Unsupervised feature selection via adaptive graph and dependency score

Authors：Huang, Pei^*; Yang, Xiaowei^*

Source：Pattern Recognition, 2022, 127: 108622.

DOI：10.1016/j.patcog.2022.108622

• Unsupervised feature selection
• Adaptive graph
• Mutual information
• Entropy

Unsupervised feature selection is an important topic in the fields of machine learning, pattern recognition and data mining. The representation methods include adaptive-graph-based methods and selfrepresentation-based methods. The former methods have a longstanding and undiscovered problem about imbalanced neighbors, and the latter ones do not perform well when features are not linearly dependent. To deal with these problems, a novel unsupervised feature selection method is proposed to ensure k connectivity and eliminate more redundant features based on adaptive graph and dependency score (AGDS). Extensive experiments conducted on 13 benchmark datasets show the effectiveness of AGDS.