Skip to main content
SpringerLink
Log in

Refiner: a reliable and efficient incentive-driven federated learning system powered by blockchain

  • Regular Paper
  • Published:
The VLDB Journal Aims and scope Submit manuscript

Abstract

Federated learning (FL) enables learning a model from data distributed across numerous workers while preserving data privacy. However, the classical FL technique is designed for Web2 applications where participants are trusted to produce correct computation results. Moreover, classical FL workers are assumed to voluntarily contribute their computational resources and have the same learning speed. Therefore, the classical FL technique is not applicable to Web3 applications, where participants are untrusted and self-interested players with potentially malicious behaviors and heterogeneous learning speeds. This paper proposes Refiner, a novel blockchain-powered decentralized FL system for Web3 applications. Refiner addresses the challenges introduced by Web3 participants by extending the classical FL technique with three interoperative extensions: (1) an incentive scheme for attracting self-interested participants, (2) a two-stage audit scheme for preventing malicious behavior, and (3) an incentive-aware semi-synchronous learning scheme for handling heterogeneous workers. We provide theoretical analyses of the security and efficiency of Refiner. Extensive experimental results on the CIFAR-10 and Shakespeare datasets confirm the effectiveness, security, and efficiency of Refiner.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Algorithm 1
Algorithm 2
Algorithm 3
Algorithm 4
Algorithm 5
Algorithm 6
Algorithm 7
Algorithm 8
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., Shmatikov, V.: How to backdoor federated learning. In: AISTATS, vol. 108, pp. 2938–2948 (2020)

  2. Bhagoji, A.N., Chakraborty, S., Mittal, P., Calo, S.: Analyzing federated learning through an adversarial lens. In: ICML, vol. 97, pp. 634–643 (2019)

  3. Blanchard, P., Mhamdi, E.M.E., Guerraoui, R., Stainer, J.: Machine learning with adversaries: Byzantine tolerant gradient descent. In: NeurIPS (2017)

  4. Buterin, V.: A next-generation smart contract and decentralized application platform (2014)

  5. Caldas, S., Wu, P., Li, T., Konecný, J., McMahan, H.B., Smith, V., Talwalkar, A.: LEAF: a benchmark for federated settings. In: NeurIPS Workshop (2019)

  6. Cao, L.: Decentralized AI: edge intelligence and smart blockchain, metaverse, Web3, and DeSci. IEEE Intell. Syst. 37, 6–19 (2022)

    Google Scholar 

  7. Desai, H.B., Ozdayi, M.S., Kantarcioglu, M.: BlockFLA: Accountable federated learning via hybrid blockchain architecture. In: CODASPY (2021)

  8. Dirir, A.M., Salah, K., Svetinovic, D., Jayaraman, R., Yaqoob, I., Kanhere, S.S.: Blockchain-based decentralized federated learning. In: BCCA pp. 99–106 (2022)

  9. Fan, S., Zhang, H., Wang, Z., Cai, W.: Mobile devices strategies in blockchain-based federated learning: a dynamic game perspective. In: IEEE TNSE, pp. 1–13 (2022)

  10. Fan, S., Zhang, H., Zeng, Y., Cai, W.: Hybrid blockchain-based resource trading system for federated learning in edge computing. IOT 8, 2252–2264 (2021)

    Google Scholar 

  11. Feng, L., Zhao, Y., Guo, S., Qiu, X., Li, W., Peng, Y.: BAFL: a blockchain-based asynchronous federated learning framework. IEEE Trans. Comput. 71, 1092–1103 (2022)

    Article  Google Scholar 

  12. Gilad, Y., Hemo, R., Micali, S., Vlachos, G., Zeldovich, N.: Algorand: scaling byzantine agreements for cryptocurrencies. In: SOSP, pp. 51–68 (2017)

  13. Issa, W., Moustafa, N., Turnbull, B.P., Sohrabi, N., Tari, Z.: Blockchain-based federated learning for securing internet of things: a comprehensive survey. ACM Comput. Surv. 1–37 (2022)

  14. Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S.J., Stich, S.U., Suresh, A.T.: Scaffold: stochastic controlled averaging for federated learning. In: ICML (2020)

  15. Kim, H., Park, J., Bennis, M., Kim, S.L.: Blockchained on-device federated learning. IEEE Commun. Lett. 24, 1279–1283 (2020)

    Article  Google Scholar 

  16. Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical Report, pp. 1–60 (2009)

  17. Li, T., Hu, S., Beirami, A., Smith, V.: Ditto: Fair and robust federated learning through personalization. In: ICML (2021)

  18. Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. In: MLSys, vol. 2, pp. 429–450 (2020)

  19. Li, Y., Chen, C., Liu, N., Huang, H., Zheng, Z., Yan, Q.: A blockchain-based decentralized federated learning framework with committee consensus. IEEE Netw. 35, 234–241 (2021)

    Article  Google Scholar 

  20. Liu, Y., Qu, Y., Xu, C., Hao, Z., Gu, B.: Blockchain-enabled asynchronous federated learning in edge computing. Sensors 21, 1–16 (2021)

    Google Scholar 

  21. Lu, Y., Tang, Q., Wang, G.: On enabling machine learning tasks atop public blockchains: a crowdsourcing approach. In: ICDMW, pp. 81–88 (2018)

