Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer

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.

Cite

Text

Eaton et al. "Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2008. doi:10.1007/978-3-540-87479-9_39

Markdown

[Eaton et al. "Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2008.](https://mlanthology.org/ecmlpkdd/2008/eaton2008ecmlpkdd-modeling/) doi:10.1007/978-3-540-87479-9_39

BibTeX

@inproceedings{eaton2008ecmlpkdd-modeling,
  title     = {{Modeling Transfer Relationships Between Learning Tasks for Improved Inductive Transfer}},
  author    = {Eaton, Eric and desJardins, Marie and Lane, Terran},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2008},
  pages     = {317-332},
  doi       = {10.1007/978-3-540-87479-9_39},
  url       = {https://mlanthology.org/ecmlpkdd/2008/eaton2008ecmlpkdd-modeling/}
}