Zobrazeno 1 - 10
of 179
pro vyhledávání: '"VENKATASUBRAMANIAN, SURESH"'
Social media platforms have become central to global communication, yet they also facilitate the spread of hate speech. For underrepresented dialects like Levantine Arabic, detecting hate speech presents unique cultural, ethical, and linguistic chall
Externí odkaz:
http://arxiv.org/abs/2412.10991
In many domains, it is difficult to obtain the race data that is required to estimate racial disparity. To address this problem, practitioners have adopted the use of proxy methods which predict race using non-protected covariates. However, these pro
Externí odkaz:
http://arxiv.org/abs/2409.01984
As Artificial Intelligence (AI) tools are increasingly employed in diverse real-world applications, there has been significant interest in regulating these tools. To this end, several regulatory frameworks have been introduced by different countries
Externí odkaz:
http://arxiv.org/abs/2407.08689
Autor:
Venkatasubramanian, Suresh, Gebru, Timnit, Topcu, Ufuk, Griffin, Haley, Rosenbloom, Leah Namisa, Sonboli, Nasim
Based on our workshop activities, we outlined three ways in which research can support community needs: (1) Mapping the ecosystem of both the players and ecosystem and harm landscapes, (2) Counter-Programming, which entails using the same surveillanc
Externí odkaz:
http://arxiv.org/abs/2406.07556
In fair machine learning, one source of performance disparities between groups is over-fitting to groups with relatively few training samples. We derive group-specific bounds on the generalization error of welfare-centric fair machine learning that b
Externí odkaz:
http://arxiv.org/abs/2402.18803
Data forms the backbone of artificial intelligence (AI). Privacy and data protection laws thus have strong bearing on AI systems. Shielded by the rhetoric of compliance with data protection and privacy regulations, privacy-preserving techniques have
Externí odkaz:
http://arxiv.org/abs/2402.06609
Autor:
Kwegyir-Aggrey, Kweku, Gerchick, Marissa, Mohan, Malika, Horowitz, Aaron, Venkatasubramanian, Suresh
When determining which machine learning model best performs some high impact risk assessment task, practitioners commonly use the Area under the Curve (AUC) to defend and validate their model choices. In this paper, we argue that the current use and
Externí odkaz:
http://arxiv.org/abs/2305.18159
Autor:
Bashardoust, Ashkan, Friedler, Sorelle A., Scheidegger, Carlos E., Sullivan, Blair D., Venkatasubramanian, Suresh
In social networks, a node's position is a form of \it{social capital}. Better-positioned members not only benefit from (faster) access to diverse information, but innately have more potential influence on information spread. Structural biases often
Externí odkaz:
http://arxiv.org/abs/2209.07616
Autor:
Abbasi, Mohsen, Venkatasubramanian, Suresh, Friedler, Sorelle A., Lum, Kristian, Barrett, Calvin
Voter suppression and associated racial disparities in access to voting are long-standing civil rights concerns in the United States. Barriers to voting have taken many forms over the decades. A history of violent explicit discouragement has shifted
Externí odkaz:
http://arxiv.org/abs/2205.14867
Autor:
Kwegyir-Aggrey, Kweku, Cooper, A. Feder, Dai, Jessica, Dickerson, John, Hines, Keegan, Venkatasubramanian, Suresh
We study the problem of post-processing a supervised machine-learned regressor to maximize fair binary classification at all decision thresholds. By decreasing the statistical distance between each group's score distributions, we show that we can inc
Externí odkaz:
http://arxiv.org/abs/2203.07490