Robust Clustering Model Research Articles

Fuzzy clustering of financial time series based on volatility spillovers

AbstractIn this paper we propose a framework for fuzzy clustering of time series based on directional volatility spillovers. In the case of financial time series, detecting clusters of volatility spillovers provides insights into the market structure, which can be useful to both portfolio managers and policy makers. We measure directional—i.e. “From” and “To” the others—volatility spillovers with a methodology based on the generalized forecast-error variance decomposition. Then, we propose a weighted fuzzy clustering model for grouping stocks with a similar degree of directional spillovers. By using a weighted approach, we allow the algorithm to decide which dimension of spillover is more relevant for clustering. Moreover, a robust clustering model is also proposed to alleviate the effect of possible outlier stocks. We apply the proposed clustering model for the analysis of spillover effects in the Italian stock market.

Robust Clustering Model Based on Attention Mechanism and Graph Convolutional Network

GCN-based clustering schemes cannot interactively fuse feature information of nodes and topological structure information of graphs, leading to insufficient accuracy of clustering results. Moreover, the deep clustering model based on graph structure is vulnerable to the attack of adversarial samples leading to the reduced robustness of the model. To solve the above two problems, this paper proposes a robust clustering model based on attention mechanism and graph convolutional network (GCN), named AG-cluster. This model firstly uses graph attention network (GAT) and GCN to learn the feature information of nodes and the topological structure information of graphs, respectively. Then the representation results of the above two learning modules are interactively fused by the interlayer transfer operator. Finally, the model is trained end-to-end using a self-supervised training module to optimize the clustering results. In particular, an efficient graph purification defense mechanism (GPDM) is designed to resist adversarial attacks on graph data to improve the robustness of the model. Experimental results show that AG-cluster outperforms the other four benchmark methods, specifically, AG-cluster improves 7.6% in Accuracy and 11.5% in NMI compared to the best benchmark method. Besides, the new model still exhibits higher robustness and stronger migration ability under multiple attacks.

Robust clustering with sparse corruption via [formula omitted], [formula omitted] norm constraint and Laplacian regularization

Robust clustering with sparse corruption via [formula omitted], [formula omitted] norm constraint and Laplacian regularization

Adaptive Graph Regularized Low–Rank Matrix Factorization With Noise and Outliers for Clustering

Clustering, which is a commonly used tool, has been applied in machine learning, data mining and so on, and has received extensive research. However, there are usually noise and outliers in the data, which will bring about significant errors in the clustering results. In this paper, a robust clustering model with adaptive graph regularization (RCAG) is proposed, on which, sparse error matrix is introduced to express sparse noise, such as impulse noise, dead line, stripes, and $\ell _{1}$ norm is introduced to alleviate the sparse noise. In addition, the $\ell _{2,1}$ norm is also proposed mitigating the effects of outliers, and it has rotation invariance property. Therefore, our RCAG is insensitive to data noise and outliers. More importantly, the adaptive graph regularization is introduced into the RCAG to improve the clustering performance. Aiming at the optimization objective, we propose an iterative updating algorithm, named the Augmented Lagrangian Method (ALM), to update each optimization variable respectively. The convergence and time complexity of RCAG is also proved in theory. Finally, experimental results on fourteen datasets of four application scenarios, such as face image, handwriting recognition and UCI, elaborate the superiority of proposed method over seven existing classical clustering methods. The experimental results demonstrate that our approach achieves better clustering performance in ACC and Purity, which is a little less impressive in other ways.

Time series clustering by a robust autoregressive metric with application to air pollution

Time series clustering by a robust autoregressive metric with application to air pollution

Visualization of Non-Euclidean Relational Data by Robust Linear Fuzzy Clustering Based on FCMdd Framework

Visualization is a fundamental approach for revealing intrinsic structures in multidimensional observation. This paper considers visualization of non-Euclidean relational data by extracting local linear substructures. In order to extract robust linear clusters, an FCMdd-based linear fuzzy clustering model is applied in conjunction with a robust measure of alternativec-means. Non-Euclidean data matrices are handled with β-spread transformation in a manner similar to that of NERFc-Means. In several experiments, robust feature maps derived by the robust clustering model are compared with feature maps given by the conventional clustering model and Multi-Dimensional Scaling (MDS).