论文标题
信息理论在线记忆选择用于持续学习
Information-theoretic Online Memory Selection for Continual Learning
论文作者
论文摘要
无任务持续学习中的一个挑战性问题是从数据流中的代表性重播内存进行在线选择。在这项工作中，我们从信息理论的角度研究了在线内存选择问题。为了收集最多的信息，我们提出\ textit {survisy}和\ textit {Lelinability}标准，以选择信息的观点并避免异常值。我们提出了一个贝叶斯模型，以通过利用排名一基质矩阵结构来有效地计算标准。我们证明，这些标准鼓励在贪婪的算法中选择信息，以进行在线记忆选择。此外，通过识别\ textit {更新内存的时间的重要性}，我们引入了一个随机信息理论储层采样器（INFORS），该储存器（INFORS）在选择性点之间进行采样，并具有很高的信息。与储层抽样相比，Infors证明了针对数据失衡的鲁棒性提高。最后，对持续学习基准的经验表现表明了其效率和功效。
A challenging problem in task-free continual learning is the online selection of a representative replay memory from data streams. In this work, we investigate the online memory selection problem from an information-theoretic perspective. To gather the most information, we propose the \textit{surprise} and the \textit{learnability} criteria to pick informative points and to avoid outliers. We present a Bayesian model to compute the criteria efficiently by exploiting rank-one matrix structures. We demonstrate that these criteria encourage selecting informative points in a greedy algorithm for online memory selection. Furthermore, by identifying the importance of \textit{the timing to update the memory}, we introduce a stochastic information-theoretic reservoir sampler (InfoRS), which conducts sampling among selective points with high information. Compared to reservoir sampling, InfoRS demonstrates improved robustness against data imbalance. Finally, empirical performances over continual learning benchmarks manifest its efficiency and efficacy.
