Adaptive Matching of Kernel Means
This work addresses efficiency and scalability in kernel machines for knowledge discovery, but appears incremental as it builds on existing kernel mean matching methods.
The paper tackles the problem of improving data analysis and feature learning by proposing an adaptive kernel mean matching method that selects high-importance data for efficiency, achieving outstanding performance compared to state-of-the-art methods on real-world datasets.
As a promising step, the performance of data analysis and feature learning are able to be improved if certain pattern matching mechanism is available. One of the feasible solutions can refer to the importance estimation of instances, and consequently, kernel mean matching (KMM) has become an important method for knowledge discovery and novelty detection in kernel machines. Furthermore, the existing KMM methods have focused on concrete learning frameworks. In this work, a novel approach to adaptive matching of kernel means is proposed, and selected data with high importance are adopted to achieve calculation efficiency with optimization. In addition, scalable learning can be conducted in proposed method as a generalized solution to matching of appended data. The experimental results on a wide variety of real-world data sets demonstrate the proposed method is able to give outstanding performance compared with several state-of-the-art methods, while calculation efficiency can be preserved.