Filters








64,916 Hits in 4.3 sec

Socially Fair k-Means Clustering [article]

Mehrdad Ghadiri, Samira Samadi, Santosh Vempala
2020 arXiv   pre-print
We present a fair k-means objective and algorithm to choose cluster centers that provide equitable costs for different groups.  ...  a negligible increase in running time, thus making it a viable fair option wherever k-means is currently used.  ...  Figure 10 : 10 Comparison of socially fair -means (Fair-Lloyd) to proportionally fair -means (Fairlet) on the Credit and Adult dataset in terms of proportionality and clustering cost.  ... 
arXiv:2006.10085v2 fatcat:ghheb7m6zrgjznsq2apiu5lp7i

Tight FPT Approximation for Socially Fair Clustering [article]

Dishant Goyal, Ragesh Jaiswal
2021 arXiv   pre-print
The socially fair k-means problem is defined similarly by using squared distances, i.e., d^2(.,.) instead of d(.,.).  ...  We design (3+ε) and (9 + ε) approximation algorithms for the socially fair k-median and k-means problems, respectively, in FPT (fixed parameter tractable) time f(k,ε) · n^O(1), where f(k,ε) = (k/ε)^O(k  ...  For z = 1 and z = 2, the problem is known as "socially fair k-median" and "socially fair k-means" problem, respectively.  ... 
arXiv:2106.06755v2 fatcat:2zoqyak7mffaldszq6unlocvjq

An Overview of Fairness in Clustering

Anshuman Chhabra, Karina Masalkovaite, Prasant Mohapatra
2021 IEEE Access  
One example is the k-means social fairness cost, proposed by [33] .  ...  of fairness is equivalent to minimizing the original 2-group balance notion proposed by [30] . 2) Social Fairness The social fairness cost was proposed by Ghadiri et al [33] for the k-means clustering  ... 
doi:10.1109/access.2021.3114099 fatcat:dipcrgby45amnkk3dodv2ppzai

Approximation Algorithms for Socially Fair Clustering [article]

Yury Makarychev, Ali Vakilian
2021 arXiv   pre-print
The goal is to find a k-medians, k-means, or, more generally, ℓ_p-clustering that is simultaneously good for all of the groups.  ...  The socially fair clustering problem was independently proposed by Ghadiri, Samadi, and Vempala [2021] and Abbasi, Bhaskara, and Venkatasubramanian [2021].  ...  Theorem 2 There exists a polynomial-time algorithm that computes an (e O(p) log ℓ log log ℓ )-approximation for the socially fair ℓ p -clustering problem (where ℓ is the number of groups).  ... 
arXiv:2103.02512v2 fatcat:pbf4oyxfwzhkbjftuikagsxbsa

Exploring Rawlsian Fairness for K-Means Clustering [article]

Stanley Simoes, Deepak P, Muiris MacCarthaigh
2022 arXiv   pre-print
., one that operates on the cluster assignment generated by the standard k-means clustering algorithm.  ...  Our focus is on the task of clustering, specifically the k-means clustering algorithm. To the best of our knowledge, this is the first work that uses Rawlsian ideas in clustering.  ...  i.e., the Rawlsian k-means clusters.  ... 
arXiv:2205.02052v1 fatcat:ruzxr4yvtnby3c3bdn3bbet3ym

Approximate Group Fairness for Clustering [article]

Bo Li, Lijun Li, Ankang Sun, Chenhao Wang, Yingfan Wang
2022 arXiv   pre-print
We refine the notion of proportional fairness proposed in [Chen et al., ICML 2019] as core fairness, and k-clustering is in the core if no coalition containing at least n/k agents can strictly decrease  ...  We incorporate group fairness into the algorithmic centroid clustering problem, where k centers are to be located to serve n agents distributed in a metric space.  ...  We consider the k-means objective as social cost, and compare our algorithm ALG + g (k-means) with k-means++. For each dataset, we consider a range of values of k.  ... 
arXiv:2203.17146v1 fatcat:kfxdqstpcbck7dd53dwfmwcgie

Imitation-based Social Spectrum Sharing [article]

Xu Chen, Jianwei Huang
2014 arXiv   pre-print
Numerical results show that the imitative spectrum access mechanism can achieve efficient spectrum utilization and meanwhile provide good fairness across secondary users.  ...  In this paper, we study how secondary users can share the spectrum in a distributed fashion based on social imitations.  ...  We also denote the set of clusters that communicates with cluster k as K k = {k : (i, k) ∈ W, ∀kK}.  ... 
arXiv:1405.2822v1 fatcat:fwvh6yaiybdtralewqgl4l627u

Constant-Factor Approximation Algorithms for Socially Fair k-Clustering [article]

Mehrdad Ghadiri, Mohit Singh, Santosh S. Vempala
2022 arXiv   pre-print
We study approximation algorithms for the socially fair (ℓ_p, k)-clustering problem with m groups, whose special cases include the socially fair k-median (p=1) and socially fair k-means (p=2) problems.  ...  in time k^m·poly(n).  ...  As discussed in [18] , the objective of the socially fair k-means promotes a more equitable average clustering cost among different groups.  ... 
arXiv:2206.11210v1 fatcat:4e23t4xarjdopn7z5p5aahwmde

