Robust continuous clustering
By Sohil Shah, Vladlen Koltun. 2017
187 citations recorded by the source corpus.
Significance Clustering is a fundamental experimental procedure in data analysis. It is used in virtually all natural and social sciences and has played a central role in biology, astronomy, psychology, medicine, and chemistry. Despite the importance and ubiquity of clustering, existing algorithms suffer from a variety of drawbacks and no universal solution has emerged. We present a clustering algorithm that reliably achieves high accuracy across domains, handles high data dimensionality, and scales to large datasets. The algorithm optimizes a smooth global objective, using efficient numerical methods. Experiments demonstrate that our method outperforms state-of-the-art clustering algorithms by significant factors in multiple domains. Clustering is a fundamental procedure in the analysis of scientific data. It is used ubiquitously across the sciences. Despite decades of research, existing clustering algorithms have limited effectiveness in high dimensions and often require tuning parameters for different domains and datasets. We present a clustering algorithm that achieves high accuracy across multiple domains and scales efficiently to high dimensions and large datasets. The presented algorithm optimizes a smooth continuous objective, which is based on robust statistics and allows heavily mixed clusters to be untangled. The continuous nature of the objective also allows clustering to be integrated as a module in end-to-end feature learning pipelines. We demonstrate this by extending the algorithm to perform joint clustering and dimensionality reduction by efficiently optimizing a continuous global objective. The presented approach is evaluated on large datasets of faces, hand-written digits, objects, newswire articles, sensor readings from the Space Shuttle, and protein expression levels. Our method achieves high accuracy across all datasets, outperforming the best prior algorithm by a factor of 3 in average rank.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- General Incremental Learning with Domain-aware Categorical Representations (2022, methodology): “Furthermore, we introduce a component regularization loss [26] on the mixture model of each class to learn a tight cluster, which is computed as below”
- Deep Spectral Clustering Using Dual Autoencoder Network (2019, methodology): “Shah and Koltun [34] jointly solve the tasks of clustering and dimensionality reduction by efficiently optimizing a continuous global objective based on robust statistics, which allows heavily mixed clusters to be untangled.”
- A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture (2018, background): “DCC is rooted in Robust Continuous Clustering (RCC) [43], a formulation having a clear continuous objective and no prior knowledge of clusters number.”
- COMIC: Multi-view Clustering Without Parameter Selection (2019, methodology): “Motivated by the success of convex clustering, Flammarion et al. (2017); Chen et al. (2015); Shah & Koltun (2017) have proposed a variety of penalties which result in regularization paths useful for clustering.”
- A General and Adaptive Robust Loss Function (2017, methodology): “Results on the clustering task of [31] where we compare their “RCC” algorithm to our “gRCC*” generalization in terms of AMI on several datasets.”