arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.06418cs.LGcs.AI
收藏

通过知识重构实现终身生成性学习

Lifelong Generative Learning via Knowledge Reconstruction

Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学)

Libo Huang, Zhulin An, Xiang Zhi, Yongjun Xu

摘要:

当生成模型用于顺序学习多个任务时,通常会引发灾难性遗忘问题,即,终身生成学习虽然有一些努力来解决这个问题,他们遭受高的时间消耗或错误积累。在这项工作中,我们开发了一个高效和有效的终身生成模型的基础上变分自编码器(VAE)。与生成对抗网络不同,VAE在训练过程中具有很高的效率,可以用很少的资源提供自然的好处。我们将VAE的内在重构性扩展到历史知识的保持上,推导出一个终身生成模型。此外,我们设计了一个反馈策略的重建数据,以减轻错误的积累。对MNIST、FashionMNIST和SVHN的终身生成任务的实验验证了我们方法的有效性,其结果与SOTA相当。

英文摘要:

Generative models often incur the catastrophic forgetting problem when they are used to sequentially learning multiple tasks, i.e., lifelong generative learning. Although there are some endeavors to tackle this problem, they suffer from high time-consumptions or error accumulation. In this work, we develop an efficient and effective lifelong generative model based on variational autoencoder (VAE). Unlike the generative adversarial network, VAE enjoys high efficiency in the training process, providing natural benefits with few resources. We deduce a lifelong generative model by expending the intrinsic reconstruction character of VAE to the historical knowledge retention. Further, we devise a feedback strategy about the reconstructed data to alleviate the error accumulation. Experiments on the lifelong generating tasks of MNIST, FashionMNIST, and SVHN verified the efficacy of our approach, where the results were comparable to SOTA.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