Federated Learning without Full Labels: A Survey

Data privacy has become an increasingly important concern in real-world big data applications such as machine learning. To address the problem, federated learning (FL) has been a promising solution to building effective machine learning models from decentralized and private data. Existing federated learning algorithms mainly tackle the supervised learning problem, where data are assumed to be fully labeled. However, in practice, fully labeled data is often hard to obtain, as the participants may not have sufficient domain expertise, or they lack the motivation and tools to label data. Therefore, the problem of federated learning without full labels is important in real-world FL applications. In this paper, we discuss how the problem can be solved with machine learning techniques that leverage unlabeled data. We present a survey of methods that combine FL with semi-supervised learning, self-supervised learning, and transfer learning methods. We also summarize the datasets used to evaluate FL methods without full labels. Finally, we highlight future directions in the context of FL without full labels.

[1]  Chuhan Wu,et al.  FedX: Unsupervised Federated Learning with Cross Knowledge Distillation , 2022, ECCV.

[2]  Qiang Yang,et al.  Semi-Supervised Federated Heterogeneous Transfer Learning , 2022, Knowl. Based Syst..

[3]  Chenyou Fan,et al.  Private Semi-Supervised Federated Learning , 2022, IJCAI.

[4]  Ekdeep Singh Lubana,et al.  Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering , 2022, ICML.

[5]  Liusheng Huang,et al.  Enhancing Federated Learning with In-Cloud Unlabeled Data , 2022, 2022 IEEE 38th International Conference on Data Engineering (ICDE).

[6]  Weiming Zhuang,et al.  Divergence-aware Federated Self-Supervised Learning , 2022, ICLR.

[7]  X. Li,et al.  RSCFed: Random Sampling Consensus Federated Semi-supervised Learning , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Nicholas D. Lane,et al.  FRuDA: Framework for Distributed Adversarial Domain Adaptation , 2021, IEEE Transactions on Parallel and Distributed Systems.

[9]  Qiang Yang,et al.  Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability , 2021, IEEE Transactions on Big Data.

[10]  Ross B. Girshick,et al.  Masked Autoencoders Are Scalable Vision Learners , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Amir Salman Avestimehr,et al.  SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision , 2021, ArXiv.

[12]  Ming-Hsuan Yang,et al.  Federated Multi-Target Domain Adaptation , 2021, 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).

[13]  Shuai Yi,et al.  Collaborative Unsupervised Visual Representation Learning from Decentralized Data , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[14]  Jiayu Zhou,et al.  Federated Adversarial Debiasing for Fair and Transferable Representations , 2021, KDD.

[15]  Suhas Diggavi,et al.  A Field Guide to Federated Optimization , 2021, ArXiv.

[16]  Xiaolin Gui,et al.  Federated Learning with Positive and Unlabeled Data , 2021, ICML.

[17]  Hangyu Zhu,et al.  Federated Learning on Non-IID Data: A Survey , 2021, Neurocomputing.

[18]  V. Tarokh,et al.  SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training , 2021, NeurIPS.

[19]  Sanjay Sri Vallabh Singapuram,et al.  FedScale: Benchmarking Model and System Performance of Federated Learning at Scale , 2021, ICML.

[20]  Pheng-Ann Heng,et al.  FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Qiang Yang,et al.  Towards Personalized Federated Learning , 2021, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Bingsheng He,et al.  Federated Learning on Non-IID Data Silos: An Experimental Study , 2021, 2022 IEEE 38th International Conference on Data Engineering (ICDE).

[23]  Virginia Smith,et al.  Ditto: Fair and Robust Federated Learning Through Personalization , 2020, ICML.

[24]  Xinlei Chen,et al.  Exploring Simple Siamese Representation Learning , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Tao Shen,et al.  Federated unsupervised representation learning , 2020, Frontiers of Information Technology & Electronic Engineering.

[26]  M. Chowdhury,et al.  Oort: Efficient Federated Learning via Guided Participant Selection , 2020, OSDI.

[27]  Jie Ding,et al.  HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients , 2020, ICLR.

[28]  T. Nishio,et al.  Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training With Non-IID Private Data , 2020, IEEE Transactions on Mobile Computing.

[29]  Tianjian Chen,et al.  A Secure Federated Transfer Learning Framework , 2020, IEEE Intelligent Systems.

[30]  Eunho Yang,et al.  Federated Semi-Supervised Learning with Inter-Client Consistency , 2020, ArXiv.

[31]  Jie Tang,et al.  Self-Supervised Learning: Generative or Contrastive , 2020, IEEE Transactions on Knowledge and Data Engineering.

[32]  James Y. Zou,et al.  Improving Adversarial Robustness via Unlabeled Out-of-Domain Data , 2020, AISTATS.

[33]  Pierre H. Richemond,et al.  Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning , 2020, NeurIPS.

[34]  Michael Moeller,et al.  Inverting Gradients - How easy is it to break privacy in federated learning? , 2020, NeurIPS.

