The latest update has been moved to https://github.com/FedML-AI/FedML/blob/master/research/Awesome-Federated-Learning.md

FedML - The Most Popular Federated Learning Library https://fedml.ai

Awesome-Federated-Learning

A curated list of federated learning publications, re-organized from Arxiv (mostly).

Last Update: July, 20th, 2021.

If your publication is not included here, please email to chaoyanghe.com@gmail.com

Foundations and Trends in Machine Learning

We are thrilled to share that Advances and Open Problems in Federated Learning has been accepted to FnTML (Foundations and Trends in Machine Learning, the chief editor is Michael Jordan).

A Field Guide to Federated Optimization

Publications in Top-tier ML/CV/NLP/DM Conference (ICML, NeurIPS, ICLR, CVPR, ACL, AAAI, KDD)

ICML

Title	Team/Authors	Venue and Year	Targeting Problem	Method
Federated Learning with Only Positive Labels	Google Research	ICML 2020	label deficiency in multi-class classification	regularization
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning	EPFL, Google Research	ICML 2020	heterogeneous data (non-I.I.D)	nonconvex/convex optimization with variance reduction
FedBoost: A Communication-Efficient Algorithm for Federated Learning	Google Research, NYU	ICML 2020	communication cost	ensemble algorithm
FetchSGD: Communication-Efficient Federated Learning with Sketching	UC Berkeley, JHU, Amazon	ICML 2020	communication cost	compress model updates with Count Sketch
From Local SGD to Local Fixed-Point Methods for Federated Learning	KAUST	ICML 2020	communication cost	Optimization

NeurIPS

Title	Team/Authors	Venue and Year	Targeting Problem
Lower Bounds and Optimal Algorithms for Personalized Federated Learning	KAUST	NeurIPS 2020	non-I.I.D, personalization
Personalized Federated Learning with Moreau Envelopes	The University of Sydney	NeurIPS 2020	non-I.I.D, personalization
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach	MIT	NeurIPS 2020	non-I.I.D, personalization
Differentially-Private Federated Contextual Bandits	MIT	NeurIPS 2020	Contextual Bandits
Federated Principal Component Analysis	Cambridge	NeurIPS 2020	PCA
FedSplit: an algorithmic framework for fast federated optimization	UCB	NeurIPS 2020	Acceleration
Federated Bayesian Optimization via Thompson Sampling	MIT	NeurIPS 2020
Robust Federated Learning: The Case of Affine Distribution Shifts	MIT	NeurIPS 2020	Privacy, Robustness
An Efficient Framework for Clustered Federated Learning	UCB	NeurIPS 2020	heterogeneous data (non-I.I.D)
Distributionally Robust Federated Averaging	PSU	NeurIPS 2020	Privacy, Robustness
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge	USC	NeurIPS 2020	Efficient Training of Large DNN at Edge
A Scalable Approach for Privacy-Preserving Collaborative Machine Learning	USC	NeurIPS 2020	Scalability
Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization	CMU	NeurIPS 2020	local update step heterogeneity
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning	Wiscosin	NeurIPS 2020	Privacy, Robustness
Federated Accelerated Stochastic Gradient Descent	Stanford	NeurIPS 2020	Acceleration
Inverting Gradients - How easy is it to break privacy in federated learning?	University of Siegen	NeurIPS 2020	Privacy, Robustness
Ensemble Distillation for Robust Model Fusion in Federated Learning	EPFL	NeurIPS 2020	Privacy, Robustness
Optimal Topology Design for Cross-Silo Federated Learning	Inria	NeurIPS 2020	Topology Optimization
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms	University of Minnesota	NeurIPS 2020
Distributed Distillation for On-Device Learning	Stanford	NeurIPS 2020
Byzantine Resilient Distributed Multi-Task Learning	Vanderbilt University	NeurIPS 2020
Distributed Newton Can Communicate Less and Resist Byzantine Workers	UCB	NeurIPS 2020
Minibatch vs Local SGD for Heterogeneous Distributed Learning	TTIC	NeurIPS 2020
Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks		NeurIPS 2020

(according to https://neurips.cc/Conferences/2020/AcceptedPapersInitial)

