@article{Yang2018, author = {Yan Yang and Hao Wang}, title = {Multi-view Clustering: A Survey}, year = {2018}, journal = {Big Data Mining and Analytics}, volume = {1}, number = {2}, pages = {83-107}, keywords = {big data, data mining, conditional functional dependency, data quality}, url = {https://www.sciopen.com/article/10.26599/BDMA.2018.9020003}, doi = {10.26599/BDMA.2018.9020003}, abstract = {In the big data era, the data are generated from different sources or observed from different views. These data are referred to as multi-view data. Unleashing the power of knowledge in multi-view data is very important in big data mining and analysis. This calls for advanced techniques that consider the diversity of different views, while fusing these data. Multi-view Clustering (MvC) has attracted increasing attention in recent years by aiming to exploit complementary and consensus information across multiple views. This paper summarizes a large number of multi-view clustering algorithms, provides a taxonomy according to the mechanisms and principles involved, and classifies these algorithms into five categories, namely, co-training style algorithms, multi-kernel learning, multi-view graph clustering, multi-view subspace clustering, and multi-task multi-view clustering. Therein, multi-view graph clustering is further categorized as graph-based, network-based, and spectral-based methods. Multi-view subspace clustering is further divided into subspace learning-based, and non-negative matrix factorization-based methods. This paper does not only introduce the mechanisms for each category of methods, but also gives a few examples for how these techniques are used. In addition, it lists some publically available multi-view datasets. Overall, this paper serves as an introductory text and survey for multi-view clustering.} }