Sequential Transfer Machine Learning in Networks: Measuring the Impact of Data and Neural Net Similarity on Transferability
This work addresses the need for indicators to improve model performance with fewer transfers in networks of entities with similar predictive tasks, but it is incremental as it builds on existing transfer learning concepts.
The study tackled the problem of predicting successful neural network transfers in business networks by empirically testing transferability across sales data from six restaurants, finding significant negative correlations between transferability and indicators like data divergence and neural net similarity.
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.