关键词: 多标记特征提取, 特征标记依赖度, 核极限学习机, 主成分分析, 自编码器

Abstract:

In multi-label learning, how to deal with high-dimensional features has always been one of the research difficulties. The feature extraction algorithm can effectively solve the problem of classification performance degra-dation caused by high dimensionality of data features. However, the existing multi-label feature extraction algo-rithms rarely make full use of feature information and fully extract the “feature-label” independent information and fusion information. Based on this, a multi-label feature extraction method based on feature-label dependence auto-encoder is proposed. The kernel extreme learning machine self-encoder is used to fuse the label space with the ori-ginal feature space and generate the reconstructed feature space. On the one hand, Hilbert-Schmidt independence cri-terion is maximized to make full use of the information between labels and the features; on the other hand, principal component analysis is used to reduce the information loss in the process of feature extraction. These?two?aspects are combined and the information of “feature-feature” and “feature-label” is extracted respectively. The comparison experi-ments on Yahoo high-dimensional multi-label datasets show that the performance of this algorithm is better than the current five main multi-label feature extraction methods, and the effectiveness of the proposed algorithm is verified.

Key words: multi-label feature extraction, feature-label dependence, kernel extreme learning machine, principal component analysis, autoencoder