# PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning

arXiv: https://arxiv.org/abs/2502.00354 · HTML: https://mlsanity.com/paper/2502.00354/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Federated mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 29 of its 63 references that are in the map.
- First posted on arXiv 1 Feb 2025.

## Placed in

- Mixture-of-experts / [Federated mixture-of-experts](https://mlsanity.com/moe/federated-mixture-of-experts/)

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Think Locally, Act Globally: Federated Learning with Local and Global Representations](https://mlsanity.com/paper/2001.01523/) (2020)
- [Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers](https://mlsanity.com/paper/2212.10559/) (2022)
- [FedBABU: Towards Enhanced Representation for Federated Image Classification](https://mlsanity.com/paper/2106.06042/) (2021)
- [FedVision: An Online Visual Object Detection Platform Powered by Federated Learning](https://mlsanity.com/paper/2001.06202/) (2020)
- [FedALA: Adaptive Local Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2212.01197/) (2022)
- [FedGH: Heterogeneous Federated Learning with Generalized Global Header](https://mlsanity.com/paper/2303.13137/) (2023)
- [Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning](https://mlsanity.com/paper/2110.08394/) (2021)
- [Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference](https://mlsanity.com/paper/2211.15969/) (2022)
- [Eliminating Domain Bias for Federated Learning in Representation Space](https://mlsanity.com/paper/2311.14975/) (2023)
- [FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy](https://mlsanity.com/paper/2307.01217/) (2023)
- [Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy](https://mlsanity.com/paper/2007.00914/) (2020)
- [PFL-MoE: Personalized Federated Learning Based on Mixture of Experts](https://mlsanity.com/paper/2012.15589/) (2020)
- [FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers](https://mlsanity.com/paper/2203.00219/) (2022)
- [FedGen: Generalizable Federated Learning for Sequential Data](https://mlsanity.com/paper/2211.01914/) (2022)

## Built on by (most cited first, 9 of 9)

- [HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts](https://mlsanity.com/paper/2601.00583/) (2026)
- [Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity](https://mlsanity.com/paper/2603.21276/) (2026)
- [FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE](https://mlsanity.com/paper/2506.16600/) (2025)
- [Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment](https://mlsanity.com/paper/2511.08399/) (2025)
- [DeepFusion: Accelerating MoE Training via Federated Knowledge Distillation from Heterogeneous Edge Devices](https://mlsanity.com/paper/2602.14301/) (2026)
- [FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs](https://mlsanity.com/paper/2605.21264/) (2026)
- [Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2606.15625/) (2026)
- [Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning](https://mlsanity.com/paper/2606.28835/) (2026)
- [Does Every User Need a Private LoRA? Decoupling Personalization from Per-User Adaptation](https://mlsanity.com/paper/2610.02353/) (2026)

## Abstract (arXiv)

Federated learning (FL) has gained widespread attention for its privacy-preserving and collaborative learning capabilities. Due to significant statistical heterogeneity, traditional FL struggles to generalize a shared model across diverse data domains. Personalized federated learning addresses this issue by dividing the model into a globally shared part and a locally private part, with the local model correcting representation biases introduced by the global model. Nevertheless, locally converged parameters more accurately capture domain-specific knowledge, and current methods overlook the potential benefits of these parameters. To address these limitations, we propose PM-MoE architecture. This architecture integrates a mixture of personalized modules and an energy-based personalized modules denoising, enabling each client to select beneficial personalized parameters from other clients. We applied the PM-MoE architecture to nine recent model-split-based personalized federated learning algorithms, achieving performance improvements with minimal additional training. Extensive experiments on six widely adopted datasets and two heterogeneity settings validate the effectiveness of our approach. The source code is available at urlhttps://github.com/dannis97500/PM-MOE.