A Framework for Incentivized Collaborative Learning

Collaborations among various entities, such as companies, research labs, AI agents, and edge devices, have become increasingly crucial for achieving machine learning tasks that cannot be accomplished by a single entity alone. This is likely due to factors such as security constraints, privacy concerns, and limitations in computation resources. As a result, collaborative learning (CL) research has been gaining momentum. However, a significant challenge in practical applications of CL is how to effectively incentivize multiple entities to collaborate before any collaboration occurs. In this study, we propose ICL, a general framework for incentivized collaborative learning, and provide insights into the critical issue of when and why incentives can improve collaboration performance. Furthermore, we show the broad applicability of ICL to specific cases in federated learning, assisted learning, and multi-armed bandit with both theory and experimental results.

[1]  A. Avestimehr,et al.  Federated Alternate Training (FAT): Leveraging Unannotated Data Silos in Federated Segmentation for Medical Imaging , 2023, ArXiv.

[2]  C. Julien,et al.  iDML: Incentivized Decentralized Machine Learning , 2023, ArXiv.

[3]  Muhammad Ali Gulzar,et al.  FedDebug: Systematic Debugging for Federated Learning Applications , 2023, 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE).

[4]  V. Tarokh,et al.  Personalized Federated Recommender Systems with Private and Partially Federated AutoEncoders , 2022, 2022 56th Asilomar Conference on Signals, Systems, and Computers.

[5]  Rong Yu,et al.  Incentivizing Semisupervised Vehicular Federated Learning: A Multidimensional Contract Approach With Bounded Rationality , 2022, IEEE Internet of Things Journal.

[6]  Novi Quadrianto,et al.  A Snapshot of the Frontiers of Client Selection in Federated Learning , 2022, Trans. Mach. Learn. Res..

[7]  Junshan Zhang,et al.  Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective , 2022, IEEE Transactions on Mobile Computing.

[8]  Alberto Blanco-Justicia,et al.  Defending against the Label-flipping Attack in Federated Learning , 2022, ArXiv.

[9]  Ahmad Faraz Khan,et al.  TIFF: Tokenized Incentive for Federated Learning , 2022, 2022 IEEE 15th International Conference on Cloud Computing (CLOUD).

[10]  W. Samek,et al.  Decentral and Incentivized Federated Learning Frameworks: A Systematic Literature Review , 2022, IEEE Internet of Things Journal.

[11]  Anit Kumar Sahu,et al.  Self-Aware Personalized Federated Learning , 2022, NeurIPS.

[12]  Anit Kumar Sahu,et al.  Federated Learning Challenges and Opportunities: An Outlook , 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  Xun Yang,et al.  Federated Learning Incentive Mechanism Design via Enhanced Shapley Value Method , 2022, Wireless Communications and Mobile Computing.

[14]  Yuezhou Wu,et al.  Online Auction-Based Incentive Mechanism Design for Horizontal Federated Learning with Budget Constraint , 2022, arXiv.org.

[15]  Shengshan Hu,et al.  Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning , 2021, 2022 IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom).

[16]  Bryan Kian Hsiang Low,et al.  Incentivizing Collaboration in Machine Learning via Synthetic Data Rewards , 2021, AAAI.

[17]  Dusit Niyato,et al.  Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective , 2021, IEEE Transactions on Cognitive Communications and Networking.

[18]  Han Yu,et al.  Towards Fairness-Aware Federated Learning. , 2021, IEEE transactions on neural networks and learning systems.

[19]  Han Yu,et al.  MarS-FL: Enabling Competitors to Collaborate in Federated Learning , 2021, IEEE Transactions on Big Data.

[20]  Jie Ding,et al.  Assisted Learning for Organizations with Limited Data , 2021, arXiv.org.

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

[22]  V. Tarokh,et al.  GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations , 2021, NeurIPS.

[23]  Vincent W. S. Wong,et al.  An Incentive Mechanism for Cross-Silo Federated Learning: A Public Goods Perspective , 2021, IEEE INFOCOM 2021 - IEEE Conference on Computer Communications.

[24]  Bingsheng He,et al.  Federated Learning on Non-IID Data Silos: An Experimental Study , 2021, 2022 IEEE 38th International Conference on Data Engineering (ICDE).

[25]  Peter Richtárik,et al.  Optimal Client Sampling for Federated Learning , 2020, Trans. Mach. Learn. Res..

[26]  Jie Ding,et al.  HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients , 2020, ICLR.

[27]  Jie Ding,et al.  Information Laundering for Model Privacy , 2020, ICLR.

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

[29]  Stefano Palminteri,et al.  Modelling Stock Markets by Multi-agent Reinforcement Learning , 2020, Computational Economics.

[30]  Mun Choon Chan,et al.  Collaborative Machine Learning with Incentive-Aware Model Rewards , 2020, ICML.

