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% 🎉)
How balance violations impact the learned distribution, motivating an weighted balance loss to improve training. For graph distributions, there are scenarios where balance is unattainable, and richer embeddings of children’s states is needed enhance expressiveness. To measure of distributional correctness in GFN we introduce a provable correct novel assessment metric.