潜在表示学习框架下的低冗余多视图聚类算法

Multi-view clustering based on latent representation learning and low redundancy

基于潜在空间学习的多视图聚类研究得到了较大发展,但其通常忽略了原始数据中冗余信息的存在可能会带来不理想的聚类结果。为解决这个问题,提出一种潜在表示学习框架下的低冗余多视图聚类算法。基于k-means的方法,直接从各视图数据学习其低维表示,由于该低维表示的各个特征相互正交,学习到的低维表示通常含有较少的冗余信息。基于潜在空间的假设,各视图的低维表示可由同一个潜在表示投影得到。将两者结合,就能得到一个具有低冗余信息的统一的潜在表示。设计了一个优化算法来求解目标问题,在多个公开数据集上的实验表明了该算法的有效性。

Multi-view clustering algorithms based on latent representation learning have gained enormous development.However,they usually neglect the redundant information in the original data,which may cause degraded clustering results.To address this issue,this paper proposes a new algorithm named multi-view clustering based on latent representation learning and low redundancy(LRLLR).First,based on k-means,a new low-dimensional representation can be learnt from each view.It follows from orthogonality that the new representations usually contain low redundant information.Second,we assume that the low-dimensional representation of each view can be projected by a shared latent representation.By combining the two parts into a unified framework,our model can produce a latent representation with low redundancy.Finally,an optimization algorithm is proposed to solve the target problem.Extensive experiments on several benchmark datasets demonstrate the effectiveness of our algorithm compared with other state-of-the-art algorithms.