[31]  Jaewoo Kang,et al.  MAPS: Multi-Agent reinforcement learning-based Portfolio management System , 2020, IJCAI.

[32]  Yang Liu,et al.  A Sustainable Incentive Scheme for Federated Learning , 2020, IEEE Intelligent Systems.

[33]  Amir Salman Avestimehr,et al.  FedNAS: Federated Deep Learning via Neural Architecture Search , 2020, ArXiv.

[34]  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).

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

[36]  Deze Zeng,et al.  A Learning-Based Incentive Mechanism for Federated Learning , 2020, IEEE Internet of Things Journal.

[37]  Zhu Han,et al.  Incentivize to Build: A Crowdsourcing Framework for Federated Learning , 2019, 2019 IEEE Global Communications Conference (GLOBECOM).

[38]  Jinyuan Jia,et al.  Local Model Poisoning Attacks to Byzantine-Robust Federated Learning , 2019, USENIX Security Symposium.

[39]  Qun Li,et al.  FABA: An Algorithm for Fast Aggregation against Byzantine Attacks in Distributed Neural Networks , 2019, IJCAI.

[40]  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).

[41]  Rui Zhang,et al.  A Hybrid Approach to Privacy-Preserving Federated Learning , 2018, Informatik Spektrum.

[42]  Prateek Mittal,et al.  Analyzing Federated Learning through an Adversarial Lens , 2018, ICML.

[43]  Amos J. Storkey,et al.  School of Informatics, University of Edinburgh , 2022 .

[44]  Vitaly Shmatikov,et al.  How To Backdoor Federated Learning , 2018, AISTATS.

[45]  Yan Liu,et al.  Benchmarking deep learning models on large healthcare datasets , 2018, J. Biomed. Informatics.

[46]  Roger Wattenhofer,et al.  Teaching a Machine to Read Maps with Deep Reinforcement Learning , 2017, AAAI.

[47]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[48]  Jiwen Lu,et al.  3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[49]  David C. Kale,et al.  Multitask learning and benchmarking with clinical time series data , 2017, Scientific Data.

[50]  Peter Richtárik,et al.  Federated Learning: Strategies for Improving Communication Efficiency , 2016, ArXiv.

[51]  Joelle Pineau,et al.  An Actor-Critic Algorithm for Sequence Prediction , 2016, ICLR.

[52]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[53]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

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

[55]  Jia Xu,et al.  Incentive Mechanisms for Time Window Dependent Tasks in Mobile Crowdsensing , 2015, IEEE Transactions on Wireless Communications.

[56]  Jan Peters,et al.  Reinforcement learning in robotics: A survey , 2013, Int. J. Robotics Res..

[57]  Xi Fang,et al.  Crowdsourcing to smartphones: incentive mechanism design for mobile phone sensing , 2012, Mobicom '12.

[58]  Bogdan Carbunar,et al.  Fair Payments for Outsourced Computations , 2010, 2010 7th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks (SECON).

[59]  Eric Maskin,et al.  Mechanism Design: How to Implement Social Goals , 2008 .

[60]  Moni Naor,et al.  Our Data, Ourselves: Privacy Via Distributed Noise Generation , 2006, EUROCRYPT.

[61]  Haitao Zheng,et al.  Collaboration and fairness in opportunistic spectrum access , 2005, IEEE International Conference on Communications, 2005. ICC 2005. 2005.

[62]  Hervé Moulin,et al.  An Application of the Shapley Value to Fair Division with Money , 1992 .

[63]  L. Shapley,et al.  The Shapley Value , 1994 .

[64]  George F. Jenks,et al.  ERROR ON CHOROPLETHIC MAPS: DEFINITION, MEASUREMENT, REDUCTION , 1971 .

[65]  Fangxin Wang,et al.  FedAB: Truthful Federated Learning With Auction-Based Combinatorial Multi-Armed Bandit , 2023, IEEE Internet of Things Journal.

[66]  Jie Ding,et al.  Parallel Assisted Learning , 2022, IEEE Transactions on Signal Processing.

[67]  Yae Jee Cho,et al.  To Federate or Not To Federate: Incentivizing Client Participation in Federated Learning , 2022, ArXiv.

[68]  V. Tarokh,et al.  SemiFL: Communication Efficient Semi-Supervised Federated Learning with Unlabeled Clients , 2021, arXiv.org.

[69]  Vahid Tarokh,et al.  Privacy-Preserving Multi-Target Multi-Domain Recommender Systems with Assisted AutoEncoders , 2021, ArXiv.

[70]  Jie Ding,et al.  Assisted Learning: A Framework for Multi-Organization Learning , 2020, NeurIPS.

[71]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[72]  Lang Tong,et al.  Distributed Detection in the Presence of Byzantine Attacks , 2009, IEEE Transactions on Signal Processing.

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