论文阅读 [TPAMI-2022] Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method

论文阅读 [TPAMI-2022] Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method

论文搜索(studyai.com)

搜索论文: Multiview Clustering: A Scalable and Parameter-Free Bipartite Graph Fusion Method

搜索论文: http://www.studyai.com/search/whole-site/?q=Multiview+Clustering:+A+Scalable+and+Parameter-Free+Bipartite+Graph+Fusion+Method

关键字(Keywords)

Laplace equations; Clustering algorithms; Bipartite graph; Optical imaging; Electronic mail; Data models; Computer science; Multiview clustering; scalable and parameter-free; graph fusion; connectivity constraint; initialization-independent

机器学习; 机器视觉

自监督学习; 聚类; 多目立体视觉

摘要(Abstract)

Multiview clustering partitions data into different groups according to their heterogeneous features.

多视图聚类根据数据的异构特征将数据划分为不同的组。.

Most existing methods degenerate the applicability of models due to their intractable hyper-parameters triggered by various regularization terms.

由于各种正则化项触发了难以处理的超参数，现有的大多数方法都降低了模型的适用性。.

Moreover, traditional spectral based methods always encounter the expensive time overheads and fail in exploring the explicit clusters from graphs.

此外，传统的基于谱的方法往往会遇到昂贵的时间开销，并且无法从图中发现显式聚类。.

In this paper, we present a scalable and parameter-free graph fusion framework for multiview clustering, seeking for a joint graph compatible across multiple views in a self-supervised weighting manner.

在本文中，我们提出了一个用于多视图聚类的可伸缩且无参数的图融合框架，以自监督加权方式寻求跨多个视图兼容的联合图。.

Our formulation coalesces multiple view-wise graphs straightforward and learns the weights as well as the joint graph interactively, which could actively release the model from any weight-related hyper-parameters.

我们的公式直接合并了多个视图图，并以交互方式学习权重以及关节图，这可以主动地将模型从任何与权重相关的超参数中释放出来。.

Meanwhile, we manipulate the joint graph by a connectivity constraint such that the connected components indicate clusters directly.

同时，我们通过一个连通性约束来操纵连接图，使得连接的组件直接表示簇。.

The designed algorithm is initialization-independent and time-economical which obtains the stable performance and scales well with the data size.

所设计的算法具有初始化无关性和时间经济性，性能稳定，并能很好地适应数据量的变化。.

Substantial experiments on toy data as well as real datasets are conducted that verify the superiority of the proposed method compared to the state-of-the-arts over the clustering performance and time expenditure…

在玩具数据和真实数据集上进行了大量实验，验证了所提方法在聚类性能和时间开销方面与现有方法相比的优越性。。.

作者(Authors)

[‘Xuelong Li’, ‘Han Zhang’, ‘Rong Wang’, ‘Feiping Nie’]