具有可塑性二值贝叶斯神经网络的主动持续学习
Active Continual Learning with Metaplastic Binary Bayesian Neural Networks
AI总结：
针对边缘系统持续学习中的后验饱和与可塑性冻结问题，提出基于有界记忆变分目标的BiMU方法，通过不确定性依赖步长和先验松弛维持非退化后验，实现无缓冲主动查询，在Permuted-MNIST和OpenLORIS-Object上显著减少标签与更新次数。
摘要：
始终在线的边缘系统必须在严格的计算预算下随着条件变化持续学习，并检测不可靠的预测。贝叶斯二值神经网络在此场景中具有吸引力，但均值场伯努利后验可能在长非平稳流上饱和，消除认知不确定性并冻结可塑性。我们提出BiMU，它源于一个有界记忆变分目标，平衡了稳定性、可塑性和遗忘。BiMU结合了数据项与受控松弛向先验，以及不确定性依赖的步长，防止饱和并维持信息性不确定性。这种非退化后验通过蒙特卡洛分歧实现完全在线、无缓冲的主动查询，在类别不平衡下减少标签查询和反向传播更新。BiMU在1000任务Permuted-MNIST上维持学习和强OOD检测，在OpenLORIS-Object上在类别不平衡和特征压缩下，以匹配的准确率实现高达32倍的标签/更新节省。
英文摘要：
Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic uncertainty and freezing plasticity. We propose BiMU, derived from a bounded-memory variational objective that balances stability, plasticity, and forgetting. BiMU combines a data term with controlled relaxation toward the prior and an uncertainty-dependent step size that prevents saturation and sustains informative uncertainty. This non-degenerate posterior enables fully online, buffer-free active querying via Monte Carlo disagreement, reducing label queries and backpropagation updates under imbalance. BiMU sustains learning and strong OOD detection on 1000-tasks Permuted-MNIST, and on OpenLORIS-Object achieves up to 32$\times$ label/update savings at matched accuracy under class imbalance and feature compression.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
