Zhang Zhengchao, Zhou Lianke, Wu Yuyang, Wang Nianbin
College of Computer Science and Technology, Harbin Engineering University, Harbin, Heilongjiang, China.
Modeling and Emulation in E-Government National Engineering Laboratory, Harbin Engineering University, Harbin, Heilongjiang, China.
Front Neurorobot. 2024 Apr 26;18:1391247. doi: 10.3389/fnbot.2024.1391247. eCollection 2024.
The meta-learning methods have been widely used to solve the problem of few-shot learning. Generally, meta-learners are trained on a variety of tasks and then generalized to novel tasks.
However, existing meta-learning methods do not consider the relationship between meta-tasks and novel tasks during the meta-training period, so that initial models of the meta-learner provide less useful meta-knowledge for the novel tasks. This leads to a weak generalization ability on novel tasks. Meanwhile, different initial models contain different meta-knowledge, which leads to certain differences in the learning effect of novel tasks during the meta-testing period. Therefore, this article puts forward a meta-optimization method based on situational meta-task construction and cooperation of multiple initial models. First, during the meta-training period, a method of constructing situational meta-task is proposed, and the selected candidate task sets provide more effective meta-knowledge for novel tasks. Then, during the meta-testing period, an ensemble model method based on meta-optimization is proposed to minimize the loss of inter-model cooperation in prediction, so that multiple models cooperation can realize the learning of novel tasks.
The above-mentioned methods are applied to popular few-shot character datasets and image recognition datasets. Furthermore, the experiment results indicate that the proposed method achieves good effects in few-shot classification tasks.
In future work, we will extend our methods to provide more generalized and useful meta-knowledge to the model during the meta-training period when the novel few-shot tasks are completely invisible.
元学习方法已被广泛用于解决少样本学习问题。一般来说，元学习器在各种任务上进行训练，然后推广到新任务。
然而，现有的元学习方法在元训练期间没有考虑元任务和新任务之间的关系，以至于元学习器的初始模型为新任务提供的有用元知识较少。这导致在新任务上的泛化能力较弱。同时，不同的初始模型包含不同的元知识，这导致在元测试期间新任务的学习效果存在一定差异。因此，本文提出了一种基于情境元任务构建和多个初始模型协作的元优化方法。首先，在元训练期间，提出了一种构建情境元任务的方法，所选的候选任务集为新任务提供了更有效的元知识。然后，在元测试期间，提出了一种基于元优化的集成模型方法，以最小化预测中模型间协作的损失，从而使多个模型协作能够实现新任务的学习。
上述方法应用于流行的少样本字符数据集和图像识别数据集。此外，实验结果表明，所提出的方法在少样本分类任务中取得了良好效果。
在未来的工作中，当全新的少样本任务完全不可见时，我们将扩展我们的方法，以便在元训练期间为模型提供更通用和有用的元知识。
