Abstract. In order to train learning models for multi-label classification (MLC), it is typically desirable to have a large amount of fully annotated multi-label data. Since such annotation process is in general costly, we focus on the learning task of weakly-supervised multi-label classification (WS-MLC). In this paper, we tackle WS-MLC by learning deep generative models for describing the collected data. In particular, we introduce a sequential network architecture for constructing our generative model with the ability to approximate observed data posterior distributions. We show that how information of training data with missing labels or unlabeled ones can be exploited, which allows us to learn multi-label classifiers via scalable variational inferences. Empirical studies on various scales of datasets demonstrate the effectiveness of our proposed model, which performs favorably against state-of-the-art MLC algorithms