[35]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[36]  Maneesh Kumar Singh,et al.  DRIT++: Diverse Image-to-Image Translation via Disentangled Representations , 2020, International Journal of Computer Vision.

[37]  Jesper E. van Engelen,et al.  A survey on semi-supervised learning , 2019, Machine Learning.

[38]  Ross B. Girshick,et al.  Momentum Contrast for Unsupervised Visual Representation Learning , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Hui Xiong,et al.  A Comprehensive Survey on Transfer Learning , 2019, Proceedings of the IEEE.

[40]  Kate Saenko,et al.  Federated Adversarial Domain Adaptation , 2019, ICLR.

[41]  Sashank J. Reddi,et al.  SCAFFOLD: Stochastic Controlled Averaging for Federated Learning , 2019, ICML.

[42]  Aryan Mokhtari,et al.  FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization , 2019, AISTATS.

[43]  Anit Kumar Sahu,et al.  Federated Learning: Challenges, Methods, and Future Directions , 2019, IEEE Signal Processing Magazine.

[44]  Kaiyong Zhao,et al.  AutoML: A Survey of the State-of-the-Art , 2019, Knowl. Based Syst..

[45]  Shiho Moriai,et al.  Privacy-Preserving Deep Learning via Additively Homomorphic Encryption , 2019, 2019 IEEE 26th Symposium on Computer Arithmetic (ARITH).

[46]  Ludwig Schmidt,et al.  Unlabeled Data Improves Adversarial Robustness , 2019, NeurIPS.

[47]  Po-Sen Huang,et al.  Are Labels Required for Improving Adversarial Robustness? , 2019, NeurIPS.

[48]  David Berthelot,et al.  MixMatch: A Holistic Approach to Semi-Supervised Learning , 2019, NeurIPS.

[49]  Yingli Tian,et al.  Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[50]  Tianjian Chen,et al.  Federated Machine Learning: Concept and Applications , 2019 .

[51]  Anit Kumar Sahu,et al.  Federated Optimization in Heterogeneous Networks , 2018, MLSys.

[52]  Ramesh Raskar,et al.  Split learning for health: Distributed deep learning without sharing raw patient data , 2018, ArXiv.

[53]  Sebastian Caldas,et al.  LEAF: A Benchmark for Federated Settings , 2018, ArXiv.

[54]  Yue Zhao,et al.  Federated Learning with Non-IID Data , 2018, ArXiv.

[55]  Shiho Moriai,et al.  Privacy-Preserving Deep Learning via Additively Homomorphic Encryption , 2018, IEEE Transactions on Information Forensics and Security.

[56]  Nikos Komodakis,et al.  Unsupervised Representation Learning by Predicting Image Rotations , 2018, ICLR.

[57]  Tatsuya Harada,et al.  Maximum Classifier Discrepancy for Unsupervised Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[58]  Sarvar Patel,et al.  Practical Secure Aggregation for Privacy-Preserving Machine Learning , 2017, IACR Cryptol. ePrint Arch..

[59]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

[60]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[61]  Michael I. Jordan,et al.  Conditional Adversarial Domain Adaptation , 2017, NeurIPS.

[62]  Shin Ishii,et al.  Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[63]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[64]  Harri Valpola,et al.  Weight-averaged consistency targets improve semi-supervised deep learning results , 2017, ArXiv.

[65]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[66]  Martín Abadi,et al.  Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data , 2016, ICLR.

[67]  Richard Socher,et al.  Pointer Sentinel Mixture Models , 2016, ICLR.

[68]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[69]  Ian Goodfellow,et al.  Deep Learning with Differential Privacy , 2016, CCS.

[70]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[71]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[72]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[73]  Sanja Fidler,et al.  Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[74]  Bernard Ghanem,et al.  ActivityNet: A large-scale video benchmark for human activity understanding , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[75]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[76]  Alexei A. Efros,et al.  Unsupervised Visual Representation Learning by Context Prediction , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[77]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[78]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[79]  Aaron Roth,et al.  The Algorithmic Foundations of Differential Privacy , 2014, Found. Trends Theor. Comput. Sci..

[80]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[81]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[82]  Zhi-Ying Li,et al.  Communicational and Computational Efficient Federated Domain Adaptation , 2022, IEEE Transactions on Parallel and Distributed Systems.

[83]  Philip H. S. Torr,et al.  FedSR: A Simple and Effective Domain Generalization Method for Federated Learning , 2022, NeurIPS.

[84]  Yang Liu,et al.  BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated Learning , 2020, USENIX ATC.

[85]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[86]  Agustí Verde Parera,et al.  General data protection regulation , 2018 .

[87]  Dong-Hyun Lee,et al.  Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks , 2013 .

[88]  Xiaojin Zhu,et al.  Semi-Supervised Learning , 2010, Encyclopedia of Machine Learning.

[89]  Thomas G. Dietterich,et al.  To transfer or not to transfer , 2005, NIPS 2005.

[90]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[91]  R. Tibshirani,et al.  Estimating the number of clusters in a data set via the gap statistic , 2000 .

[92]  J. Lodge THE EUROPEAN PARLIAMENT , 1979 .