Unbalanced Incomplete Multi-View Clustering Via the Scheme of View Evolution: Weak Views are Meat; Strong Views Do Eat

Incomplete multi-view clustering is an important technique to deal with real-world incomplete data. Previous works assume that all views have the same incompleteness, i.e., balanced incompleteness. However, different often distinct unbalanced which results in strong (low-incompleteness views) and weak (high-incompleteness views). The incompleteness prevents us from directly using previous methods for clustering. In this paper, inspired by effective biological evolution theory, we design novel scheme of view cluster views. Moreover, propose Unbalanced Multi-view Clustering method (UIMC), first based on Compared methods, UIMC has two unique advantages: 1) it proposes weighted subspace integrate these views, effectively solves problem; 2) designs low-rank robust representation recover data, diminishes impact noises. Extensive experimental demonstrate improves performance up 40% three evaluation metrics over other state-of-the-art methods.