4 papers
Efficient Meta-Learning for Continual Learning with Taylor Expansion Approximation
Xiaohan Zou, Tong Lin
Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown…
Principal Gradient Direction and Confidence Reservoir Sampling for Continual Learning
Zhiyi Chen, Tong Lin
Task-free online continual learning aims to alleviate catastrophic forgetting of the learner on a non-iid data stream. Experience Replay (ER) is a SOTA continual learning method, w…
A New Adaptive Gradient Method with Gradient Decomposition
Zhou Shao, Tong Lin
Adaptive gradient methods, especially Adam-type methods (such as Adam, AMSGrad, and AdaBound), have been proposed to speed up the training process with an element-wise scaling term…
Intra-Model Collaborative Learning of Neural Networks
Shijie Fang, Tong Lin
Recently, collaborative learning proposed by Song and Chai has achieved remarkable improvements in image classification tasks by simultaneously training multiple classifier heads.…