A Survey of Historical Learning: Learning Models with Learning History
It addresses the problem of enhancing deep learning model training by utilizing historical data, providing a foundational resource for researchers, but it is incremental as it surveys existing work rather than introducing new methods.
This survey systematically reviews and summarizes methodologies that leverage training history to improve deep neural network learning, categorizing approaches by historical type, functional part, and storage form, and it is the first comprehensive survey on this topic.
New knowledge originates from the old. The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models. In this survey, we comprehensively review and summarize the topic--``Historical Learning: Learning Models with Learning History'', which learns better neural models with the help of their learning history during its optimization, from three detailed aspects: Historical Type (what), Functional Part (where) and Storage Form (how). To our best knowledge, it is the first survey that systematically studies the methodologies which make use of various historical statistics when training deep neural networks. The discussions with related topics like recurrent/memory networks, ensemble learning, and reinforcement learning are demonstrated. We also expose future challenges of this topic and encourage the community to pay attention to the think of historical learning principles when designing algorithms. The paper list related to historical learning is available at \url{https://github.com/Martinser/Awesome-Historical-Learning.}