VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Randy Ardywibowo;Zepeng Huo;Zhangyang Wang;Bobak J. Mortazavi;Shuai Huang;Xiaoning Qian
中科院分区：
文献类型：
--
作者：
Randy Ardywibowo;Zepeng Huo;Zhangyang Wang;Bobak J. Mortazavi;Shuai Huang;Xiaoning Qian
连续学习（CL）是连续学习预测模型的问题，这些模型具有可能来自不同上下文的不同数据。许多现有的CL方法假设数据流被划分为一系列的上下文，称为任务，明确给定的过渡边界。不幸的是，许多现实世界中的CL场景既没有明确的任务信息，也没有上下文边界，激发了任务不可知的CL的研究。本文提出了一个变分架构生长框架VariGrow。通过将动态增长的神经网络解释为贝叶斯近似，并定义灵活的隐式变分分布，VariGrow通过基于能量的新奇得分来检测新任务是否到达。如果nov-task得分很高，样本被“检测”为新任务，VariGrow将生长一个新的专家模块来负责它。否则，样本将被分配给最“熟悉”它的现有专家之一（即，具有最低新奇分数的一个）以保存所有获得的知识。我们已经在几个CIFAR和基于ImageNet的基准测试中测试了VariGrow，用于严格任务不可知的CL设置，在训练或测试期间没有任何任务信息，这证明了其一贯的上级或竞争性能。更有趣的是，VariGrow实现了与任务感知CL方法相当的性能。
Continual Learning (CL) is the problem of sequentially learning predictive models with varying data that may originate from different contexts. Many existing CL methods assume that the data stream is divided into a sequence of contexts, termed as tasks , with explicitly given transition boundaries. Unfortunately, many real-world CL scenarios have neither explicit task information nor context boundaries, motivating the study of task-agnostic CL. This paper proposes a variational architecture growing framework dubbed VariGrow . By interpreting dynamically growing neural networks as a Bayesian approximation, and defining flexible implicit variational distributions, VariGrow detects if a new task is arriving through an energy-based novelty score . If the nov-elty score is high and the sample is “detected” as a new task, VariGrow will grow a new expert module to be responsible for it. Otherwise, the sample will be assigned to one of the existing experts who is the most “familiar” with it (i.e., one with the lowest novelty score) to preserve all the acquired knowledge. We have tested VariGrow on several CIFAR and ImageNet-based benchmarks for the strictly task-agnostic CL setting without any task information during training or testing, which demonstrates its consistently superior or competitive performance. More interesting, VariGrow achieves comparable performance with task-aware CL methods.