Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer

Eric Eaton, Marie desJardins, Terran LaneECML/PKDD 2008 · OpenReview

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.
BibTeX
@inproceedings{eaton2008modeling,
  author = {Eric Eaton and Marie desJardins and Terran Lane},
  title = {{Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer}},
  booktitle = {ECML/PKDD},
  year = {2008},
  url = {https://openreview.net/forum?id=2UNZTVagpl},
}

Loading related content...

Figure