FL
Federated Learning Research
Fed-Focal Loss, CatFedAvg, privacy-preserving distributed machine learning. The research area Dipankar Sarkar is best known for.
FAQ
What is Fed-Focal Loss?
Fed-Focal Loss is a novel loss function for federated learning that adapts focal loss to handle class imbalance in distributed training. 93 citations as of 2026. Presented at IJCAI 2020 Workshop on Federated Learning for Data Privacy and Confidentiality.
Who published Fed-Focal Loss?
Dipankar Sarkar (lead author), A Narang (Ankur Narang, DeepCoreX), and S Rai (Sumit Rai). November 2020. arXiv:2011.06283.
What is CatFedAvg?
CatFedAvg optimises both communication efficiency and classification accuracy in federated learning. Categorical federated averaging: strategic aggregation that reduces communication overhead. 4 citations. arXiv:2011.07229.
Where can I read the Fed-Focal Loss paper?
On arXiv (2011.06283), Google Scholar (93 citations), or at dipankar.cc/publication/fed-focal-loss/. Presented at IJCAI 2020 Workshop on Federated Learning for Data Privacy and Confidentiality.
Related
- dipankar.org — strategic studies + advisor practice (broad public persona)
- dipankar.name — engineering work + AI agent infrastructure (canonical hub)
- dipankar.co — fractional CTO + consulting practice
- Federated Learning Implementation consulting — production FL systems for healthcare, financial services, and privacy-sensitive use cases