We introduce BatchGFN -- a novel approach for pool-based active learning that
uses generative flow networks to sample sets of data points proportional to a
batch reward. With an appropriate reward function to quantify the utility of
acquiring a batch, such as the joint mutual information between the batch and
the model parameters, BatchGFN is able to construct highly informative batches
for active learning in a principled way. We show our approach enables sampling
near-optimal utility batches at inference time with a single forward pass per
point in the batch in toy regression problems. This alleviates the
computational complexity of batch-aware algorithms and removes the need for
greedy approximations to find maximizers for the batch reward. We also present
early results for amortizing training across acquisition steps, which will
enable scaling to real-world tasks.

BatchGFN 使用生成流网络来采样比例为批量奖励的数据点集，可构建高度信息化批次用于主动学习，在玩具回归问题中，通过适当的奖励函数以单次前向通过批次中的每个点，取样接近最优效用批次，最大化批次奖励的贪婪近似已不再需要。同时，我们还提出了跨获取步骤的分摊训练的初步结果，这将使其能够扩展到真实世界的任务。