Abstract Error-correcting output codes (ECOC) are a successful technique to combine a set of binary classi?ers for multi-class learning problems. However, in traditional ECOC framework, all the base classi?ers are trained independently according to the de?ned ECOC matrix. In this paper, we reformulate the ECOC models from the perspective of multi-task learning, where the binary classi?ers are learned in a common subspace of data. This novel model can be considered as an adaptive generalization of the traditional ECOC framework. It simultaneously optimizes the representation of data as well as the binary classi?ers. More importantly, it builds a bridge between the ECOC framework and multitask learning for multi-class learning problems. To deal with complex data, we also present the kernel extension of the proposed model. Extensive empirical study on 14 data sets from UCI machine learning repository and the USPS handwritten digits recognition application demonstrates the effectiveness and ef?ciency of our model.