Self-measuring Similarity for Multi-task Gaussian Process

Abstract

Multi-task learning aims at transferring knowledge between similar tasks. The multi-task Gaussian process framework of Bonilla et al. models (incomplete) responses of C data points for R tasks (e.g., the responses are given by R × C matrix) by a Gaussian process; the covariance function is defined as the product of a covariance function on input-dependent features and the inter-task covariance matrix (which is empirically estimated as a model parameter). We extend this framework by incorporating a novel similarity measurement, which allows for the representation of much more complex data structures. The proposed framework also enables us to exploit additional information (e.g., the input-dependent features) by constructing the covariance matrices with combining them on the covariance function. We also derive an efficient learning algorithm to make prediction by using an iterative method. Finally, we apply our model to a real data set of recommender systems and show that the proposed method achieves the best prediction accuracy on the data set.