arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.01798cs.LG
收藏

领域自适应的层变分分析解释

Interpretations of Domain Adaptations via Layer Variational Analysis

Research Center for Information Technology Innovation, Academia Sinica(中央研究院资讯科技创新研究中心)

Huan-Hsin Tseng, Hsin-Yi Lin, Kuo-Hsuan Hung, Yu Tsao

AI总结:

本研究通过层变分分析建立迁移学习理论,证明数据条件下迁移成功,并提出替代方法,在领域自适应中优于梯度下降,尤其适用于稀疏数据场景。

摘要:

迁移学习在许多应用中已被经验证明能高效执行,但有限文献报道了其背后的机制。本研究建立了形式化推导和启发式分析,以构建深度学习中迁移学习的理论。我们利用层变分分析的框架证明,在相应的数据条件下,迁移学习的成功可以得到保证。此外,我们的理论计算为知识迁移过程提供了直观的解释。随后,我们推导出一种基于网络的迁移学习的替代方法。该方法在领域自适应中显示出效率和准确性的提高。当新领域数据在自适应过程中足够稀疏时,该方法尤其有利。跨多种任务的数值实验验证了我们的理论,并证实我们的解析表达式在领域自适应中比梯度下降方法取得了更好的性能。

英文摘要:

Transfer learning is known to perform efficiently in many applications empirically, yet limited literature reports the mechanism behind the scene. This study establishes both formal derivations and heuristic analysis to formulate the theory of transfer learning in deep learning. Our framework utilizing layer variational analysis proves that the success of transfer learning can be guaranteed with corresponding data conditions. Moreover, our theoretical calculation yields intuitive interpretations towards the knowledge transfer process. Subsequently, an alternative method for network-based transfer learning is derived. The method shows an increase in efficiency and accuracy for domain adaptation. It is particularly advantageous when new domain data is sufficiently sparse during adaptation. Numerical experiments over diverse tasks validated our theory and verified that our analytic expression achieved better performance in domain adaptation than the gradient descent method.

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。

↑