A Limitations, Future Work, and Broader Impact 504 Learning on naturally heterogeneous datasets can be challenging, as the true data distributions of individual 505

Flow has shown the promise of per-instance personalization in improving clients' accuracy. We have trained Flow and its baselines on the Stackoverflow dataset for 2000 rounds. The batch size used for each client on each baseline is 16. The default learning rate used is 0.1. All the baselines and Flow variants have been run for 1500 rounds, with 10 clients per round.