Sequential Transfer Machine Learning in Networks: Measuring the Impact of Data and Neural Net Similarity on Transferability
| Autor: | Carlos Berg, Niklas Kühl, Akash Srivastava, Robin Hirt |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Measure (data warehouse) Artificial neural network Economics Computer science business.industry Machine Learning (stat.ML) Machine learning computer.software_genre Machine Learning (cs.LG) Empirical research Similarity (network science) Statistics - Machine Learning Transfer (computing) Path (graph theory) ddc:330 Artificial intelligence Metric (unit) business Raw data computer |
| Zdroj: | HICSS |
| ISSN: | 2572-6862 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|