mlsanityData to 7 Oct 2026

Towards Causal Federated Learning For Enhanced Robustness and Privacy

arXiv 2104.06557 ↗First posted 14 Apr 2021cs.LG cs.AI cs.CRcited by 14

Not on the map. Why?

Abstract (arXiv)

Federated Learning is an emerging privacy-preserving distributed machine learning approach to building a shared model by performing distributed training locally on participating devices (clients) and aggregating the local models into a global one. As this approach prevents data collection and aggregation, it helps in reducing associated privacy risks to a great extent. However, the data samples across all participating clients are usually not independent and identically distributed (non-iid), and Out of Distribution(OOD) generalization for the learned models can be poor. Besides this challenge, federated learning also remains vulnerable to various attacks on security wherein a few malicious participating entities work towards inserting backdoors, degrading the generated aggregated model as well as inferring the data owned by participating entities. In this paper, we propose an approach for learning invariant (causal) features common to all participating clients in a federated learning setup and analyze empirically how it enhances the Out of Distribution (OOD) accuracy as well as the privacy of the final learned model.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 11 of its 17 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

11 of 17 references.

References · 11

  1. 2019Advances and Open Problems in Federated Learningcited by 3,021
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2019Invariant Risk Minimizationcited by 1,832
  4. 2018Federated Learning with Non-IID Datacited by 1,099
  5. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  6. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  8. 2020Domain Generalization using Causal Matchingcited by 224
  9. 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 75
  10. 2017Learning Differentially Private Recurrent Language Modelscited by 32
  11. 2019Alleviating Privacy Attacks via Causal Learningcited by 19

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 8; 2023: 3.

14 papers.

Sort:

  1. 2023Federated Domain Generalization: A Surveycited by 25
  2. 2022Gradient Masked Averaging for Federated Learningcited by 22
  3. 2022Mitigating Data Heterogeneity in Federated Learning with Data Augmentationcited by 21
  4. 2022Distribution inference risks: Identifying and mitigating sources of leakagecited by 17
  5. 2021Enabling Long-Term Cooperation in Cross-Silo Federated Learning: A Repeated Game Perspectivecited by 14
  6. 2022Domain Generalization -- A Causal Perspectivecited by 14
  7. 2022FL Games: A Federated Learning Framework for Distribution Shiftscited by 14
  8. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
  9. 2021Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsalcited by 11
  10. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  11. 2022A Federated Approach to Predicting Emojis in Hindi Tweetscited by 5
  12. 2021The Connection between Out-of-Distribution Generalization and Privacy of ML Modelscited by 3
2 more
  1. 2022FL Games: A federated learning framework for distribution shiftscited by 0
  2. 2023Global Layers: Non-IID Tabular Federated Learningcited by 0