Domain Regularized Subspace Projection Method

This chapter addresses the time-varying drift with characteristics of uncertainty and unpredictability. Considering that drifted data is with different probability distribution from the regular data, we propose a machine learning-based subspace projection approach to project the data onto a new common subspace so that two clusters have similar distribution. Then drift can be automatically removed or reduced in the new common subspace. The merits are threefold: (1) the proposed subspace projection is unsupervised, without using any data label information; (2) a simple but effective domain distance is proposed to represent the mean distribution discrepancy metric; (3) the proposed anti-drift method can be easily solved by Eigen decomposition, and anti-drift is manifested with a well-solved projection matrix in real application. Experiments on synthetic data and real datasets demonstrate the effectiveness and efficiency of the proposed anti-drift method in comparison to state-of-the-art methods.