ML Anthology

Label Space Driven Heterogeneous Transfer Learning with Web Induced Alignment

Sanatan Sukhija
AAAI 2018 pp. 8165-8166
doi:10.1609/AAAI.V32I1.12166 /aaai/2018/sukhija2018aaai-label/

Abstract

Heterogeneous Transfer Learning (HTL) algorithms leverage knowledge from a heterogeneous source domain to perform a task in a target domain. We present a novel HTL algorithm that works even where there are no shared features, instance correspondences and further, the two domains do not have identical labels. We utilize the label relationships via web-distance to align the data of the domains in the projected space, while preserving the structure of the original data.

PDF AAAI Semantic Scholar

Cite

Text

Sukhija. "Label Space Driven Heterogeneous Transfer Learning with Web Induced Alignment." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12166

Markdown

[Sukhija. "Label Space Driven Heterogeneous Transfer Learning with Web Induced Alignment." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/sukhija2018aaai-label/) doi:10.1609/AAAI.V32I1.12166

BibTeX

@inproceedings{sukhija2018aaai-label,
  title     = {{Label Space Driven Heterogeneous Transfer Learning with Web Induced Alignment}},
  author    = {Sukhija, Sanatan},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8165-8166},
  doi       = {10.1609/AAAI.V32I1.12166},
  url       = {https://mlanthology.org/aaai/2018/sukhija2018aaai-label/}
}