# Research **URL:** https://discuss.flower.ai/c/research/9.md [Latest](https://discuss.flower.ai/latest.md) · [Categories](https://discuss.flower.ai/categories.md) · [Tags](https://discuss.flower.ai/tags.md) --- ## [About the Research category](https://discuss.flower.ai/t/about-the-research-category/31)
**Author:** [@flower](https://discuss.flower.ai/u/flower)\ **Replies:** 0
Post your papers and research projects here. Use this category to get feedback or discuss interesting topics. --- ## [Implementing an MCU Client](https://discuss.flower.ai/t/implementing-an-mcu-client/1266)
**Author:** [@neonduck](https://discuss.flower.ai/u/neonduck)\ **Replies:** 2\ **Last updated:** [August 24, 2026, 1:13pm UTC](https://discuss.flower.ai/t/implementing-an-mcu-client/1266 "2026-08-24T13:13:02Z")
Hi, I want to propose a possible solution on how to use MCUs such as ESP32 using Flower. My students implemented this project and presented a working example. --- ## [Clustered Federated AI](https://discuss.flower.ai/t/clustered-federated-ai/1085)
**Author:** [@williamlm](https://discuss.flower.ai/u/williamlm)\ **Replies:** 0\ **Last updated:** [August 20, 2025, 4:05pm UTC](https://discuss.flower.ai/t/clustered-federated-ai/1085 "2025-08-20T16:05:16Z")
Hi everyone, We are exploring the idea clustered federated learning systems. Potential benefits include: • Intuitive use-cases where data can be clustered. • Better handling of data through homogeneous datasets, Oppo… --- ## [MyceliumWebServer - Self-propagating, fediverse-based federated learning](https://discuss.flower.ai/t/myceliumwebserver-self-propagating-fediverse-based-federated-learning/975)
**Author:** [@blueberry](https://discuss.flower.ai/u/blueberry)\ **Replies:** 1\ **Last updated:** [August 5, 2025, 6:35pm UTC](https://discuss.flower.ai/t/myceliumwebserver-self-propagating-fediverse-based-federated-learning/975 "2025-08-05T18:35:36Z")
Research projects, which aims to create a web of self-learning, self-propagating AI agents, which can freely choose learning groups in a structure similar to the Fediverse. Most interesting to me would be whether this i… --- ## [Feedback on Federated Learning Uni-seminar Project](https://discuss.flower.ai/t/feedback-on-federated-learning-uni-seminar-project/282)
**Author:** [@emrecanyerlikaya](https://discuss.flower.ai/u/emrecanyerlikaya)\ **Replies:** 1\ **Last updated:** [July 21, 2025, 11:35am UTC](https://discuss.flower.ai/t/feedback-on-federated-learning-uni-seminar-project/282 "2025-07-21T11:35:44Z")
Hi Flower community! We are currently working on a project where we forecast hourly energy consumption using “SmartMeter Energy Consumption Data” provided by London Datastore. (SmartMeter Energy Consumption Data in Lond… --- ## [Mycelium Net - Training ML models with switching nodes based on Flower AI](https://discuss.flower.ai/t/mycelium-net-training-ml-models-with-switching-nodes-based-on-flower-ai/1001)
**Author:** [@blueberry](https://discuss.flower.ai/u/blueberry)\ **Replies:** 4\ **Last updated:** [June 20, 2025, 4:35am UTC](https://discuss.flower.ai/t/mycelium-net-training-ml-models-with-switching-nodes-based-on-flower-ai/1001 "2025-06-20T04:35:40Z")
A prototype implementation of a “network of ML networks” - an internet-like protocol for federated learning where nodes can discover, join, and migrate between different learning groups based on performance metrics. W… --- ## [Aggregation algorithms](https://discuss.flower.ai/t/aggregation-algorithms/187)
**Author:** [@logic-magician](https://discuss.flower.ai/u/logic-magician)\ **Replies:** 1\ **Last updated:** [April 2, 2024, 1:17pm UTC](https://discuss.flower.ai/t/aggregation-algorithms/187 "2024-04-02T13:17:25Z")
Hello everyone, I am currently working on the experimental section of my paper. Since this is my first time using federated learning in my tasks, I need to conduct an experiment by trying different federated learning agg… --- ## [Gradient Based Subsampling - Federated XGBoost](https://discuss.flower.ai/t/gradient-based-subsampling-federated-xgboost/128)
**Author:** [@user1](https://discuss.flower.ai/u/user1)\ **Replies:** 1\ **Last updated:** [March 5, 2024, 4:11pm UTC](https://discuss.flower.ai/t/gradient-based-subsampling-federated-xgboost/128 "2024-03-05T16:11:34Z")
Hi everyone, What happens (in practice and theoretically) when enabling gradient\_based subsampling (see parameters for more information)? From my understanding, gradient based subsampling is based on Mimimal Variance S… --- ## [Paper on bagging aggregation strategy used for XGBoost?](https://discuss.flower.ai/t/paper-on-bagging-aggregation-strategy-used-for-xgboost/114)
**Author:** [@flower](https://discuss.flower.ai/u/flower)\ **Replies:** 0\ **Last updated:** [February 29, 2024, 4:28pm UTC](https://discuss.flower.ai/t/paper-on-bagging-aggregation-strategy-used-for-xgboost/114 "2024-02-29T16:28:44Z")
This question was migrated from the Slack channel #questions. Original Question: Hello everyone, can someone point me to the paper (if it exists) that proposes the bagging aggregation strategy used for XGBoost? Answe…