Incomplete Multi-View Weak-Label Learning with Noisy Features and Imbalanced Labels
This addresses a domain-specific problem in multi-view multi-label learning for applications with incomplete and noisy data, representing an incremental improvement over existing methods.
The paper tackles the problem of incomplete multi-view multi-label learning with noisy features and imbalanced labels by proposing a method that jointly embeds views and labels into a low-dimensional subspace with adaptive weights, using techniques like auto-weighted HSIC and focal loss. Experimental results on four real-world datasets demonstrate its effectiveness.
A variety of modern applications exhibit multi-view multi-label learning, where each sample has multi-view features, and multiple labels are correlated via common views. Current methods usually fail to directly deal with the setting where only a subset of features and labels are observed for each sample, and ignore the presence of noisy views and imbalanced labels in real-world problems. In this paper, we propose a novel method to overcome the limitations. It jointly embeds incomplete views and weak labels into a low-dimensional subspace with adaptive weights, and facilitates the difference between embedding weight matrices via auto-weighted Hilbert-Schmidt Independence Criterion (HSIC) to reduce the redundancy. Moreover, it adaptively learns view-wise importance for embedding to detect noisy views, and mitigates the label imbalance problem by focal loss. Experimental results on four real-world multi-view multi-label datasets demonstrate the effectiveness of the proposed method.