DGFN: Double Generative Flow Networks
This is an incremental improvement for drug discovery applications.
The paper tackled the problem of limited exploration in generative flow networks for drug discovery by introducing double GFlowNets (DGFNs), which enhanced exploration in sparse reward domains and high-dimensional state spaces.
Deep learning is emerging as an effective tool in drug discovery, with potential applications in both predictive and generative models. Generative Flow Networks (GFlowNets/GFNs) are a recently introduced method recognized for the ability to generate diverse candidates, in particular in small molecule generation tasks. In this work, we introduce double GFlowNets (DGFNs). Drawing inspiration from reinforcement learning and Double Deep Q-Learning, we introduce a target network used to sample trajectories, while updating the main network with these sampled trajectories. Empirical results confirm that DGFNs effectively enhance exploration in sparse reward domains and high-dimensional state spaces, both challenging aspects of de-novo design in drug discovery.