Quantum Continual Learning Overcoming Catastrophic Forgetting  

作　　者：Wenjie Jiang Zhide Lu Dong-Ling Deng 蒋文杰;鲁智徳;邓东灵(Center for Quantum Information,IIIS,Tsinghua University,Beijing 100084,China;Shanghai Qi Zhi Institute,Shanghai 200232,China)

机构地区：[1]Center for Quantum Information,IIIS,Tsinghua University,Beijing 100084,China [2]Shanghai Qi Zhi Institute,Shanghai 200232,China

出　　处：《Chinese Physics Letters》2022年第5期16-22,共7页中国物理快报（英文版）

基　　金：supported by the Start-Up Fund from Tsinghua University(Grant No.53330300320);the National Natural Science Foundation of China(Grant No.12075128);the Shanghai Qi Zhi Institute。

摘　　要：Catastrophic forgetting describes the fact that machine learning models will likely forget the knowledge of previously learned tasks after the learning process of a new one.It is a vital problem in the continual learning scenario and recently has attracted tremendous concern across different communities.We explore the catastrophic forgetting phenomena in the context of quantum machine learning.It is found that,similar to those classical learning models based on neural networks,quantum learning systems likewise suffer from such forgetting problem in classification tasks emerging from various application scenes.We show that based on the local geometrical information in the loss function landscape of the trained model,a uniform strategy can be adapted to overcome the forgetting problem in the incremental learning setting.Our results uncover the catastrophic forgetting phenomena in quantum machine learning and offer a practical method to overcome this problem,which opens a new avenue for exploring potential quantum advantages towards continual learning.

关 键 词：OVERCOME GETTING LIKELY 

分 类 号：O413[理学—理论物理] TP181[理学—物理]