FedNovel: Federated Novel Class Learning

Lixu Wang, Chenxi Liu, Junfeng Guo, Jiahua Dong, Xiao Wang, Heng Huang, Qi Zhu

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Federated Learning, Novel Class Discovery, Continual Learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: The first study that can enable federated learning to continually discover and learn unseen novel class data while preserving privacy.

Abstract: In a privacy-focused era, Federated Learning (FL) has emerged as a promising machine learning technique. However, most existing FL studies assume that the data distribution remains nearly fixed over time, while real-world scenarios often involve dynamic and continual changes. To equip FL systems with continual model evolution capabilities, enabling them to discover and incorporate unseen novel classes, we focus on an important problem called *Federated Novel Class Learning* (FedNovel) in this work. The biggest challenge in FedNovel is to merge and align novel classes that are discovered and learned by different clients without compromising privacy. To address this, we propose a *Global Alignment Learning* (GAL) framework that can accurately estimate the global novel class number and provide effective guidance for local training from a global perspective, all while maintaining privacy protection. Specifically, GAL first locates high-density regions in the representation space through a bi-level clustering mechanism to estimate the novel class number, with which the global prototypes corresponding to novel classes can be constructed. Then, GAL uses a novel semantic weighted loss to capture all possible correlations between these prototypes and the training data for mitigating the impact of pseudo-label noise and data heterogeneity. Extensive experiments on various datasets demonstrate GAL's superior performance over state-of-the-art novel class discovery methods. In particular, GAL achieves significant improvements in novel-class performance, increasing the accuracy by 5.1\% to 10.6\% in the case of one novel class learning stage and by 7.8\% to 17.9\% in the case of two novel class learning stages, without sacrificing known-class performance. Moreover, GAL is shown to be effective in equipping a variety of different mainstream FL algorithms with novel class discovery and learning capability, highlighting its potential for many real-world applications.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5479