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

Date
2021-01-05
Authors
Hirt, Robin
Srivastava, Akash
Berg, Carlos
Kühl, Niklas
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
7078
Ending Page
Alternative Title
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.
Description
Keywords
Decentralized Federated Learning: Applications, Solutions, and Challenges, federated data, sales forecasting, sequential transfer learning, transferability
Citation
Extent
10 pages
Format
Geographic Location
Time Period
Related To
Proceedings of the 54th Hawaii International Conference on System Sciences
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
Rights Holder
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.