Evaluating Students' Performance of Social Work Department Using K-means and Two-step Cluster

Said.Ahmed
2021 Zenodo  
Descriptive statistics, K-means, and Two-step clusters in SPSS, as well as RATTLE in R-Studio, were used to examine 126 students' scores for the seven courses.  ...  The study aims at evaluating the results of semester seven obtained by students of the Social work department at Mogadishu University to determine their academic performance.  ...  of the K-means cluster and the former cluster.  ... 
doi:10.5281/zenodo.5808660 fatcat:ydkmj555rngupl3zrtskklnjuu

Fair clustering via equitable group representations [article]

Mohsen Abbasi, Aditya Bhaskara, Suresh Venkatasubramanian
2020 arXiv   pre-print
What does it mean for a clustering to be fair? One popular approach seeks to ensure that each cluster contains groups in (roughly) the same proportion in which they exist in the population.  ...  We present approximation algorithms for group representative k-median clustering and couple this with an empirical evaluation on various real-world data sets.  ...  Consider the relaxed version of the k-means problem, namely linear j-subspace k-clustering.  ... 
arXiv:2006.11009v1 fatcat:wtgcq73i5ndabng4zl42plu4h4

Mapping Moral Valence of Tweets Following the Killing of George Floyd [article]

J. Hunter Priniski, Negar Mokhberian, Bahareh Harandizadeh, Fred Morstatter, Kristina Lerman, Hongjing Lu, P. Jeffrey Brantingham
2021 arXiv   pre-print
Recent research argues that moral discussions on social media are a catalyst for social change.  ...  The use of social media by the Black Lives Matter movement was a primary route for activists to promote the cause and organize over 1,400 protests across the country.  ...  Table 4 . 4 Mean activation for k-means each cluster of documents in embedding space.  ... 
arXiv:2104.09578v2 fatcat:zueoojrb7vfgxow7h6g772quym

An Integrated Vaccination Site Selection and Dose Allocation Problem with Fairness Concerns [article]

Mohammad Firouz, Linda Li, Daizy Ahmed, Abdulaziz Ahmed
2021 arXiv   pre-print
Fairness in vaccination is not only important from a social justice point of view, but experience has shown that a fair distribution of vaccine proves more effective in public immunization by preventing  ...  Equity in our setting means that as far as possible, each demand zone should receive a fair-share of the total doses available.  ...  α-Fair Weighted k-Means Clustering In this section, we introduce a fairness-adjusted version of the weighted k-means clustering technique to replace the site-zone assignment with site-cluster assignment  ... 
arXiv:2111.05843v1 fatcat:7hq4a3sfcnex5ff2b6wruxxfo4

Imitation-Based Social Spectrum Sharing

Xu Chen, Jianwei Huang
2015 IEEE Transactions on Mobile Computing  
Numerical results show that the imitative spectrum access mechanism can achieve efficient spectrum utilization and meanwhile provide good fairness across secondary users.  ...  In this paper, we study how secondary users can share the spectrum in a distributed fashion based on social imitations.  ...  We also denote the set of clusters that communicates with cluster k as K k = {k : (i, k) 2 W, 8k 2 K}.  ... 
doi:10.1109/tmc.2014.2347052 fatcat:upancgx6hvbyvigca6xxxb4lra

Multidimensionality of Health Inequalities: A Cross-Country Identification of Health Clusters through Multivariate Classification Techniques

Javier Alvarez-Galvez
2018 International Journal of Environmental Research and Public Health  
Despite major efforts in scientific literature to explain and understand the social determinants of health inequalities, the complex association between social causes and health outcomes remains empirically  ...  the relative relevance of different indicators that are susceptible to affect individual health outcomes; on the other hand, the resulting multidimensional classification of countries according health clusters  ...  K-means clustering might be defined as a specific method of cluster analysis that aims to allocate n observations into k clusters, in which each observation belongs to the cluster with the nearest mean  ... 
doi:10.3390/ijerph15091900 pmid:30200439 pmcid:PMC6164619 fatcat:f5p5mzlsovehnmflk45hcziyku

Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks [article]

Moein Khajehnejad, Ahmad Asgharian Rezaei, Mahmoudreza Babaei, Jessica Hoffmann, Mahdi Jalili, Adrian Weller
2020 arXiv   pre-print
We then find a good initial set by clustering the embeddings. We believe we are the first to use embeddings for the task of fair influence maximization.  ...  Here we address fair influence maximization, aiming to reach minorities more equitably.  ...  Z) gives the set of k centroids when performing k-means on the Z space and CLUSTERSPOINTS(k, Z) returns the corresponding k cluster of points.  ... 
arXiv:2005.04074v2 fatcat:voxi6yh73fhl7bq6vy7ynwguje
« Previous Showing results 1 — 15 out of 64,916 results