# Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression

arXiv: https://arxiv.org/abs/2603.13795 · HTML: https://mlsanity.com/paper/2603.13795/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 33 of its 56 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 30 of 33)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [Federated Learning from Pre-Trained Models: A Contrastive Learning Approach](https://mlsanity.com/paper/2209.10083/) (2022)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Causality Inspired Representation Learning for Domain Generalization](https://mlsanity.com/paper/2203.14237/) (2022)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [PMR: Prototypical Modal Rebalance for Multimodal Learning](https://mlsanity.com/paper/2211.07089/) (2022)
- [Federated Unlearning via Class-Discriminative Pruning](https://mlsanity.com/paper/2110.11794/) (2021)
- [Prototypical Residual Networks for Anomaly Detection and Localization](https://mlsanity.com/paper/2212.02031/) (2022)
- [Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2204.10638/) (2022)
- [Fair Resource Allocation in Multi-Task Learning](https://mlsanity.com/paper/2402.15638/) (2024)
- [Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains](https://mlsanity.com/paper/2403.09048/) (2024)
- [APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2406.08372/) (2024)
- [GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning](https://mlsanity.com/paper/2308.10279/) (2023)
- [Communication Efficient and Provable Federated Unlearning](https://mlsanity.com/paper/2401.11018/) (2024)
- [Federated Unlearning with Gradient Descent and Conflict Mitigation](https://mlsanity.com/paper/2412.20200/) (2024)
- [Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning](https://mlsanity.com/paper/2404.14808/) (2024)
- [Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter](https://mlsanity.com/paper/2502.20709/) (2025)
- [NoT: Federated Unlearning via Weight Negation](https://mlsanity.com/paper/2503.05657/) (2025)
- [Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity](https://mlsanity.com/paper/2405.17462/) (2024)
- [Strategic Data Revocation in Federated Unlearning](https://mlsanity.com/paper/2312.01235/) (2023)
- [Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation](https://mlsanity.com/paper/2406.12516/) (2024)
- [Hyperspherical Classification with Dynamic Label-to-Prototype Assignment](https://mlsanity.com/paper/2403.16937/) (2024)

## Abstract (arXiv)

Federated Unlearning (FUL) aims to remove specific participants' data contributions from a trained Federated Learning model, thereby ensuring data privacy and compliance with regulatory requirements. Despite its potential, progress in FUL has been limited due to several challenges, including the cross-client knowledge inaccessibility and high computational and communication costs. To overcome these challenges, we propose Federated On-server Unlearning (FOUL), a novel framework that comprises two key stages. The learning-to-unlearn stage serves as a preparatory learning phase, during which the model identifies and encodes the key features associated with the forget clients. This stage is communication-efficient and establishes the basis for the subsequent unlearning process. Subsequently, on-server knowledge aggregation phase aims to perform the unlearning process at the server without requiring access to client data, thereby preserving both efficiency and privacy. We introduce a new data setting for FUL, which enables a more transparent and rigorous evaluation of unlearning. To highlight the effectiveness of our approach, we propose a novel evaluation metric termed time-to-forget, which measures how quickly the model achieves optimal unlearning performance. Extensive experiments conducted on three datasets under various unlearning scenarios demonstrate that FOUL outperforms the Retraining in FUL. Moreover, FOUL achieves competitive or superior results with significantly reduced time-to-forget, while maintaining low communication and computation costs.