Generalized query by transduction for online active learning

Transductive inference has gained popularity in recent years as a means to develop pattern classification approaches that address the specific issue of predicting the class label of a given data point, instead of the more general problem of inferring the ideal classifier function. In this paper, we propose a Generalized Query by Transduction (GQBT) approach for active learning in the online setting. This approach is based on the theory of conformal predictions, which has recently been proposed based on principles of algorithmic randomness, transductive inference and hypothesis testing. The proposed GQBT approach can be used along with any existing pattern classification algorithm, and can also be used to combine multiple criteria in selecting an unlabeled example appropriately in the active learning process. The results of our experiments with different datasets from the UCI Machine Learning repository demonstrate high promise in the proposed approach, with significantly lower label complexities than other existing online active learning approaches. The GQBT approach was also evaluated on face recognition using videos from the VidTIMIT dataset, and the observed superior performance supports the potential of applicability of the proposed approach in real-world problems.