Learning to Learn and Remember Super Long Multi-Domain Task Sequence
Learning to Learn and Remember Super Long Multi-Domain Task Sequence
复制标题
DOI：
10.1109/cvpr52688.2022.00782
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Zhenyi Wang;Li Shen;Tiehang Duan;Donglin Zhan;Le Fang;Mingchen Gao
中科院分区：
文献类型：
--
作者：
Zhenyi Wang;Li Shen;Tiehang Duan;Donglin Zhan;Le Fang;Mingchen Gao
灾难性遗忘（CF）经常发生在非平稳数据分布的学习。CF问题仍然几乎未被探索，并且当在一系列域（数据集）上进行元学习时更具挑战性，称为顺序域元学习（SDML）。在这项工作中，我们提出了一个简单而有效的学习方法，即，Meta优化器，以缓解SDML中的CF问题。我们首先将所提出的Meta优化器应用于SDML的简化设置，域感知元学习，其中域标签和边界在学习过程中是已知的。我们建议动态冻结网络，并通过在Meta训练期间考虑域性质将其与建议的Meta优化器相结合。此外，我们将Meta优化器扩展到更通用的SDML设置，域不可知元学习，其中域标签和边界在学习过程中是未知的。我们提出了一种域偏移检测技术来捕获潜在的域更改，并为Meta优化器配备它以在此设置中工作。所提出的Meta优化器是通用的，可以很容易地与现有的几个元学习算法集成。最后，我们构建了一个具有挑战性的大规模基准测试，该基准测试由10个异构域组成，具有由10万个任务组成的超长任务序列。我们对这两种设置的基准进行了广泛的实验，并证明了我们所提出的方法的有效性，大大优于当前的强基线。
Catastrophic forgetting (CF) frequently occurs when learning with non-stationary data distribution. The CF issue remains nearly unexplored and is more challenging when meta-learning on a sequence of domains (datasets), called sequential domain meta-learning (SDML). In this work, we propose a simple yet effective learning to learn approach, i.e., meta optimizer, to mitigate the CF problem in SDML. We first apply the proposed meta optimizer to the simplified setting of SDML, domain-aware meta-learning, where the domain labels and boundaries are known during the learning process. We propose dynamically freezing the network and incorporating it with the proposed meta optimizer by considering the domain nature during meta training. In addition, we extend the meta optimizer to the more general setting of SDML, domain-agnostic meta-learning, where domain labels and boundaries are unknown during the learning process. We propose a domain shift detection technique to capture latent domain change and equip the meta optimizer with it to work in this setting. The proposed meta optimizer is versatile and can be easily integrated with several existing meta-learning algorithms. Finally, we construct a challenging and large-scale benchmark consisting of 10 heterogeneous domains with a super long task sequence consisting of 100K tasks. We perform extensive experiments on the proposed benchmark for both settings and demonstrate the effectiveness of our proposed method, outperforming current strong baselines by a large margin.