Deep Fair Clustering for Visual Learning

Li, Peizhao; Zhao, Han; Liu, Hongfu

doi:10.1109/cvpr42600.2020.00909

Cited by 51 publications

(38 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Entropy is a fairness metric that was defined in [111], and has only been exclusively used for fairness in the context of deep clustering models. A distinction of deep clustering with respect to general clustering methods is that ground truth labels for each sample are known prior to training.…”

Section: ) Entropymentioning

confidence: 99%

“…Content may change prior to final publication. [97], [98], [99], [100], [112], [105], [32], [113], [111], [114], [115], [116], [102], [117], [101] Bounded Representation clustering algorithm is constrained by two parameters that define the allowed maximum and minimum proportions of protected group members in a cluster any [86] [105], [85], [86], [97], [118], [119], [ remove the dependence of dimension for fair coreset generation in the case of k-means. Further, their approach works for multiple disjoint protected groups.…”

Section: A Clustering Objective 1) Center-based Clusteringmentioning

confidence: 99%

“…Fairoids allow for non-binary valued protected groups. Li et al [111] developed a scalable, deep clustering model that used adversarial loss to constrain learning and ensure fairness while maintaining cluster quality. They were the first paper to use deep, fair clustering on visual datasets for visual learning.…”

Section: ) Deep Clusteringmentioning

confidence: 99%

“…Significant Works Pre-processing [30], [99], [113], [105], [119], [97], [121], [122], [116] In-processing [114], [127], [115], [100], [125], [111], [101], [31], [93], [88], [91], [89], [90], [94], [102] Post-processing [128], [129], [130], [113], [85], [98], [86], [123], [118], [126], [34], [92], [87] 1) Pre-processing Approaches…”

Section: Classificationmentioning

confidence: 99%

“…In [125], the authors developed a k-median algorithm specifically for diversityaware fairness. In papers, [101], [102], [111] the authors constrained the deep clustering process itself, optimizing the trade-off between cluster quality and fairness through joint optimization, adversarial learning or other similar approaches.…”

Section: Classificationmentioning

confidence: 99%

See 4 more Smart Citations

An Overview of Fairness in Clustering

Chhabra¹,

Masalkovaite

Mohapatra

2021

IEEE Access

View full text Add to dashboard Cite

Clustering algorithms are a class of unsupervised machine learning (ML) algorithms that feature ubiquitously in modern data science, and play a key role in many learning-based application pipelines. Recently, research in the ML community has pivoted to analyzing the fairness of learning models, including clustering algorithms. Furthermore, research on fair clustering varies widely depending on the choice of clustering algorithm, fairness definitions employed, and other assumptions made regarding models. Despite this, a comprehensive survey of the field does not exist. In this paper, we seek to bridge this gap by categorizing existing research on fair clustering, and discussing possible avenues for future work. Through this survey, we aim to provide researchers with an organized overview of the field, and motivate new and unexplored lines of research regarding fairness in clustering.

show abstract

Section: ) Entropymentioning

confidence: 99%

Section: A Clustering Objective 1) Center-based Clusteringmentioning

confidence: 99%

Section: ) Deep Clusteringmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

See 3 more Smart Citations

An Overview of Fairness in Clustering

Chhabra¹,

Masalkovaite

Mohapatra

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

Fair and optimal prediction via post‐processing

Zhao

2024

AI Magazine

View full text Add to dashboard Cite

With the development of machine learning algorithms and the increasing computational resources available, artificial intelligence has achieved great success in many application domains. However, the success of machine learning has also raised concerns about the fairness of the learned models. For instance, the learned models can perpetuate and even exacerbate the potential bias and discrimination in the training data. This issue has become a major obstacle to the deployment of machine learning systems in high‐stakes domains, for example, criminal judgment, medical testing, online advertising, hiring process, and so forth. To mitigate the potential bias exhibited by machine learning models, fairness criteria can be integrated into the training process to ensure fair treatment across all demographics, but it often comes at the expense of model performance. Understanding such tradeoffs, therefore, is crucial to the design of optimal and fair algorithms. My research focuses on characterizing the inherent tradeoff between fairness and accuracy in machine learning, and developing algorithms that can achieve both fairness and optimality. In this article, I will discuss our recent work on designing post‐processing algorithms for fair classification, which can be applied to a wide range of fairness criteria, including statistical parity, equal opportunity, and equalized odds, under both attribute‐aware and attribute‐blind settings, and is particularly suited to large‐scale foundation models where retraining is expensive or even infeasible. I will also discuss the connections between our work and other related research on trustworthy machine learning, including the connections between algorithmic fairness and differential privacy as well as adversarial robustness.

show abstract