Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/71472

Sequential Transfer Machine Learning in Networks: Measuring the Impact of Data and Neural Net Similarity on Transferability

File Size Format  
0692.pdf 1.41 MB Adobe PDF View/Open

Item Summary

Title:Sequential Transfer Machine Learning in Networks: Measuring the Impact of Data and Neural Net Similarity on Transferability
Authors:Hirt, Robin
Srivastava, Akash
Berg, Carlos
Kühl, Niklas
Keywords:Decentralized Federated Learning: Applications, Solutions, and Challenges
federated data
sales forecasting
sequential transfer learning
transferability
Date Issued:05 Jan 2021
Abstract:In networks of independent entities that face similar predictive tasks, transfer machine learning enables to re-use and improve neural nets using distributed data sets without the exposure of raw data. As the number of data sets in business networks grows and not every neural net transfer is successful, indicators are needed for its impact on the target performance-its transferability. We perform an empirical study on a unique real-world use case comprised of sales data from six different restaurants. We train and transfer neural nets across these restaurant sales data and measure their transferability. Moreover, we calculate potential indicators for transferability based on divergences of data, data projections and a novel metric for neural net similarity. We obtain significant negative correlations between the transferability and the tested indicators. Our findings allow to choose the transfer path based on these indicators, which improves model performance whilst simultaneously requiring fewer model transfers.
Pages/Duration:10 pages
URI:http://hdl.handle.net/10125/71472
ISBN:978-0-9981331-4-0
DOI:10.24251/HICSS.2021.851
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
Appears in Collections: Decentralized Federated Learning: Applications, Solutions, and Challenges


Please email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons