摘要：It is common in real-world data streams that previously seen concepts will reappear, which suggests a unique kind of concept drift, known as recurring concepts. Unfortunately, most of existing algorithms do not take full account of this case. Motivated by this challenge, a novel paradigm was proposed for capturing and exploiting recurring concepts in data streams. It not only incorporates a distribution-based change detector for handling concept drift but also captures recurring concept by storing recurring concepts in a classifier graph. The possibility of detecting recurring drifts allows reusing previously learnt models and enhancing the overall learning performance. Extensive experiments on both synthetic and real-world data streams reveal that the approach performs significantly better than the state-of-the-art algorithms, especially when concepts reappear.
