When do GFlowNets Learn the Right Distribution?
Analysis of the limitations and stability of GFlowNets under balance violations, showing how these affect accuracy. We introduce a novel metric for assessing correctness, improving evaluation beyond existing protocols.
ICLR 2025 (Spotlight, ~top 5% 🎉)
Abstract
Generative Flow Networks (GFlowNets) are an emerging class of sampling methods for distributions over discrete and compositional objects, e.g., graphs. In spite of their remarkable success in problems such as drug discovery and phylogenetic inference, the question of when and whether GFlowNets learn to sample from the target distribution remains underexplored. To tackle this issue, we first assess the extent to which a violation of the detailed balance of the underlying flow network might hamper the correctness of GFlowNet’s sampling distribution. In particular, we demonstrate that the impact of an imbalanced edge on the model’s accuracy is influenced by the total amount of flow passing through it and, as a consequence, is unevenly distributed across the network. We also argue that, depending on the parameterization, imbalance may be inevitable. In this regard, we consider the problem of sampling from distributions over graphs with GFlowNets parameterized by graph neural networks (GNNs) and show that the representation limits of GNNs delineate which distributions these GFlowNets can approximate. Lastly, we address these limitations by proposing a theoretically sound and computationally tractable metric for assessing GFlowNets, experimentally showing it is a better proxy for correctness than popular evaluation protocols.
Publication
- Tiago da Silva, Rodrigo Barreto Alves, Eliezer de Souza da Silva, Amauri H Souza, Vikas Garg, Samuel Kaski, Diego Mesquita. When do GFlowNets Learn the Right Distribution? The Thirteenth International Conference on Learning Representations (ICLR 2025).
Links
Extras Bibtex