# Feature-Aware One-Shot Federated Learning via Hierarchical Token Sequences

arXiv: https://arxiv.org/abs/2601.03882 · HTML: https://mlsanity.com/paper/2601.03882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Federated, robust and private distillation, one of 12 directions in Knowledge distillation.
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- Knowledge distillation / [Federated, robust and private distillation](https://mlsanity.com/distill/federated-robust-and-private-distillation/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Threats to Federated Learning: A Survey](https://mlsanity.com/paper/2003.02133/) (2020)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [Distilled One-Shot Federated Learning](https://mlsanity.com/paper/2009.07999/) (2020)
- [LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets](https://mlsanity.com/paper/2008.03371/) (2020)
- [Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting](https://mlsanity.com/paper/2402.15070/) (2024)
- [Federated Generative Learning with Foundation Models](https://mlsanity.com/paper/2306.16064/) (2023)
- [FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Models](https://mlsanity.com/paper/2407.19953/) (2024)
- [One-shot Federated Learning via Synthetic Distiller-Distillate Communication](https://mlsanity.com/paper/2412.05186/) (2024)
- [Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space](https://mlsanity.com/paper/2312.09817/) (2023)
- [One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models](https://mlsanity.com/paper/2311.08870/) (2023)

## Abstract (arXiv)

One-shot federated learning (OSFL) reduces the communication cost and privacy risks of iterative federated learning by constructing a global model with a single round of communication. However, most existing methods struggle to achieve robust performance on real-world domains such as medical imaging, or are inefficient when handling non-IID (Independent and Identically Distributed) data. To address these limitations, we introduce FALCON, a framework that enhances the effectiveness of OSFL over non-IID image data. The core idea of FALCON is to leverage the feature-aware hierarchical token sequences generation and knowledge distillation into OSFL. First, each client leverages a pretrained visual encoder with hierarchical scale encoding to compress images into hierarchical token sequences, which capture multi-scale semantics. Second, a multi-scale autoregressive transformer generator is used to model the distribution of these token sequences and generate the synthetic sequences. Third, clients upload the synthetic sequences along with the local classifier trained on the real token sequences to the server. Finally, the server incorporates knowledge distillation into global training to reduce reliance on precise distribution modeling. Experiments on medical and natural image datasets validate the effectiveness of FALCON in diverse non-IID scenarios, outperforming the best OSFL baselines by 9.58% in average accuracy.