Deep Adversarial Inconsistent Cognitive Sampling for Multi-view Progressive Subspace Clustering
This work provides an incremental improvement for multi-view clustering by addressing the problem of inconsistent difficulty labels in training samples, which can lead to suboptimal clustering networks.
This paper addresses the challenge of inconsistent 'difficulty labels' in multi-view clustering by proposing Deep Adversarial Inconsistent Cognitive Sampling (DAICS). It jointly learns a binary classifier and a deep consistent feature embedding network through an adversarial minimax game, and employs a multi-view cognitive sampling strategy to progressively select samples from easy to difficult. The method demonstrates superior performance on four real-world datasets compared to state-of-the-art approaches.
Deep multi-view clustering methods have achieved remarkable performance. However, all of them failed to consider the difficulty labels (uncertainty of ground-truth for training samples) over multi-view samples, which may result into a nonideal clustering network for getting stuck into poor local optima during training process; worse still, the difficulty labels from multi-view samples are always inconsistent, such fact makes it even more challenging to handle. In this paper, we propose a novel Deep Adversarial Inconsistent Cognitive Sampling (DAICS) method for multi-view progressive subspace clustering. A multiview binary classification (easy or difficult) loss and a feature similarity loss are proposed to jointly learn a binary classifier and a deep consistent feature embedding network, throughout an adversarial minimax game over difficulty labels of multiview consistent samples. We develop a multi-view cognitive sampling strategy to select the input samples from easy to difficult for multi-view clustering network training. However, the distributions of easy and difficult samples are mixed together, hence not trivial to achieve the goal. To resolve it, we define a sampling probability with theoretical guarantee. Based on that, a golden section mechanism is further designed to generate a sample set boundary to progressively select the samples with varied difficulty labels via a gate unit, which is utilized to jointly learn a multi-view common progressive subspace and clustering network for more efficient clustering. Experimental results on four real-world datasets demonstrate the superiority of DAICS over the state-of-the-art methods.