  22. Ma, J., Naas, S.A., Sigg, S., Lyu, X.: Privacy-preserving federated learning based on multi-key homomorphic encryption. IJIS 37, 5880–5901 (2021)

    Google Scholar 

  23. Malewicz, G., Austern, M.H., Bik, A.J.C., Dehnert, J.C., Horn, I., Leiser, N., Czajkowski, G.: Pregel: a system for large-scale graph processing. In: SIGMOD (2010)

  24. McMahan, H.B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: AISTATS, vol. 54, pp. 1273–1282 (2017)

  25. Micali, S., Rabin, M., Vadhan, S.: Verifiable random functions. In: FOCS, pp. 120–130 (1999)

  26. Ming, W.Y., Hao, L.G., Yu, F.L., Mao, P.: Research on block chain defense against malicious attack in federated learning. In: ICBCT (2021)

  27. Moudoud, H., Cherkaoui, S., Khoukhi, L.: Towards a secure and reliable federated learning using blockchain. In: IEEE GLOBECOM, pp. 1–6 (2021)

  28. Mugunthan, V., Rahman, R., Kagal, L.: Blockflow: Decentralized, privacy-preserving, and accountable federated machine learning. BLOCKCHAIN 320 (2021)

  29. Nakamoto, S.: Bitcoin: a peer-to-peer electronic cash system (2008)

  30. Nelaturu, K., Beillahi, S.M., Long, F., Veneris, A.G.: Smart contracts refinement for gas optimization. In: BRAINS, pp. 229–236 (2021)

  31. Nguyen, Q.T., Do, B.S., Nguyen, T.T., Do, B.L.: GasSaver: a tool for solidity smart contract optimization. In: ACM BSCI (2022)

  32. OpenAI’s GPT-3: a technical overview. https://lambdalabs.com/blog/demystifying-gpt-3

  33. Park, J., Lim, H.K.: Privacy-preserving federated learning using homomorphic encryption. Appl. Sci. (2022)

  34. Ramanan, P., Nakayama, K., Sharma, R.K.: Baffle: blockchain based aggregator free federated learning. In: IEEE Blockchain, pp. 72–81 (2020)

  35. Saldanha, O.L., Quirke, P., West, N.P., Jacqueline, A., James, E.: Swarm learning for decentralized artificial intelligence in cancer histopathology. Nat. Med. 28, 1232–1239 (2021)

    Article  Google Scholar 

  36. Shorten, C., Khoshgoftaar, T.: A survey on image data augmentation for deep learning. J. Big Data 6, 1–48 (2019)

    Article  Google Scholar 

  37. Sprague, M.R., Jalalirad, A., Scavuzzo, M., Capota, C., Neun, M., Do, L., Kopp, M.: Asynchronous federated learning for geospatial applications. In: ECML PKDD, pp. 21–28 (2019)

  38. Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., Khazaeni, Y.: Federated learning with matched averaging. In: ICLR (2020)

  39. Warnat-Herresthal, S., Schultze, H., Shastry, K., Sathyanarayanan Manamohan, E.: Swarm learning for decentralized and confidential clinical machine learning. Nature 594, 265–270 (2021)

    Article  Google Scholar 

  40. Web2 v.s. Web3: What’s the difference? https://www.algorand.foundation/news/web2-vs-web3

  41. Web3’s most accurate gas fee prediction. https://www.blocknative.com/gas-estimator

  42. Weng, J., Weng, J., Zhang, J., Li, M., Zhang, Y., Luo, W.: Deepchain: auditable and privacy-preserving deep learning with blockchain-based incentive. TDSC 18(5), 2438–2455 (2021)

    Google Scholar 

  43. Wood, G.: Ethereum: a secure decentralised generalised transaction ledger. Ethereum Proj. Yellow Pap. 151, 1–32 (2014)

    Google Scholar 

  44. Xie, C., Koyejo, O., Gupta, I.: Asynchronous federated optimization. In: OPT (2019)

  45. Xu, C., Qu, Y., Eklund, P.W., Xiang, Y., Gao, L.: BAFL: an efficient blockchain-based asynchronous federated learning framework. In: ISCC, pp. 1–6 (2021)

  46. Byzantine-robust distributed learning: Yin, D., Chen, Y., Kannan, R., Bartlett, P. Towards optimal statistical rates. In: ICML, vol. 80, pp. 5650–5659 (2018)

  47. Yuan, S., Cao, B., Peng, M., Sun, Y.: ChainsFL: blockchain-driven federated learning from design to realization. In: IEEE WCNC, pp. 1–6 (2021)

  48. Zhang, Z., Dong, D., Ma, Y., Ying, Y., Jiang, D., Chen, K., Shou, L.: Refiner: a reliable incentive-driven federated learning system powered by blockchain. PVLDB 14, 2659–2662 (2021)

    Google Scholar 

Download references

Acknowledgements

This work was funded by National Key Research and Development Project (Grant No: 2022YFB2703100).

Author information

Authors and Affiliations

  1. The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China

    Hong Lin, Ke Chen, Dawei Jiang, Lidan Shou & Gang Chen

Authors
  1. Hong Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ke Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dawei Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lidan Shou
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Gang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lidan Shou.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lin, H., Chen, K., Jiang, D. et al. Refiner: a reliable and efficient incentive-driven federated learning system powered by blockchain. The VLDB Journal 33, 807–831 (2024). https://doi.org/10.1007/s00778-024-00839-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00778-024-00839-y

Keywords

Search

Navigation