Transfer Clustering Ensemble Selection

Shi, Yifan; Yu, Zhiwen; Chen, C. L. Philip; You, Jane; Wong, Hau-San; Wang, Yide; Zhang, Mengjie

doi:10.1109/tcyb.2018.2885585

Cited by 33 publications

(10 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two widely-used evaluation metrics, called Normalized Mutual Information (NMI) [35] and Adjusted Rand Index (AR-I) [7], are used to evaluate the clustering performance. They can provide a sound indication of the similarities between the predicted and ground truth label.…”

Section: B Evaluation Metricsmentioning

confidence: 99%

“…To capture different characteristics of the datasets, many multiobjective clustering approaches based on multiple cluster validity indices have been developed. Mukhopadhyay et al [6] developed a novel interactive genetic algorithm-based multiobjective approach by evolving a set of clustering validity measures to cluster real-life gene expression datasets; Shi et al [7] proposed a transfer clustering ensemble selection algorithm (TCES) under a multiobjective self-evolutionary process, in which three objective functions are optimized in a target dataset transferred from a source dataset; Li and Wong [8] proposed a multiobjective clustering method by fast search of density peaks (MOCDP) with five cluster validity indices served as the objective functions to stratify the patients into subtypes; Wang et al [9] investigated a multiobjective spectral clustering algorithm (MOSC) for patient stratification based on decomposition under two clustering validation measures. Unfortunately, those methods always employ one clustering algorithm as the basic clustering algorithm.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Learning to Optimize: Reference Vector Reinforcement Learning Adaption to Constrained Many-Objective Optimization of Industrial Copper Burdening System

Guo

et al. 2022

IEEE Trans. Cybern.

106

View full text Add to dashboard Cite

Patient stratification has been studied widely to tackle subtype diagnosis problems for effective treatment. Due to the dimensionality curse and poor interpretability of data, there is always a long-lasting challenge in constructing a stratification model with high diagnostic ability and good generalization. To address these problems, this paper proposes two novel evolutionary multiobjective clustering algorithms with ensemble (NSGA-II-ECFE and MOEA/D-ECFE) with four cluster validity indices used as the objective functions. First, an effective ensemble construction method is developed to enrich the ensemble diversity. After that, an ensemble clustering fitness evaluation (ECFE) method is proposed to evaluate the ensembles by measuring the consensus clustering under those four objective functions. To generate the consensus clustering, ECFE exploits the hybrid co-association matrix from the ensembles and then dynamically selects the suitable clustering algorithm on that matrix. Multiple experiments have been conducted to demonstrate the effectiveness of the proposed algorithm in comparison with seven clustering algorithms, twelve ensemble clustering approaches, and two multiobjective clustering algorithms on 55 synthetic datasets and 35 real patient stratification datasets. The experimental results demonstrate the competitive edges of the proposed algorithms over those compared methods. Furthermore, the proposed algorithm is applied to extend its advantages by identifying cancer subtypes from five cancer-related single-cell RNA-seq datasets.

show abstract

Section: B Evaluation Metricsmentioning

confidence: 99%

mentioning

confidence: 99%

Learning to Optimize: Reference Vector Reinforcement Learning Adaption to Constrained Many-Objective Optimization of Industrial Copper Burdening System

Guo

et al. 2022

IEEE Trans. Cybern.

106

View full text Add to dashboard Cite

show abstract

“…All partitions are treated equally. However, studies found that: 1) There are redundancy and noise in the base partitions, which can degrade the ensemble efficiency and the ensemble performance [16]. 2) The base partitions are not mutually independent.…”

Section: Introductionmentioning

confidence: 99%

Selective clustering ensemble based on kappa and F-score

Yan¹,

Liu²,

Qi³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper analyzed how to evaluate the quality of the base partitions and clusters in Selective Clustering Ensemble (SCE) and Weighted Clustering Ensemble (WCE).• We proposed a new evaluation method for partitions and clusters using kappa and F-score, leading to a new SCE method, which is called Diversity-Stability-Kappa-F method (DSKF).• The effectiveness and efficiency of the proposed method was empirically validated over real datasets.• Based on the empirical results, we observed that Normalized Mutual Information (NMI) values were misleading and failed to accurately reflect the actual performance of the partitions, and kappa is a better choice.

show abstract

“…Clustering is a primary yet challenging task in data analysis, aiming to partition similar samples into the same group and dissimilar samples into different groups. Recently, benefiting from the breakthroughs in deep learning, numerous deep clustering approaches have achieved state-of-the-art performance in many applications, including anomaly detection [4,26,39], signal propagation [10,[13][14][15][16]22], and transfer clustering [7,29,31,32]. The crucial prerequisite of deep clustering is to extract intricate patterns from underlying data for effectively learning the data representation.…”

Section: Introductionmentioning

confidence: 99%

Attention-driven Graph Clustering Network

Peng,

Liu,

Jia

et al. 2021

Preprint

View full text Add to dashboard Cite

The combination of the traditional convolutional network (i.e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph convolutional network captures the topological graph feature. However, the existing works (𝑖) lack a flexible combination mechanism to adaptively fuse those two kinds of features for learning the discriminative representation and (𝑖𝑖) overlook the multi-scale information embedded at different layers for subsequent cluster assignment, leading to inferior clustering results. To this end, we propose a novel deep clustering method named Attention-driven Graph Clustering Network (AGCN). Specifically, AGCN exploits a heterogeneity-wise fusion module to dynamically fuse the node attribute feature and the topological graph feature. Moreover, AGCN develops a scale-wise fusion module to adaptively aggregate the multi-scale features embedded at different layers. Based on a unified optimization framework, AGCN can jointly perform feature learning and cluster assignment in an unsupervised fashion. Compared with the existing deep clustering methods, our method is more flexible and effective since it comprehensively considers the numerous and discriminative information embedded in the network and directly produces the clustering results. Extensive quantitative and qualitative results on commonly used benchmark datasets validate that our AGCN consistently outperforms state-of-the-art methods. CCS CONCEPTS• Computing methodologies → Cluster analysis.

show abstract

Transfer Clustering Ensemble Selection

Cited by 33 publications

References 64 publications

Learning to Optimize: Reference Vector Reinforcement Learning Adaption to Constrained Many-Objective Optimization of Industrial Copper Burdening System

Learning to Optimize: Reference Vector Reinforcement Learning Adaption to Constrained Many-Objective Optimization of Industrial Copper Burdening System

Selective clustering ensemble based on kappa and F-score

Attention-driven Graph Clustering Network

Contact Info

Product

Resources

About