KIT | KIT-Bibliothek | Impressum | Datenschutz

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

Hirt, Robin; Srivastava, Akash; Berg, Carlos; Kühl, Niklas

Abstract (englisch):
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.

Zugehörige Institution(en) am KIT Karlsruhe Service Research Institute (KSRI)
Institut für Wirtschaftsinformatik und Marketing (IISM)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2021
Sprache Englisch
Identifikator KITopen-ID: 1000125423
Erschienen in Hawaii International Conference on Systems Sciences (HICSS-54), Kauai, Hawaii, USA, January 5-8, 2021
Vorab online veröffentlicht am 05.01.2021
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page