Combating Negative Transfer From Predictive Distribution Differences

• Main Authors: Seah, Chun-Wei, Ong, Yew-Soon, Tsang, Ivor W.
• Other Authors: School of Computer Engineering
• Format: Article
• Language: English
• Published: 2016
• Subjects: Domain adaptation (DA); logistic regression (LR); negative transfer; predictive distribution matching (PDM); support vector machines (SVMs)
• Online Access: https://hdl.handle.net/10356/81712; http://hdl.handle.net/10220/39657
• Institution: Nanyang Technological University

Domain adaptation (DA), which leverages labeled data from related source domains, comes in handy when the label information of the target domain is scarce or unavailable. However, as the source data do not come from the same origin as that of the target domain, the predictive distributions of the so...