Towards Fairness-Aware Federated Learning.

Recent advances in federated learning (FL) have brought large-scale collaborative machine learning opportunities for massively distributed clients with performance and data privacy guarantees. However, most current works focus on the interest of the central controller in FL and overlook the interests of the FL clients. This may result in unfair treatment of clients, which discourages them from actively participating in the learning process and damages the sustainability of the FL ecosystem. Therefore, the topic of ensuring fairness in FL is attracting a great deal of research interest. In recent years, diverse fairness-aware FL (FAFL) approaches have been proposed in an effort to achieve fairness in FL from different perspectives. However, there is no comprehensive survey that helps readers gain insight into this interdisciplinary field. This article aims to provide such a survey. By examining the fundamental and simplifying assumptions, as well as the notions of fairness adopted by the existing literature in this field, we propose a taxonomy of FAFL approaches covering major steps in FL, including client selection, optimization, contribution evaluation, and incentive distribution. In addition, we discuss the main metrics for experimentally evaluating the performance of FAFL approaches and suggest promising future research directions toward FAFL.

[1]  Xuan Zhang,et al.  A Fair and Efficient Hybrid Federated Learning Framework based on XGBoost for Distributed Power Prediction , 2022, ArXiv.

[2]  Lizhen Cui,et al.  GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning , 2021, ACM Trans. Intell. Syst. Technol..

[3]  Fei Wang,et al.  Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning , 2021, NeurIPS.

[4]  Siddharth Divi,et al.  New Metrics to Evaluate the Performance and Fairness of Personalized Federated Learning , 2021, ArXiv.

[5]  Rongfei Zeng,et al.  A Comprehensive Survey of Incentive Mechanism for Federated Learning , 2021, ArXiv.

[6]  Sung Kuk Shyn,et al.  FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learning , 2021, ArXiv.

[7]  Tony Q. S. Quek,et al.  Reputation-Based Federated Learning for Secure Wireless Networks , 2021, IEEE Internet of Things Journal.

[8]  Pengyuan Zhou,et al.  Loss Tolerant Federated Learning , 2021, ArXiv.

[9]  Jianzhong Qi,et al.  Federated Learning with Fair Averaging , 2021, IJCAI.

[10]  Ernesto Damiani,et al.  TrustFed: A Framework for Fair and Trustworthy Cross-Device Federated Learning in IIoT , 2021, IEEE Transactions on Industrial Informatics.

[11]  Jingwen Zhang,et al.  Incentive Mechanism for Horizontal Federated Learning Based on Reputation and Reverse Auction , 2021, WWW.

[12]  Song Guo,et al.  A Survey of Incentive Mechanism Design for Federated Learning , 2021, IEEE Transactions on Emerging Topics in Computing.

[13]  Qiang Yang,et al.  Towards Personalized Federated Learning , 2021, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Nicholas D. Lane,et al.  FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout , 2021, NeurIPS.

[15]  Marco Canini,et al.  On the Impact of Device and Behavioral Heterogeneity in Federated Learning , 2021, ArXiv.

[16]  Ali Dehghantanha,et al.  A survey on security and privacy of federated learning , 2021, Future Gener. Comput. Syst..

[17]  Virginia Smith,et al.  Ditto: Fair and Robust Federated Learning Through Personalization , 2020, ICML.

[18]  Hongbin Zhu,et al.  Federated Learning with Class Imbalance Reduction , 2020, 2021 29th European Signal Processing Conference (EUSIPCO).

[19]  Lingjuan Lyu,et al.  Towards Building a Robust and Fair Federated Learning System , 2020, ArXiv.

[20]  Lingjuan Lyu,et al.  A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning , 2020, 2011.10464.

[21]  Albert Y. Zomaya,et al.  Stochastic Client Selection for Federated Learning With Volatile Clients , 2020, IEEE Internet of Things Journal.

[22]  Xin Liu,et al.  Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learning , 2020, IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[23]  Albert Y. Zomaya,et al.  An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee , 2020, IEEE Transactions on Parallel and Distributed Systems.

[24]  Osman Yagan,et al.  Bandit-based Communication-Efficient Client Selection Strategies for Federated Learning , 2020, 2020 54th Asilomar Conference on Signals, Systems, and Computers.

[25]  Hanghang Tong,et al.  Fairness-aware Agnostic Federated Learning , 2020, SDM.

[26]  Jianyu Wang,et al.  Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies , 2020, ArXiv.

