Adaptation Regularization: A General Framework for Transfer Learning

Domain transfer learning, which learns a target classifier using labeled data from a different distribution, has shown promising value in knowledge discovery yet still been a challenging problem. Most previous works designed adaptive classifiers by exploring two learning strategies independently: di...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on knowledge and data engineering Ročník 26; číslo 5; s. 1076 - 1089
Hlavní autori: Mingsheng Long, Jianmin Wang, Guiguang Ding, Pan, Sinno Jialin, Yu, Philip S.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.05.2014
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Artificial Intelligence
Classifier design and evaluation
Computing Methodologies
Database Applications
Database Management
Design Methodology
Feature extraction
Information Technology and Systems
Joints
Kernel
Knowledge acquisition
Learning
Manifolds
Mining methods and algorithms
Modeling structured
Pattern Recognition
Probability distribution
Risk management
textual and multimedia data
manifold regularization
distribution adaptation
Transfer learning
generalization error
adaptation regularization
ISSN:1041-4347, 1558-2191
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Domain transfer learning, which learns a target classifier using labeled data from a different distribution, has shown promising value in knowledge discovery yet still been a challenging problem. Most previous works designed adaptive classifiers by exploring two learning strategies independently: distribution adaptation and label propagation. In this paper, we propose a novel transfer learning framework, referred to as Adaptation Regularization based Transfer Learning (ARTL), to model them in a unified way based on the structural risk minimization principle and the regularization theory. Specifically, ARTL learns the adaptive classifier by simultaneously optimizing the structural risk functional, the joint distribution matching between domains, and the manifold consistency underlying marginal distribution. Based on the framework, we propose two novel methods using Regularized Least Squares (RLS) and Support Vector Machines (SVMs), respectively, and use the Representer theorem in reproducing kernel Hilbert space to derive corresponding solutions. Comprehensive experiments verify that ARTL can significantly outperform state-of-the-art learning methods on several public text and image datasets.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2013.111