Proceedings

CoFL: Consensus Driven Human-AI Collaborative Federated Learning

Zeyuan Cai, Yao Zhang, Zhiwen Yu, Jiaqi Liu, Yuchang Sun, Chenhao Ma, Yilin Zhao

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 3567-3575.

https://doi.org/10.24963/ijcai.2026/397

Keywords

  • Humans and AI: Human computation and crowdsourcing
  • Humans and AI: Human-AI collaboration

Abstract

Federated learning (FL) has emerged as a distributed machine learning paradigm due to its privacy-preserving advantages. Most FL studies assume offline labeled datasets are available at clients. In practice, however, client data often arrive without labels in a streaming manner, making label acquisition a crucial problem. Existing solutions typically rely on human experts or artificial intelligence (AI) models for annotation. Nevertheless, due to the subjectivity among human experts and the inherent limitations of AI models, the labels they provide are often unreliable. In this work, we propose CoFL, a novel consensus driven human-AI collaborative FL method, which utilizes the complementarity between humans and AI models to produce more reliable labels. Moreover, CoFL leverages cross-client consensus among human experts to further enhance the collaboration process. Experiments on three datasets demonstrate that CoFL consistently outperforms baseline methods under various settings. The code is available at https://github.com/huaiguang233/CoFL.

Zeyuan Cai, Yao Zhang, Zhiwen Yu, Jiaqi Liu, Yuchang Sun, Chenhao Ma, and Yilin Zhao. 2026. CoFL: Consensus Driven Human-AI Collaborative Federated Learning. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 3567–3575. https://doi.org/10.24963/ijcai.2026/397
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards