Generative Flow Networks (GFlowNets) learn to sample states proportional to an unnormalized reward.

By Zengxiang Lei, Ananth Shreekumar, Jonathan Rosenthal, Ruoyu Song, Alvaro A. Cardenas, Daniel J. Fremont, Dongyan Xu, Satish Ukkusuri, Z. Berkay Celik
More like this →
arXiv AI
Oct 27

Hierarchical Cooperative GFlowNets

Hierarchical Cooperative GFlowNets (HCG) dynamically partition the search space to coordinate multiple GFlowNets, preventing them from collapsing onto the same high‑reward regions. HCG imposes an ordering where the top model explores the full space while lower‑ranked models focus on uncovered areas, using a shared classifier and a normalizer‑weighted aggregation rule to maintain reward‑proportional sampling. Experiments on multimodal distributions, sequence generation, combinatorial optimization, and biological sequence design demonstrate that HCG improves mode coverage and target approximation, enabling broader complementary exploration.

By Pedro Dall'Antonia, Juan Belieni, Ana Carolina Erthal, Saullo H. G. de Oliveira, Eliezer de Souza da Silva, Diego Mesquita
multimodal
More like this →
arXiv AI
Oct 7

Learning a Mixture of GFlowNets

arXiv:2610.07562v1 Announce Type: cross Abstract: Learning an ensemble of GFlowNets to sample from a discrete target distribution has become a common approach for achieving better state space explora...

By Tiago da Silva, Amauri H. Souza, Salem Lahlou
More like this →
arXiv Machine Learning
Sep 1

GFlowNets and variational inference

arXiv:2210.00580v4 Announce Type: replace Abstract: This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to m...

By Esmeralda S. Whitammer, Salem Lahlou, Tristan Deleu, Xu Ji, Edward Hu, Katie Everett, Dinghuai Zhang, Yoshua Bengio
reinforcement-learningmultimodal
More like this →
arXiv AI
Oct 31

DEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems

The paper introduces Diffusion-Enhanced GFlowNet (DEG), a framework that combines Generative Flow Networks with diffusion models to improve vehicle routing problem solutions. DEG uses GFlowNet to generate edge-level signals, perturbs them with diffusion noise, and denoises them to expand flow into high-reward regions, thereby increasing solution diversity. A scalable decoder is added, and experiments on synthetic and real datasets—including up to 10,000-node instances—show DEG outperforms baseline methods.

By Ni Zhang, Zhiqin Zhang, Ling Pan, Hoong Chuin Lau, Zhiguang Cao
diffusion
More like this →