KeCo: Kernel-Based Online Co-agreement Algorithm

We propose a kernel-based online semi-supervised algorithm that is applicable for large scale learning tasks. In particular, we use a multi-view learning framework and a co-agreement strategy to take into account unlabelled data and to improve classification performance of the algorithm. Unlike the standard online methods our algorithm is naturally applicable to many real-world situations where data is available in multiple representations. In addition our online algorithm allows learning non-linear relations in the data via kernel functions, that are efficiently embedded into the formulation of the algorithm. We test performance of the algorithm on several large-scale LIBSVM and UCI benchmark datasets and demonstrate improved performance in comparison to standard online learning methods. Last but not least, we make a Python implementation of our algorithm available for download.