# Catastrophic Forgetting Resilient One-Shot Incremental Federated Learning

arXiv: https://arxiv.org/abs/2602.17625 · HTML: https://mlsanity.com/paper/2602.17625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Federated Class-Incremental Learning](https://mlsanity.com/paper/2203.11473/) (2022)
- [One-Shot Federated Learning](https://mlsanity.com/paper/1902.11175/) (2019)
- [Distilled One-Shot Federated Learning](https://mlsanity.com/paper/2009.07999/) (2020)
- [DENSE: Data-Free One-Shot Federated Learning](https://mlsanity.com/paper/2112.12371/) (2021)
- [No One Left Behind: Real-World Federated Class-Incremental Learning](https://mlsanity.com/paper/2302.00903/) (2023)
- [Towards Efficient Replay in Federated Incremental Learning](https://mlsanity.com/paper/2403.05890/) (2024)
- [FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Models](https://mlsanity.com/paper/2407.19953/) (2024)
- [From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcare](https://mlsanity.com/paper/2409.09727/) (2024)
- [Federated Continual Learning: Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2502.07059/) (2025)
- [Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models](https://mlsanity.com/paper/2405.01494/) (2024)
- [One-Shot Federated Learning with Classifier-Free Diffusion Models](https://mlsanity.com/paper/2502.08488/) (2025)
- [Federated Continual Learning for Socially Aware Robotics](https://mlsanity.com/paper/2201.05527/) (2022)
- [Cyclical Weight Consolidation: Towards Solving Catastrophic Forgetting in Serial Federated Learning](https://mlsanity.com/paper/2405.10647/) (2024)
- [Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning](https://mlsanity.com/paper/2505.12318/) (2025)

## Abstract (arXiv)

Modern big-data systems generate massive, heterogeneous, and geographically dispersed streams that are large-scale and privacy-sensitive, making centralization challenging. While federated learning (FL) provides a privacy-enhancing training mechanism, it assumes a static data flow and learns a collaborative model over multiple rounds, making learning with textitincremental data challenging in limited-communication scenarios. This paper presents One-Shot Incremental Federated Learning (OSI-FL), the first FL framework that addresses the dual challenges of communication overhead and catastrophic forgetting. OSI-FL communicates category-specific embeddings, devised by a frozen vision-language model (VLM) from each client in a single communication round, which a pre-trained diffusion model at the server uses to synthesize new data similar to the client's data distribution. The synthesized samples are used on the server for training. However, two challenges still persist: i) tasks arriving incrementally need to retrain the global model, and ii) as future tasks arrive, retraining the model introduces catastrophic forgetting. To this end, we augment training with Selective Sample Retention (SSR), which identifies and retains the top-p most informative samples per category and task pair based on sample loss. SSR bounds forgetting by ensuring that representative retained samples are incorporated into training in further iterations. The experimental results indicate that OSI-FL outperforms baselines, including traditional and one-shot FL approaches, in both class-incremental and domain-incremental scenarios across three benchmark datasets.