This is a PyTorch[1] implemention of the real-world problem part of paper Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients[2].
I am not a participant in the article, and a lot of code in this link is referenced.
The notebooks can be run on Kaggle. But you need to add the data to your workspace firstly.
[1] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” in Advances in neural information processing systems, 2019, pp. 8026–8037.
[2] Lu, Nan, et al. "Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients." arXiv preprint arXiv:2204.03304 (2022).