F3: Fair and Federated Face Attribute Classification with Heterogeneous Data
نویسندگان
چکیده
Fairness across different demographic groups is an essential criterion for face-related tasks, Face Attribute Classification (FAC) being a prominent example. Simultaneously, federated Learning (FL) gaining traction as scalable paradigm distributed training. In FL, client models trained on private datasets get aggregated by central aggregator. Existing FL approaches require data homogeneity to ensure fairness. However, this assumption restrictive in real-world settings. E.g., geographically distant or closely associated clients may have heterogeneous data. paper, we observe that existing techniques ensuring fairness are not viable with heterogeneity. We introduce F3, framework fair FAC under propose two methodologies (i) Heuristic-based and (ii) Gradient-based, improve without requiring assumption. demonstrate the efficacy of our through empirically observed measures accuracy guarantees popular face datasets. Using Mahalanobis distance, show F3 obtains practical balance between FAC. The code available at: github.com/magnetar-iiith/F3 .
منابع مشابه
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach
Face attribute estimation has many potential applications in video surveillance, face retrieval, and social media. While a number of methods have been proposed for face attribute estimation, most of them did not explicitly consider the attribute correlation and heterogeneity (e.g., ordinal vs. nominal and holistic vs. local) during feature representation learning. In this paper, we present a De...
متن کاملthe clustering and classification data mining techniques in insurance fraud detection:the case of iranian car insurance
با توجه به گسترش روز افزون تقلب در حوزه بیمه به خصوص در بخش بیمه اتومبیل و تبعات منفی آن برای شرکت های بیمه، به کارگیری روش های مناسب و کارآمد به منظور شناسایی و کشف تقلب در این حوزه امری ضروری است. درک الگوی موجود در داده های مربوط به مطالبات گزارش شده گذشته می تواند در کشف واقعی یا غیرواقعی بودن ادعای خسارت، مفید باشد. یکی از متداول ترین و پرکاربردترین راه های کشف الگوی داده ها استفاده از ر...
Distributed, heterogeneous, federated databases
These popular terms refer to collections of autonomous interoperable databases that model similar or complementary universes [8], [9], [3]. Examples include databases of banks, of hospitals, of car rentals, of restaurants, of jobs... The federated databases are typically subject to multidatabase queries, spanning several databases. A homebuyer may shop for the bank offering the cheapest mortgag...
متن کاملdata mining rules and classification methods in insurance: the case of collision insurance
assigning premium to the insurance contract in iran mostly has based on some old rules have been authorized by government, in such a situation predicting premium by analyzing database and it’s characteristics will be definitely such a big mistake. therefore the most beneficial information one can gathered from these data is the amount of loss happens during one contract to predicting insurance ...
15 صفحه اولذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Lecture Notes in Computer Science
سال: 2023
ISSN: ['1611-3349', '0302-9743']
DOI: https://doi.org/10.1007/978-3-031-33374-3_38