Abstract:We present GFlowState, a visual analytics system designed to illuminate the training process of Generative Flow Networks (GFlowNets or GFNs). GFlowNets are a probabilistic framework for generating samples proportionally to a reward function. While GFlowNets have proved to be powerful tools in applications such as molecule and material discovery, their training dynamics remain difficult to interpret. Standard machine learning tools allow metric tracking but do not reveal how models explore the sample space, construct sample trajectories, or shift sampling probabilities during training. Our solution, GFlowState, allows users to analyze sampling trajectories, compare the sample space relative to reference datasets, and analyze the training dynamics. To this end, we introduce multiple views, including a chart of candidate rankings, a state projection, a node-link diagram of the trajectory network, and a transition heatmap. These visualizations enable GFlowNet developers and users to investigate sampling behavior and policy evolution, and to identify underexplored regions and sources of training failure. Case studies demonstrate how the system supports debugging and assessing the quality of GFlowNets across application domains. By making the structural dynamics of GFlowNets observable, our work enhances their interpretability and can accelerate GFlowNet development in practice.
| Subjects: | Machine Learning (cs.LG); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2604.21830 [cs.LG] |
| (or arXiv:2604.21830v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.21830 arXiv-issued DOI via DataCite (pending registration) |
From: Christina Humer [view email]
[v1]
Thu, 23 Apr 2026 16:22:55 UTC (3,017 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。