[27]  Choong Seon Hong,et al.  An Incentive Mechanism for Federated Learning in Wireless Cellular Networks: An Auction Approach , 2020, IEEE Transactions on Wireless Communications.

[28]  Takayuki Nishio,et al.  Estimation of Individual Device Contributions for Incentivizing Federated Learning , 2020, 2020 IEEE Globecom Workshops (GC Wkshps.

[29]  Dawn Song,et al.  A Principled Approach to Data Valuation for Federated Learning , 2020, Federated Learning.

[30]  Lingjuan Lyu,et al.  Collaborative Fairness in Federated Learning , 2020, Federated Learning.

[31]  Han Yu,et al.  A VCG-based Fair Incentive Mechanism for Federated Learning , 2020, ArXiv.

[32]  Kin K. Leung,et al.  Energy-Efficient Resource Management for Federated Edge Learning With CPU-GPU Heterogeneous Computing , 2020, IEEE Transactions on Wireless Communications.

[33]  Haris Vikalo,et al.  Communication-Efficient Federated Learning via Optimal Client Sampling , 2020, LatinX in AI at International Conference on Machine Learning 2020.

[34]  Kartik Sreenivasan,et al.  Attack of the Tails: Yes, You Really Can Backdoor Federated Learning , 2020, NeurIPS.

[35]  Hao Wang,et al.  Optimizing Federated Learning on Non-IID Data with Reinforcement Learning , 2020, IEEE INFOCOM 2020 - IEEE Conference on Computer Communications.

[36]  Qi Li,et al.  Enabling Execution Assurance of Federated Learning at Untrusted Participants , 2020, IEEE INFOCOM 2020 - IEEE Conference on Computer Communications.

[37]  Yaoliang Yu,et al.  FedMGDA+: Federated Learning meets Multi-objective Optimization , 2020, ArXiv.

[38]  Antonio Robles-Kelly,et al.  Hierarchically Fair Federated Learning , 2020, ArXiv.

[39]  Han Yu,et al.  Threats to Federated Learning: A Survey , 2020, ArXiv.

[40]  X. Chu,et al.  FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC , 2020, 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS).

[41]  Tianjian Chen,et al.  A Fairness-aware Incentive Scheme for Federated Learning , 2020, AIES.

[42]  Miao Pan,et al.  Federated Learning in Vehicular Edge Computing: A Selective Model Aggregation Approach , 2020, IEEE Access.

[43]  S. Levine,et al.  Gradient Surgery for Multi-Task Learning , 2020, NeurIPS.

[44]  Yang Liu,et al.  Federated Learning , 2019, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[45]  Richard Nock,et al.  Advances and Open Problems in Federated Learning , 2019, Found. Trends Mach. Learn..

[46]  Shuyue Wei,et al.  Profit Allocation for Federated Learning , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[47]  Walid Saad,et al.  Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism , 2019, IEEE Communications Magazine.

[48]  Shashi Raj Pandey,et al.  A Crowdsourcing Framework for On-Device Federated Learning , 2019, IEEE Transactions on Wireless Communications.

[49]  Mohsen Guizani,et al.  Reliable Federated Learning for Mobile Networks , 2019, IEEE Wireless Communications.

[50]  Anuj Kumar,et al.  Active Federated Learning , 2019, ArXiv.

[51]  Leandros Tassiulas,et al.  Model Pruning Enables Efficient Federated Learning on Edge Devices , 2019, IEEE transactions on neural networks and learning systems.

[52]  Wei Yang Bryan Lim,et al.  Federated Learning in Mobile Edge Networks: A Comprehensive Survey , 2019, IEEE Communications Surveys & Tutorials.

[53]  Sercan O. Arik,et al.  Data Valuation using Reinforcement Learning , 2019, ICML.

[54]  Ziye Zhou,et al.  Measure Contribution of Participants in Federated Learning , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[55]  Shengli Xie,et al.  Incentive Mechanism for Reliable Federated Learning: A Joint Optimization Approach to Combining Reputation and Contract Theory , 2019, IEEE Internet of Things Journal.

[56]  Kristina Lerman,et al.  A Survey on Bias and Fairness in Machine Learning , 2019, ACM Comput. Surv..

[57]  Xia Hu,et al.  Fairness in Deep Learning: A Computational Perspective , 2019, IEEE Intelligent Systems.

[58]  Anit Kumar Sahu,et al.  Federated Learning: Challenges, Methods, and Future Directions , 2019, IEEE Signal Processing Magazine.

