A Three-phase Augmented Classifiers Chain Approach Based on Co-occurrence Analysis for Multi-Label Classification
This work addresses a known bottleneck in multi-label classification methods, offering an incremental improvement for tasks requiring efficient and accurate label dependency modeling.
The paper tackles the problem of modeling label dependencies and error propagation in Classifier Chains for multi-label classification by proposing a three-phase augmented approach based on co-occurrence analysis, resulting in significantly improved performance with lower computational costs compared to existing variants.
As a very popular multi-label classification method, Classifiers Chain has recently been widely applied to many multi-label classification tasks. However, existing Classifier Chains methods are difficult to model and exploit the underlying dependency in the label space, and often suffer from the problems of poorly ordered chain and error propagation. In this paper, we present a three-phase augmented Classifier Chains approach based on co-occurrence analysis for multi-label classification. First, we propose a co-occurrence matrix method to model the underlying correlations between a label and its precedents and further determine the head labels of a chain. Second, we propose two augmented strategies of optimizing the order of labels of a chain to approximate the underlying label correlations in label space, including Greedy Order Classifier Chain and Trigram Order Classifier Chain. Extensive experiments were made over six benchmark datasets, and the experimental results show that the proposed augmented CC approaches can significantly improve the performance of multi-label classification in comparison with CC and its popular variants of Classifier Chains, in particular maintaining lower computational costs while achieving superior performance.