Symmetry-Aware GFlowNets
This addresses a specific bottleneck in graph generation for researchers in machine learning and computational chemistry, offering an incremental improvement over existing GFlowNet methods.
The paper tackled systematic biases in Generative Flow Networks (GFlowNets) for graph sampling due to symmetry-related inaccuracies, introducing Symmetry-Aware GFlowNets (SA-GFN) that corrects biases through reward scaling, resulting in unbiased sampling with enhanced diversity and high-reward graphs matching the target distribution.
Generative Flow Networks (GFlowNets) offer a powerful framework for sampling graphs in proportion to their rewards. However, existing approaches suffer from systematic biases due to inaccuracies in state transition probability computations. These biases, rooted in the inherent symmetries of graphs, impact both atom-based and fragment-based generation schemes. To address this challenge, we introduce Symmetry-Aware GFlowNets (SA-GFN), a method that incorporates symmetry corrections into the learning process through reward scaling. By integrating bias correction directly into the reward structure, SA-GFN eliminates the need for explicit state transition computations. Empirical results show that SA-GFN enables unbiased sampling while enhancing diversity and consistently generating high-reward graphs that closely match the target distribution.