# Low-rank Kernel Learning for Graph-based Clustering

arXiv: https://arxiv.org/abs/1903.05962 · HTML: https://mlsanity.com/paper/1903.05962/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [Multiple Kernel Clustering with Dual Noise Minimization](https://mlsanity.com/paper/2207.06041/) (2022)
- [Nonlinear subspace clustering by functional link neural networks](https://mlsanity.com/paper/2402.02051/) (2024)
- [Adaptively Topological Tensor Network for Multi-view Subspace Clustering](https://mlsanity.com/paper/2305.00716/) (2023)
- [A Restarted Large-Scale Spectral Clustering with Self-Guiding and Block Diagonal Representation](https://mlsanity.com/paper/2306.15138/) (2023)
- [Beyond Linear Subspace Clustering: A Comparative Study of Nonlinear Manifold Clustering Algorithms](https://mlsanity.com/paper/2103.10656/) (2021)
- [Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge](https://mlsanity.com/paper/2105.11902/) (2021)
- [Multi-view clustering integrating anchor attribute and structural information](https://mlsanity.com/paper/2410.21711/) (2024)

## Abstract (arXiv)

Constructing the adjacency graph is fundamental to graph-based clustering. Graph learning in kernel space has shown impressive performance on a number of benchmark data sets. However, its performance is largely determined by the chosen kernel matrix. To address this issue, the previous multiple kernel learning algorithm has been applied to learn an optimal kernel from a group of predefined kernels. This approach might be sensitive to noise and limits the representation ability of the consensus kernel. In contrast to existing methods, we propose to learn a low-rank kernel matrix which exploits the similarity nature of the kernel matrix and seeks an optimal kernel from the neighborhood of candidate kernels. By formulating graph construction and kernel learning in a unified framework, the graph and consensus kernel can be iteratively enhanced by each other. Extensive experimental results validate the efficacy of the proposed method.