# From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity

arXiv: https://arxiv.org/abs/2604.08617 · HTML: https://mlsanity.com/paper/2604.08617/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 50 of its 80 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 30 of 50)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Dynamical Variational Autoencoders: A Comprehensive Review](https://mlsanity.com/paper/2008.12595/) (2020)
- [Federated Class-Incremental Learning](https://mlsanity.com/paper/2203.11473/) (2022)
- [TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation](https://mlsanity.com/paper/2303.06937/) (2023)
- [FedGH: Heterogeneous Federated Learning with Generalized Global Header](https://mlsanity.com/paper/2303.13137/) (2023)
- [Better Generative Replay for Continual Federated Learning](https://mlsanity.com/paper/2302.13001/) (2023)
- [No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier](https://mlsanity.com/paper/2303.10058/) (2023)
- [Federated Continual Learning via Knowledge Fusion: A Survey](https://mlsanity.com/paper/2312.16475/) (2023)
- [Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems](https://mlsanity.com/paper/2012.03448/) (2020)
- [Federated Incremental Semantic Segmentation](https://mlsanity.com/paper/2304.04620/) (2023)
- [Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2308.03457/) (2023)
- [Towards Efficient Replay in Federated Incremental Learning](https://mlsanity.com/paper/2403.05890/) (2024)
- [Relaxed Contrastive Learning for Federated Learning](https://mlsanity.com/paper/2401.04928/) (2024)
- [Towards Universal Modal Tracking with Online Dense Temporal Token Learning](https://mlsanity.com/paper/2507.20177/) (2025)
- [Asynchronous Federated Continual Learning](https://mlsanity.com/paper/2304.03626/) (2023)
- [Few-shot Class-incremental Learning for Classification and Object Detection: A Survey](https://mlsanity.com/paper/2308.06764/) (2023)
- [Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning](https://mlsanity.com/paper/2409.01128/) (2024)
- [Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey](https://mlsanity.com/paper/2412.13840/) (2024)
- [Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking](https://mlsanity.com/paper/2507.21606/) (2025)
- [FedCross: Towards Accurate Federated Learning via Multi-Model Cross-Aggregation](https://mlsanity.com/paper/2210.08285/) (2022)
- [Federated Model Heterogeneous Matryoshka Representation Learning](https://mlsanity.com/paper/2406.00488/) (2024)
- [Exploiting Multi-Label Correlation in Label Distribution Learning](https://mlsanity.com/paper/2308.01742/) (2023)
- [Personalized Federated Continual Learning via Multi-granularity Prompt](https://mlsanity.com/paper/2407.00113/) (2024)
- [Text-Enhanced Data-free Approach for Federated Class-Incremental Learning](https://mlsanity.com/paper/2403.14101/) (2024)
- [Learning Equi-angular Representations for Online Continual Learning](https://mlsanity.com/paper/2404.01628/) (2024)
- [Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence](https://mlsanity.com/paper/2412.13779/) (2024)
- [FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models](https://mlsanity.com/paper/2510.27486/) (2025)

## Abstract (arXiv)

Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance estimation mechanisms to identify information-rich samples. However, they typically overlook strategies for effectively utilizing the selected exemplars, which limits their performance under continual dynamic heterogeneity across clients and tasks. To address this issue, this paper proposes a Federated gEometry-Aware correcTion method, termed FEAT, which alleviates imbalance-induced representation collapse that drags rare-class features toward frequent classes across clients. Specifically, it consists of two key modules: 1) the Geometric Structure Alignment module performs structural knowledge distillation by aligning the pairwise angular similarities between feature representations and their corresponding Equiangular Tight Frame prototypes, which are fixed and shared across clients to serve as a class-discriminative reference structure. This encourages geometric consistency across tasks and helps mitigate representation drift; 2) the Energy-based Geometric Correction module removes task-irrelevant directional components from feature embeddings, which reduces prediction bias toward majority classes. This improves sensitivity to minority classes and enhances the model's robustness under class-imbalanced distributions.