Learning a sequence of tasks without access to i.i.d. observations is a widely studied form of continual learning (CL) that remains challenging. In principle, Bayesian learning directly applies to this setting, since recursive and one-off Bayesian updates yield the same result. In practice, however, recursive updating often leads to poor trade-off solutions across tasks because approximate inference is necessary for most models of interest. Here, we describe an alternative Bayesian approach where task-conditioned parameter distributions are continually inferred from data. We offer a practical deep learning implementation of our framework based on probabilistic task-conditioned hypernetworks, an approach we term "posterior meta-replay". Experiments on standard benchmarks show that our probabilistic hypernetworks compress sequences of posterior parameter distributions with virtually no forgetting. We obtain considerable performance gains compared to existing Bayesian CL methods, and identify task inference as our major limiting factor. This limitation has several causes that are independent of the considered sequential setting, opening up new avenues for progress in CL.
翻译:在原则上,贝叶斯学习直接适用于这一环境,因为循环和一次性的贝叶斯更新产生同样的结果。但在实践上,循环更新往往导致不同任务之间的权衡不善,因为对于大多数感兴趣的模式来说,大致推论是必要的。这里,我们描述了一种替代的巴伊西亚方法,根据任务条件参数分布不断从数据中推断出。我们提供了一种实际的深层次学习执行我们框架的方法,其基础是概率性任务条件超强的网络,我们称之为“超前元重现”的方法。对标准基准的实验表明,我们概率性超网络的后生参数分布序列几乎不会忘记。我们与现有的巴伊西亚CL方法相比取得了相当大的绩效收益,并将任务推论作为我们的主要限制因素。这一限制有几个原因与考虑的顺序设置无关,为CL的进展开辟了新的途径。