Kernel based incremental learning Isomap algorithm

Isomap is one of widely-used low-dimensional embedding methods. However, in many scenarios, the data come sequentially and the effect of the data is accumulated. Isomap algorithms have no the ability of new data be added for all data need to be available when estimates the geodesic distances. In this paper we propose an incremental learning isomap algorithm, which take the approximate geodesic distance matrix as a kernel matrix then projection is converted to solve a kernel eigenvalues problem. We have no need to reconstructing the neighborhood graph for those incremental samples. Experiments results on Swiss datasets and Helix datasets show that our algorithm is more effective than isomap method.