Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Interpretations of Domain Adaptations via Layer Variational Analysis

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

MH1-2-3-4 #160

Keywords: [ knowledge transfer ] [ transfer learning ] [ deep learning theory ] [ variational analysis ] [ domain adaptation ] [ Theory ]


Abstract:

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.

Chat is not available.