mlsanityData to 14 Oct 2026

FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning

arXiv 2412.18904 ↗First posted 25 Dec 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a promising technology for data privacy and distributed optimization, but it suffers from data imbalance and heterogeneity among clients. Existing FL methods try to solve the problems by aligning client with server model or by correcting client model with control variables. These methods excel on IID and general Non-IID data but perform mediocrely in Simpson's Paradox scenarios. Simpson's Paradox refers to the phenomenon that the trend observed on the global dataset disappears or reverses on a subset, which may lead to the fact that global model obtained through aggregation in FL does not accurately reflect the distribution of global data. Thus, we propose FedCFA, a novel FL framework employing counterfactual learning to generate counterfactual samples by replacing local data critical factors with global average data, aligning local data distributions with the global and mitigating Simpson's Paradox effects. In addition, to improve the quality of counterfactual samples, we introduce factor decorrelation (FDC) loss to reduce the correlation among features and thus improve the independence of extracted factors. We conduct extensive experiments on six datasets and verify that our method outperforms other FL methods in terms of efficiency and global model accuracy under limited communication rounds.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 22 of its 41 references that are in the map. First posted on arXiv 25 Dec 2024.

Builds on

22 of 41 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  3. 2018LEAF: A Benchmark for Federated Settingscited by 792
  4. 2021Model-Contrastive Federated Learningcited by 766
  5. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  6. 2019Fair Resource Allocation in Federated Learningcited by 394
  7. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  8. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  9. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 179
  10. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  11. 2021Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learningcited by 111
  12. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
10 more
  1. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
  2. 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
  3. 2020DeVLBert: Learning Deconfounded Visio-Linguistic Representationscited by 42
  4. 2022Differentially Private Federated Learning with Local Regularization and Sparsificationcited by 36
  5. 2022FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergencecited by 29
  6. 2023GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgettingcited by 27
  7. 2023A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Datacited by 14
  8. 2022Federated Learning in Non-IID Settings Aided by Differentially Private Synthetic Datacited by 12
  9. 2023The Resource Problem of Using Linear Layer Leakage Attack in Federated Learningcited by 9
  10. 2023Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneitycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025FlowMM: Cross-Modal Information Flow Guided KV Cache Merging for Efficient Multimodal Context Inferencecited by 6
  2. 2026Not Just What's There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-tuningcited by 5
  3. 2025Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalitiescited by 2
  4. 2025Technical note on Fisher Information for Robust Federated Cross-Validationcited by 0