# Investigating Generalization Behaviours of Generative Flow Networks

arXiv: https://arxiv.org/abs/2402.05309 · HTML: https://mlsanity.com/paper/2402.05309/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 7 Feb 2024.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [GFlowNet Foundations](https://mlsanity.com/paper/2111.09266/) (2021)
- [Trajectory balance: Improved credit assignment in GFlowNets](https://mlsanity.com/paper/2201.13259/) (2022)
- [DeeperGCN: All You Need to Train Deeper GCNs](https://mlsanity.com/paper/2006.07739/) (2020)
- [Biological Sequence Design with GFlowNets](https://mlsanity.com/paper/2203.04115/) (2022)
- [Bayesian Structure Learning with Generative Flow Networks](https://mlsanity.com/paper/2202.13903/) (2022)
- [Generalization in Deep Learning](https://mlsanity.com/paper/1710.05468/) (2017)
- [Assessing Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1810.12282/) (2018)
- [Learning GFlowNets from partial episodes for improved convergence and stability](https://mlsanity.com/paper/2209.12782/) (2022)
- [Generative Flow Networks for Discrete Probabilistic Modeling](https://mlsanity.com/paper/2202.01361/) (2022)
- [Multi-Objective GFlowNets](https://mlsanity.com/paper/2210.12765/) (2022)
- [A theory of continuous generative flow networks](https://mlsanity.com/paper/2301.12594/) (2023)
- [On the number of response regions of deep feed forward networks with piece-wise linear activations](https://mlsanity.com/paper/1312.6098/) (2013)
- [A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning](https://mlsanity.com/paper/1806.07937/) (2018)
- [Better Training of GFlowNets with Local Credit and Incomplete Trajectories](https://mlsanity.com/paper/2302.01687/) (2023)
- [Towards Understanding and Improving GFlowNet Training](https://mlsanity.com/paper/2305.07170/) (2023)
- [Generative Flow Networks as Entropy-Regularized RL](https://mlsanity.com/paper/2310.12934/) (2023)
- [Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network](https://mlsanity.com/paper/2305.19366/) (2023)
- [Interference and Generalization in Temporal Difference Learning](https://mlsanity.com/paper/2003.06350/) (2020)
- [Thompson sampling for improved exploration in GFlowNets](https://mlsanity.com/paper/2306.17693/) (2023)
- [Maximum entropy GFlowNets with soft Q-learning](https://mlsanity.com/paper/2312.14331/) (2023)

## Built on by (most cited first, 6 of 6)

- [A Complexity-Based Theory of Compositionality](https://mlsanity.com/paper/2410.14817/) (2024)
- [Adaptive Destruction Processes for Diffusion Samplers](https://mlsanity.com/paper/2506.01541/) (2025)
- [Evaluating GFlowNet from partial episodes for stable and flexible policy-based training](https://mlsanity.com/paper/2603.01047/) (2026)
- [Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training](https://mlsanity.com/paper/2505.20110/) (2025)
- [Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets](https://mlsanity.com/paper/2602.10583/) (2026)
- [Path-dependent Discrete Amortized Inference](https://mlsanity.com/paper/2608.08644/) (2026)

## Abstract (arXiv)

Generative Flow Networks (GFlowNets, GFNs) are a generative framework for learning unnormalized probability mass functions over discrete spaces. Since their inception, GFlowNets have proven to be useful for learning generative models in applications where the majority of the discrete space is unvisited during training. This has inspired some to hypothesize that GFlowNets, when paired with deep neural networks (DNNs), have favorable generalization properties. In this work, we empirically verify some of the hypothesized mechanisms of generalization of GFlowNets. We accomplish this by introducing a novel graph-based benchmark environment where reward difficulty can be easily varied, p(x) can be computed exactly, and an unseen test set can be constructed to quantify generalization performance. Using this graph-based environment, we are able to systematically test the hypothesized mechanisms of generalization of GFlowNets and put forth a set of empirical observations that summarize our findings. In particular, we find (and confirm) that the functions that GFlowNets learn to approximate have an implicit underlying structure which facilitate generalization. Surprisingly -- and somewhat contradictory to existing knowledge -- we also find that GFlowNets are sensitive to being trained offline and off-policy. However, the reward implicitly learned by GFlowNets is robust to changes in the training distribution.