GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning

Yue, Xubo; Nouiehed, Maher; Kontar, Raed Al

doi:10.48550/arxiv.2108.02741

Cited by 8 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One popular definition of fairness in the federated setting is that all clients (i.e. data owners) achieve similar accuracies (or loss values), which we call client parity, and several algorithms have been proposed to achieve this goal [Li et al, 2021, Mohri et al, 2019, Yue et al, 2021, Zhang et al, 2020a. To compare our methods with existing federated fair learning algorithms designed for client parity, we also extend our FEDFB such that it can also achieve client parity instead of the standard notion of group fairness.…”

Section: Federated Fair Learning For Client Paritymentioning

confidence: 99%

See 1 more Smart Citation

Improving Fairness via Federated Learning

Zeng¹,

Chen²,

Lee³

2021

Preprint

View full text Add to dashboard Cite

Recently, lots of algorithms have been proposed for learning a fair classifier from centralized data. However, how to privately train a fair classifier on decentralized data has not been fully studied yet. In this work, we first propose a new theoretical framework, with which we analyze the value of federated learning in improving fairness. Our analysis reveals that federated learning can strictly boost model fairness compared with all non-federated algorithms. We then theoretically and empirically show that the performance tradeoff of FedAvg-based fair learning algorithms is strictly worse than that of a fair classifier trained on centralized data. To resolve this, we propose FEDFB, a private fair learning algorithm on decentralized data with a modified FedAvg protocol. Our extensive experimental results show that FEDFB significantly outperforms existing approaches, sometimes achieving a similar tradeoff as the one trained on centralized data.

show abstract

Section: Federated Fair Learning For Client Paritymentioning

confidence: 99%

“…Baselines We consider GIFAIR [Yue et al, 2021], Q-FFL [Li et al, 2020b], DITTO [Li et al, 2021], and the unconstrained baseline FedAvg . GIFAIR and Q-FFL are the most similar ones to FEDFB.…”

Section: Fedfb Evaluation On Client Paritymentioning

confidence: 99%

Improving Fairness via Federated Learning

Zeng¹,

Chen²,

Lee³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, the experimental results of measuring fairness in FL literature have been arbitrary. In one study (Yue, Nouiehed, and Kontar 2021), authors define biases in terms of the color of the handwritten digits in MNIST (blue versus black group). Such studies fail to address biases as contextual and societal driven.…”

Section: Achieving Fairness In Spatial-temporal Fl Fairness In Federa...mentioning

confidence: 99%

Fairness in Federated Learning for Spatial-Temporal Applications

Mashhadi¹,

Kyllo²,

Parizi³

2022

Preprint

View full text Add to dashboard Cite

Federated learning involves training statistical models over remote devices such as mobile phones while keeping data localized. Training in heterogeneous and potentially massive networks introduces opportunities for privacy-preserving data analysis and diversifying these models to become more inclusive of the population. Federated learning can be viewed as a unique opportunity to bring fairness and parity to many existing models by enabling model training to happen on a diverse set of participants and on data that is generated regularly and dynamically. In this paper, we discuss the current metrics and approaches that are available to measure and evaluate fairness in the context of spatial-temporal models. We propose how these metrics and approaches can be re-defined to address the challenges that are faced in the federated learning setting.

show abstract

“…This becomes a bigger challenge if such sensitive attributes are not shared. Therefore, fair FL is an important challenge to tackle within IoFT [349,173] • Other Statistical and Optimization Challenges:…”

Section: • Communication Efficiency and Resource Managementmentioning

confidence: 99%

The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning

Kontar¹,

Shi²,

Yue³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The Internet of Things (IoT) is on the verge of a major paradigm shift. In the IoT system of the future, IoFT, the "cloud" will be substituted by the "crowd" where model training is brought to the edge, allowing IoT devices to collaboratively extract knowledge and build smart analytics/models while keeping their personal data stored locally. This paradigm shift was set into motion by the tremendous increase in computational power on IoT devices and the recent advances in decentralized and privacypreserving model training, coined as federated learning (FL). This article provides a vision for IoFT and a systematic overview of current efforts towards realizing this vision. Specifically, we first introduce the defining characteristics of IoFT and discuss FL data-driven approaches, opportunities, and challenges that allow decentralized inference within three dimensions: (i) a global model that maximizes utility across all IoT devices, (ii) a personalized model that borrows strengths across all devices yet retains its own model, (iii) a meta-learning model that quickly adapts to new devices or learning tasks. We end by describing the vision and challenges of IoFT in reshaping different industries through the lens of domain experts. Those industries include manufacturing, transportation, energy, healthcare, quality & reliability, business, and computing.

show abstract

GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning

Cited by 8 publications

References 23 publications

Improving Fairness via Federated Learning

Improving Fairness via Federated Learning

Fairness in Federated Learning for Spatial-Temporal Applications

The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning

Contact Info

Product

Resources

About