Revisiting Silhouette Aggregation

• URL: http://arxiv.org/abs/2401.05831v3
• Date: Sat, 22 Jun 2024 17:59:01 GMT
• Title: Revisiting Silhouette Aggregation
• Authors: John Pavlopoulos, Georgios Vardakas, Aristidis Likas,
• Abstract summary: Silhouette coefficient is an evaluation measure that produces a score per data point, assessing the quality of its clustering assignment. An alternative path, that is rarely employed, is to average first at the cluster level and then (macro) average across clusters. We show that the typical micro-averaging strategy is sensitive to cluster imbalance while the overlooked macro-averaging strategy is far more robust.
• Score: 2.56711111236449
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Silhouette coefficient is an established internal clustering evaluation measure that produces a score per data point, assessing the quality of its clustering assignment. To assess the quality of the clustering of the whole dataset, the scores of all the points in the dataset are typically (micro) averaged into a single value. An alternative path, however, that is rarely employed, is to average first at the cluster level and then (macro) average across clusters. As we illustrate in this work with a synthetic example, the typical micro-averaging strategy is sensitive to cluster imbalance while the overlooked macro-averaging strategy is far more robust. By investigating macro-Silhouette further, we find that uniform sub-sampling, the only available strategy in existing libraries, harms the measure's robustness against imbalance. We address this issue by proposing a per-cluster sampling method. An experimental study on eight real-world datasets is then used to analyse both coefficients in two clustering tasks.

Related papers

• Self-Supervised Graph Embedding Clustering [70.36328717683297]
  K-means one-step dimensionality reduction clustering method has made some progress in addressing the curse of dimensionality in clustering tasks. We propose a unified framework that integrates manifold learning with K-means, resulting in the self-supervised graph embedding framework.
  arXiv  Detail & Related papers  (2024-09-24T08:59:51Z)
• Interpretable Clustering with the Distinguishability Criterion [0.4419843514606336]
  We present a global criterion called the Distinguishability criterion to quantify the separability of identified clusters and validate inferred cluster configurations. We propose a combined loss function-based computational framework that integrates the Distinguishability criterion with many commonly used clustering procedures. We present these new algorithms as well as the results from comprehensive data analysis based on simulation studies and real data applications.
  arXiv  Detail & Related papers  (2024-04-24T16:38:15Z)
• Quality check of a sample partition using multinomial distribution [0.0]
  We advocate a novel measure for the purpose of checking the quality of a cluster partition for a sample into several distinct classes. We apply the multinomial distribution to the distances of data members, clustered in a group, from their respective cluster representatives.
  arXiv  Detail & Related papers  (2024-04-11T14:14:58Z)
• Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model [79.46465138631592]
  We devise an efficient algorithm that recovers clusters using the observed labels. We present Instance-Adaptive Clustering (IAC), the first algorithm whose performance matches these lower bounds both in expectation and with high probability.
  arXiv  Detail & Related papers  (2023-06-18T08:46:06Z)
• Cluster-level Group Representativity Fairness in $k$-means Clustering [3.420467786581458]
  Clustering algorithms could generate clusters such that different groups are disadvantaged within different clusters. We develop a clustering algorithm, building upon the centroid clustering paradigm pioneered by classical algorithms. We show that our method is effective in enhancing cluster-level group representativity fairness significantly at low impact on cluster coherence.
  arXiv  Detail & Related papers  (2022-12-29T22:02:28Z)
• Self-Evolutionary Clustering [1.662966122370634]
  Most existing deep clustering methods are based on simple distance comparison and highly dependent on the target distribution generated by a handcrafted nonlinear mapping. A novel modular Self-Evolutionary Clustering (Self-EvoC) framework is constructed, which boosts the clustering performance by classification in a self-supervised manner. The framework can efficiently discriminate sample outliers and generate better target distribution with the assistance of self-supervised.
  arXiv  Detail & Related papers  (2022-02-21T19:38:18Z)
• Differentially-Private Clustering of Easy Instances [67.04951703461657]
  In differentially private clustering, the goal is to identify $k$ cluster centers without disclosing information on individual data points. We provide implementable differentially private clustering algorithms that provide utility when the data is "easy" We propose a framework that allows us to apply non-private clustering algorithms to the easy instances and privately combine the results.
  arXiv  Detail & Related papers  (2021-12-29T08:13:56Z)
• Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types [60.45942774425782]
  We introduce anomaly clustering, whose goal is to group data into coherent clusters of anomaly types. This is different from anomaly detection, whose goal is to divide anomalies from normal data. We present a simple yet effective clustering framework using a patch-based pretrained deep embeddings and off-the-shelf clustering methods.
  arXiv  Detail & Related papers  (2021-12-21T23:11:33Z)
• You Never Cluster Alone [150.94921340034688]
  We extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation. We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps.
  arXiv  Detail & Related papers  (2021-06-03T14:59:59Z)
• Scalable Hierarchical Agglomerative Clustering [65.66407726145619]
  Existing scalable hierarchical clustering methods sacrifice quality for speed. We present a scalable, agglomerative method for hierarchical clustering that does not sacrifice quality and scales to billions of data points.
  arXiv  Detail & Related papers  (2020-10-22T15:58:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.