mlsanityData to 14 Oct 2026

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

arXiv 2503.06158 ↗First posted 8 Mar 2025cs.LGcited by 0

Not on the map. Why?

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.

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

31 of 44 references.

References · 31

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Invariant Risk Minimizationcited by 1,854
  3. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  4. 2013Domain Generalization via Invariant Feature Representationcited by 623
  5. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  6. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  7. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  8. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  9. 2020The Risks of Invariant Risk Minimizationcited by 262
  10. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  11. 2020Domain Generalization using Causal Matchingcited by 225
  12. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
19 more
  1. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  2. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  3. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  4. 2022Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalizationcited by 97
  5. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  6. 2019Robust Federated Learning in a Heterogeneous Environmentcited by 90
  7. 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
  8. 2017Invariant Causal Prediction for Sequential Datacited by 63
  9. 2020Learning Causal Semantic Representation for Out-of-Distribution Predictioncited by 60
  10. 2022Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learningcited by 46
  11. 2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
  12. 2020Inverse Distance Aggregation for Federated Learning with Non-IID Datacited by 44
  13. 2021Federated Learning with Domain Generalizationcited by 41
  14. 2022Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferringcited by 28
  15. 2021Invariant Policy Learning: A Causal Perspectivecited by 17
  16. 2019Convex Formulation of Overparameterized Deep Neural Networkscited by 16
  17. 2020Accounting for Unobserved Confounding in Domain Generalizationcited by 14
  18. 2022FedGen: Generalizable Federated Learning for Sequential Datacited by 9
  19. 2025The Impact Analysis of Delays in Asynchronous Federated Learning with Data Heterogeneity for Edge Intelligencecited by 1

Built on by

Not cited yet.