Knowledge transfer: what, how, and why

• Main Author: Chin, Si-Chi
• Other Authors: Street, W. Nick
• Format: Others
• Language: English
• Published: University of Iowa 2013
• Subjects: Bioinformatics
• Online Access: https://ir.uiowa.edu/etd/2456; https://ir.uiowa.edu/cgi/viewcontent.cgi?article=4584&context=etd

People learn from prior experiences. We first learn how to use a spoon and then know how to use a different size of spoon. We first learn how to sew and then learn how to embroider. Transferring knowledge from one situation to another related situation often increases the speed of learning. This observation is relevant to human learning, as well as machine learning. This thesis focuses on the problem of knowledge transfer -- an area of study in machine learning. The goal of knowledge transfer is to train a system to recognize and apply knowledge acquired from previous tasks to new tasks or new domains. An effective knowledge transfer system facilitates learning processes for novel tasks, where little information is available. For example, the ability to transfer knowledge from a model that identifies writers born in the U.S. to identify writers born in Kiribati, a much lesser known country, would increase the speed of learning to identify writers born in Kiribati from scratch. In this thesis, we investigate three dimensions of knowledge transfer: what, how, and why. We present and elaborate on these questions: What type of knowledge to transfer? How to transfer knowledge across entities? Why a certain pattern of knowledge transfer is observed? We first propose Segmented Transfer -- a novel knowledge transfer model -- to identify and learn from the most informative partitions from prior tasks. The proposed model is applied to Wikipedia vandalism detection problem and to entity search and retrieval problem and improves the predictions. Based on the foundation of knowledge transfer and network theory, we propose Knowledge Transfer Network (KTN), a novel type of network describing transfer learning relationships among problems. KTN is not only a knowledge representation, but also a framework to select an effective and efficient ensemble of learners to improve a predictive model. This novel type of network provides insights on identifying ontological connections that were initially obscured. For example, we may observe knowledge transfer occurs among dissimilar tasks, such as transferring from using a knife and fork to using chopsticks.