# Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coreset

arXiv: https://arxiv.org/abs/2506.12031 · HTML: https://mlsanity.com/paper/2506.12031/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 51 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [Federated Continual Learning with Weighted Inter-client Transfer](https://mlsanity.com/paper/2003.03196/) (2020)
- [Linear Mode Connectivity in Multitask and Continual Learning](https://mlsanity.com/paper/2010.04495/) (2020)
- [Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective](https://mlsanity.com/paper/2306.13092/) (2023)
- [Federated Class-Incremental Learning](https://mlsanity.com/paper/2203.11473/) (2022)
- [Online Coreset Selection for Rehearsal-based Continual Learning](https://mlsanity.com/paper/2106.01085/) (2021)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning](https://mlsanity.com/paper/2110.04593/) (2021)
- [TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation](https://mlsanity.com/paper/2303.06937/) (2023)
- [Better Generative Replay for Continual Federated Learning](https://mlsanity.com/paper/2302.13001/) (2023)
- [No One Left Behind: Real-World Federated Class-Incremental Learning](https://mlsanity.com/paper/2302.00903/) (2023)
- [Online Prototype Learning for Online Continual Learning](https://mlsanity.com/paper/2308.00301/) (2023)
- [Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning](https://mlsanity.com/paper/2404.00781/) (2024)
- [FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2202.13670/) (2022)
- [Eliminating Domain Bias for Federated Learning in Representation Space](https://mlsanity.com/paper/2311.14975/) (2023)
- [Federated Incremental Semantic Segmentation](https://mlsanity.com/paper/2304.04620/) (2023)
- [Bayesian Framework for Gradient Leakage](https://mlsanity.com/paper/2111.04706/) (2021)
- [Towards Efficient Replay in Federated Incremental Learning](https://mlsanity.com/paper/2403.05890/) (2024)
- [GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting](https://mlsanity.com/paper/2302.14307/) (2023)
- [Data Leakage in Federated Averaging](https://mlsanity.com/paper/2206.12395/) (2022)
- [Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching](https://mlsanity.com/paper/2407.05005/) (2024)
- [Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey](https://mlsanity.com/paper/2312.08667/) (2023)

## Built on by (most cited first, 1 of 1)

- [Communication-Efficient and Accurate Approach for Aggregation in Federated Low-Rank Adaptation](https://mlsanity.com/paper/2509.26399/) (2025)

## Abstract (arXiv)

Federated Continual Learning (FCL) has recently emerged as a crucial research area, as data from distributed clients typically arrives as a stream, requiring sequential learning. This paper explores a more practical and challenging FCL setting, where clients may have unrelated or even conflicting data and tasks. In this scenario, statistical heterogeneity and data noise can create spurious correlations, leading to biased feature learning and catastrophic forgetting. Existing FCL approaches often use generative replay to create pseudo-datasets of previous tasks. However, generative replay itself suffers from catastrophic forgetting and task divergence among clients, leading to overfitting in FCL. Existing FCL approaches often use generative replay to create pseudo-datasets of previous tasks. However, generative replay itself suffers from catastrophic forgetting and task divergence among clients, leading to overfitting in FCL. To address these challenges, we propose a novel approach called Spatio-Temporal grAdient Matching with network-free Prototype (STAMP). Our contributions are threefold: 1) We develop a model-agnostic method to determine subset of samples that effectively form prototypes when using a prototypical network, making it resilient to continual learning challenges; 2) We introduce a spatio-temporal gradient matching approach, applied at both the client-side (temporal) and server-side (spatial), to mitigate catastrophic forgetting and data heterogeneity; 3) We leverage prototypes to approximate task-wise gradients, improving gradient matching on the client-side. Extensive experiments demonstrate our method's superiority over existing baselines.