Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer

TitleModeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer
Publication TypeBook Chapters
Year of Publication2008
AuthorsEaton E, desJardins M, Lane T
EditorDaelemans W, Goethals B, Morik K
Book TitleMachine Learning and Knowledge Discovery in DatabasesMachine Learning and Knowledge Discovery in Databases
Series TitleLecture Notes in Computer Science
Volume5211
Pagination317 - 332
PublisherSpringer Berlin / Heidelberg
ISBN Number978-3-540-87478-2
Abstract

In this paper, we propose a novel graph-based method for knowledge transfer. We model the transfer relationships between source tasks by embedding the set of learned source models in a graph using transferability as the metric. Transfer to a new problem proceeds by mapping the problem into the graph, then learning a function on this graph that automatically determines the parameters to transfer to the new learning task. This method is analogous to inductive transfer along a manifold that captures the transfer relationships between the tasks. We demonstrate improved transfer performance using this method against existing approaches in several real-world domains.

URLhttp://dx.doi.org/10.1007/978-3-540-87479-9_39