Transfer Learning for Bayesian Networks

In several domains it is common to have data from different, but closely related problems. For instance, in manufacturing many products follow the same industrial process but with different conditions; or in industrial diagnosis, where there is equipment with similar specifications. In these cases, it is common to have plenty of data for some scenarios but very little for other. In order to learn accurate models for rare cases, it is desirable to use data and knowledge from similar cases; a technique known as “transfer learning”. In this paper, we propose a transfer learning method for Bayesian networks, that considers both, structure and parameter learning. For structure learning, we use conditional independence tests, by combining measures from the target domain with those obtained from one or more auxiliary domains, using a weighted sum of the conditional independence measures. For parameter learning, we compared two techniques for probability aggregation that combine probabilities estimated from the target domain with those obtained from the auxiliary data. To validate our approach, we used three Bayesian networks models that are commonly used for evaluating learning techniques, and generated variants of each model by changing the structure as well as the parameters. We then learned one of the variants with a small data set and combined it with information from the other variants. The experimental results show a significant improvement in terms of structure and parameters when we transfer knowledge from similar problems.