Evaluation of the Instance Weighting Strategy for Transfer Learning of Educational Predictive Models

Mariia Luzan, Christopher Brooks
Proceedings of the 2024 AAAI Conference on Artificial Intelligence, PMLR 257:19-28, 2024.

Abstract

This work contributes to our understanding of how transfer learning can be used to improve educational predictive models across higher institution units. Specifically, we provide an empirical evaluation of the instance weighting strategy for transfer learning, whereby a model created from a source institution is modified based on the distribution characteristics of the target institution. In this work we demonstrated that this increases overall model goodness-of-fit, increases the goodness-of-fit for each demographic group considered, and reduces disparity between demographic groups when we consider a simulated institutional intervention that can only be deployed to 10% of the student body.

Cite this Paper

BibTeX
@InProceedings{pmlr-v257-luzan24a, title = {Evaluation of the Instance Weighting Strategy for Transfer Learning of Educational Predictive Models}, author = {Luzan, Mariia and Brooks, Christopher}, booktitle = {Proceedings of the 2024 AAAI Conference on Artificial Intelligence}, pages = {19--28}, year = {2024}, editor = {Ananda, Muktha and Malick, Debshila Basu and Burstein, Jill and Liu, Lydia T. and Liu, Zitao and Sharpnack, James and Wang, Zichao and Wang, Serena}, volume = {257}, series = {Proceedings of Machine Learning Research}, month = {26--27 Feb}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v257/main/assets/luzan24a/luzan24a.pdf}, url = {https://proceedings.mlr.press/v257/luzan24a.html}, abstract = {This work contributes to our understanding of how transfer learning can be used to improve educational predictive models across higher institution units. Specifically, we provide an empirical evaluation of the instance weighting strategy for transfer learning, whereby a model created from a source institution is modified based on the distribution characteristics of the target institution. In this work we demonstrated that this increases overall model goodness-of-fit, increases the goodness-of-fit for each demographic group considered, and reduces disparity between demographic groups when we consider a simulated institutional intervention that can only be deployed to 10% of the student body.} }
Endnote
%0 Conference Paper %T Evaluation of the Instance Weighting Strategy for Transfer Learning of Educational Predictive Models %A Mariia Luzan %A Christopher Brooks %B Proceedings of the 2024 AAAI Conference on Artificial Intelligence %C Proceedings of Machine Learning Research %D 2024 %E Muktha Ananda %E Debshila Basu Malick %E Jill Burstein %E Lydia T. Liu %E Zitao Liu %E James Sharpnack %E Zichao Wang %E Serena Wang %F pmlr-v257-luzan24a %I PMLR %P 19--28 %U https://proceedings.mlr.press/v257/luzan24a.html %V 257 %X This work contributes to our understanding of how transfer learning can be used to improve educational predictive models across higher institution units. Specifically, we provide an empirical evaluation of the instance weighting strategy for transfer learning, whereby a model created from a source institution is modified based on the distribution characteristics of the target institution. In this work we demonstrated that this increases overall model goodness-of-fit, increases the goodness-of-fit for each demographic group considered, and reduces disparity between demographic groups when we consider a simulated institutional intervention that can only be deployed to 10% of the student body.
APA
Luzan, M. & Brooks, C.. (2024). Evaluation of the Instance Weighting Strategy for Transfer Learning of Educational Predictive Models. Proceedings of the 2024 AAAI Conference on Artificial Intelligence, in Proceedings of Machine Learning Research 257:19-28 Available from https://proceedings.mlr.press/v257/luzan24a.html.

Related Material