Balancing efficiency vs. effectiveness and providing missing label robustness in multi-label stream classification

Available works addressing multi-label classification in a data stream environment focus on proposing accurate prediction models; however, they struggle to balance effectiveness and efficiency. In this work, we present a neural network-based approach that tackles this issue and is suitable for high-dimensional multi-label classification. The proposed model uses a selective concept drift adaptation mechanism that makes it well-suited for a non-stationary environment. We adapt the model to an environment with missing labels using a simple imputation strategy and demonstrate that it outperforms a vast majority of the supervised models. To achieve these, a weighted binary relevance-based approach named ML-BELS is introduced. To capture label dependencies, instead of a chain of stacked classifiers, the proposed model employs independent weighted ensembles as binary classifiers, with the weights generated by the predictions of a BELS classifier. We present an extensive assessment of the proposed model using 11 prominent baselines, five synthetic, and 13 real-world datasets, all with different characteristics. The results demonstrate that the proposed approach ML-BELS is successful in balancing effectiveness and efficiency, and is robust to missing labels and concept drift.