[59]  Yunus Sarikaya,et al.  Motivating Workers in Federated Learning: A Stackelberg Game Perspective , 2019, IEEE Networking Letters.

[60]  Reza Shokri,et al.  On the Privacy Risks of Model Explanations , 2019, AIES.

[61]  Jiong Jin,et al.  Towards Fair and Privacy-Preserving Federated Deep Models , 2019, IEEE Transactions on Parallel and Distributed Systems.

[62]  Tian Li,et al.  Fair Resource Allocation in Federated Learning , 2019, ICLR.

[63]  Masahiro Morikura,et al.  Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data , 2019, ICC 2020 - 2020 IEEE International Conference on Communications (ICC).

[64]  Ying-Chang Liang,et al.  Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach , 2019, 2019 IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS).

[65]  James Y. Zou,et al.  Data Shapley: Equitable Valuation of Data for Machine Learning , 2019, ICML.

[66]  Costas J. Spanos,et al.  Towards Efficient Data Valuation Based on the Shapley Value , 2019, AISTATS.

[67]  Tianjian Chen,et al.  Federated Machine Learning: Concept and Applications , 2019 .

[68]  Mehryar Mohri,et al.  Agnostic Federated Learning , 2019, ICML.

[69]  Anit Kumar Sahu,et al.  Federated Optimization in Heterogeneous Networks , 2018, MLSys.

[70]  Ying-Chang Liang,et al.  Joint Service Pricing and Cooperative Relay Communication for Federated Learning , 2018, 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData).

[71]  Sebastian Caldas,et al.  Expanding the Reach of Federated Learning by Reducing Client Resource Requirements , 2018, ArXiv.

[72]  Ninghui Li,et al.  Privacy at Scale: Local Dierential Privacy in Practice , 2018 .

[73]  Takayuki Nishio,et al.  Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge , 2018, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[74]  Krishna P. Gummadi,et al.  Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment , 2016, WWW.

[75]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[76]  Michael J. Dinneen,et al.  A Hybrid Geometric Approach for Measuring Similarity Level Among Documents and Document Clustering , 2016, 2016 IEEE Second International Conference on Big Data Computing Service and Applications (BigDataService).

[77]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[78]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[79]  A. Bifet,et al.  A survey on concept drift adaptation , 2014, ACM Comput. Surv..

[80]  Chunyan Miao,et al.  A Survey of Multi-Agent Trust Management Systems , 2013, IEEE Access.

[81]  A. Anonymous,et al.  Consumer Data Privacy in a Networked World: A Framework for Protecting Privacy and Promoting Innovation in the Global Digital Economy , 2013, J. Priv. Confidentiality.

[82]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[83]  Yong Zhang,et al.  A Novel Reputation Computation Model Based on Subjective Logic for Mobile Ad Hoc Networks , 2009, 2009 Third International Conference on Network and System Security.

[84]  Charu C. Aggarwal,et al.  On the Surprising Behavior of Distance Metrics in High Dimensional Spaces , 2001, ICDT.

[85]  Raj Jain,et al.  A Quantitative Measure Of Fairness And Discrimination For Resource Allocation In Shared Computer Systems , 1998, ArXiv.

[86]  Yeon-Koo Che.  Design competition through multidimensional auctions , 1993 .

[87]  L. Shapley.  A Value for n-person Games , 1988 .

[88]  J. Cruz,et al.  On the Stackelberg strategy in nonzero-sum games , 1973 .

[89]  Yongxin Tong,et al.  Efficient and Fair Data Valuation for Horizontal Federated Learning , 2020, Federated Learning.

[90]  Siu-Ming Yiu,et al.  A Game-Theoretic Framework for Incentive Mechanism Design in Federated Learning , 2020, Federated Learning.

[91]  Sreenivas Gollapudi,et al.  Profit Sharing and Efficiency in Utility Games , 2017, ESA.

[92]  Chuanlei Zhang,et al.  BTRES: Beta-based Trust and Reputation Evaluation System for wireless sensor networks , 2016, J. Netw. Comput. Appl..

[93]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[94]  Bastin Tony Roy Savarimuthu,et al.  Norm creation, spreading and emergence: A survey of simulation models of norms in multi-agent systems , 2011, Multiagent Grid Syst..

[95]  Peter Auer,et al.  The Nonstochastic Multiarmed Bandit Problem , 2002, SIAM J. Comput..

[96]  Audun Jøsang,et al.  AIS Electronic Library (AISeL) , 2017 .

[97]  M. Rabin.  Published by: American , 2022 .