Transductive Matrix Completion with Calibration for Multi-Task Learning
This is an incremental improvement for multi-task learning applications with incomplete data.
The paper tackles the problem of incomplete feature and target matrices in multi-task learning by proposing a transductive matrix completion algorithm with calibration constraints, which outperforms existing methods particularly for nonlinear relationships between features and targets.
Multi-task learning has attracted much attention due to growing multi-purpose research with multiple related data sources. Moreover, transduction with matrix completion is a useful method in multi-label learning. In this paper, we propose a transductive matrix completion algorithm that incorporates a calibration constraint for the features under the multi-task learning framework. The proposed algorithm recovers the incomplete feature matrix and target matrix simultaneously. Fortunately, the calibration information improves the completion results. In particular, we provide a statistical guarantee for the proposed algorithm, and the theoretical improvement induced by calibration information is also studied. Moreover, the proposed algorithm enjoys a sub-linear convergence rate. Several synthetic data experiments are conducted, which show the proposed algorithm out-performs other existing methods, especially when the target matrix is associated with the feature matrix in a nonlinear way.