Multi-Fidelity Active Learning with GFlowNets - 2023

Title : Multi-Fidelity Active Learning with GFlowNets Author(s): Hernandez-Garcia, Alex and Saxena, Nikita and Jain, Moksh and Liu, Cheng-Hao and Bengio, Yoshua Link(s) :

Figure 1 gives overview. GFlowNet outputs an object \(x\) and fidelity \(m\), the surrogate model \(p(f_m(x)|x,m,\mathcal{ D })\) makes predictions, these predictions are given to the acquisition function.