# Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty

arXiv: https://arxiv.org/abs/2503.06158 · HTML: https://mlsanity.com/paper/2503.06158/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 8 Mar 2025.

## Builds on (most cited first, 30 of 31)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Personalized Federated Learning: A Meta-Learning Approach](https://mlsanity.com/paper/2002.07948/) (2020)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare](https://mlsanity.com/paper/1907.09173/) (2019)
- [Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2202.05441/) (2022)
- [Generalized Federated Learning via Sharpness Aware Minimization](https://mlsanity.com/paper/2206.02618/) (2022)
- [Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization](https://mlsanity.com/paper/2212.10445/) (2022)
- [Exploring Chemical Space with Score-based Out-of-distribution Generation](https://mlsanity.com/paper/2206.07632/) (2022)
- [Robust Federated Learning in a Heterogeneous Environment](https://mlsanity.com/paper/1906.06629/) (2019)
- [Fast-Convergent Federated Learning with Adaptive Weighting](https://mlsanity.com/paper/2012.00661/) (2020)
- [Invariant Causal Prediction for Sequential Data](https://mlsanity.com/paper/1706.08058/) (2017)
- [Learning Causal Semantic Representation for Out-of-Distribution Prediction](https://mlsanity.com/paper/2011.01681/) (2020)
- [Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning](https://mlsanity.com/paper/2210.00226/) (2022)
- [Out-of-distribution Generalization with Causal Invariant Transformations](https://mlsanity.com/paper/2203.11528/) (2022)
- [Inverse Distance Aggregation for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2008.07665/) (2020)
- [Federated Learning with Domain Generalization](https://mlsanity.com/paper/2111.10487/) (2021)
- [Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring](https://mlsanity.com/paper/2206.06818/) (2022)
- [Invariant Policy Learning: A Causal Perspective](https://mlsanity.com/paper/2106.00808/) (2021)
- [Convex Formulation of Overparameterized Deep Neural Networks](https://mlsanity.com/paper/1911.07626/) (2019)
- [Accounting for Unobserved Confounding in Domain Generalization](https://mlsanity.com/paper/2007.10653/) (2020)
- [FedGen: Generalizable Federated Learning for Sequential Data](https://mlsanity.com/paper/2211.01914/) (2022)

## Abstract (arXiv)

This paper provides an invariant federated learning system for resource-constrained edge intelligence. This framework can mitigate the impact of heterogeneity and asynchrony via exit strategy and invariant penalty. We introduce parameter orthogonality into edge intelligence to measure the contribution or impact of heterogeneous and asynchronous clients. It is proved in this paper that the exit of abnormal edge clients can guarantee the effect of the model on most clients. Meanwhile, to ensure the models' performance on exited abnormal clients and those who lack training resources, we propose Federated Learning with Invariant Penalty for Generalization (FedIPG) by constructing the approximate orthogonality of the invariant parameters and the heterogeneous parameters. Theoretical proof shows that FedIPG reduces the Out-Of-Distribution prediction loss without increasing the communication burden. The performance of FedIPG combined with an exit strategy is tested empirically in multiple scales using four datasets. It shows our system can enhance In-Distribution performance and outperform the state-of-the-art algorithm in Out-Of-Distribution generalization while maintaining model convergence. Additionally, the results of the visual experiment prove that FedIPG contains preliminary causality in terms of ignoring confounding features.