Note: most of the accepted publications are preparing the camera ready revision, thus we are not sure the detail of their proposed methods

Research Areas

Statistical Challenges: data distribution heterogeneity and label deficiency (159)

Distributed Optimization
Non-IID and Model Personalization
Semi-Supervised Learning
Vertical Federated Learning
Decentralized FL
Hierarchical FL
Neural Architecture Search
Transfer Learning
Continual Learning
Domain Adaptation
Reinforcement Learning
Bayesian Learning
Causal Learning

Trustworthiness: security, privacy, fairness, incentive mechanism, etc. (88)

Adversarial-Attack-and-Defense
Privacy
Fairness
Interpretability
Incentive Mechanism

System Challenges: communication and computational resource constrained, software and hardware heterogeneity, and FL system (141)

Communication-Efficiency
Straggler Problem
Computation Efficiency
Wireless Communication and Cloud Computing
FL System Design

Benchmark, Dataset and Survey (27)

Benchmark and Dataset (7)
Survey (20)

Statistical Challenges: distribution heterogeneity and label deficiency

Distributed optimization

Userful Federated Optimizer Baselines:

FedAvg: Communication-Efficient Learning of Deep Networks from Decentralized Data. 2016-02. AISTAT 2017.

FedOpt: Adaptive Federated Optimization. ICLR 2021 (Under Review). 2020-02-29

FedNov: Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization. NeurIPS 2020

Federated Optimization: Distributed Optimization Beyond the Datacenter. NIPS 2016 workshop.

Federated Optimization: Distributed Machine Learning for On-Device Intelligence

Stochastic, Distributed and Federated Optimization for Machine Learning. FL PhD Thesis. By Jakub

Collaborative Deep Learning in Fixed Topology Networks

Federated Multi-Task Learning

LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning

Local Stochastic Approximation: A Unified View of Federated Learning and Distributed Multi-Task Reinforcement Learning Algorithms

Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning

Exact Support Recovery in Federated Regression with One-shot Communication

DEED: A General Quantization Scheme for Communication Efficiency in Bits Researcher: Ruoyu Sun, UIUC

Robust Federated Learning: The Case of Affine Distribution Shifts

Personalized Federated Learning with Moreau Envelopes

Towards Flexible Device Participation in Federated Learning for Non-IID Data Keywords: inactive or return incomplete updates in non-IID dataset

A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization

FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data Researcher: Wotao Yin, UCLA

FedSplit: An algorithmic framework for fast federated optimization

Distributed Stochastic Non-Convex Optimization: Momentum-Based Variance Reduction

On the Outsized Importance of Learning Rates in Local Update Methods Highlight: local model learning rate optimization + automation Researcher: Jakub

Federated Learning with Compression: Unified Analysis and Sharp Guarantees Highlight: non-IID, gradient compression + local SGD Researcher: Mehrdad Mahdavi, Jin Rong’s PhD Student http://www.cse.psu.edu/~mzm616/

From Local SGD to Local Fixed-Point Methods for Federated Learning

Federated Residual Learning. 2020-03

Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization. ICML 2020.

LASG: Lazily Aggregated Stochastic Gradients for Communication-Efficient Distributed Learning

Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor

Dynamic Federated Learning

Distributed Optimization over Block-Cyclic Data

Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability

Federated Learning with Matched Averaging

Federated Learning of a Mixture of Global and Local Models

Faster On-Device Training Using New Federated Momentum Algorithm

FedDANE: A Federated Newton-Type Method

Distributed Fixed Point Methods with Compressed Iterates

Primal-dual methods for large-scale and distributed convex optimization and data analytics

Parallel Restarted SPIDER - Communication Efficient Distributed Nonconvex Optimization with Optimal Computation Complexity

Representation of Federated Learning via Worst-Case Robust Optimization Theory

On the Convergence of Local Descent Methods in Federated Learning

SCAFFOLD: Stochastic Controlled Averaging for Federated Learning

Central Server Free Federated Learning over Single-sided Trust Social Networks

Accelerating Federated Learning via Momentum Gradient Descent

Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction

Gradient Descent with Compressed Iterates

First Analysis of Local GD on Heterogeneous Data

(*) On the Convergence of FedAvg on Non-IID Data. ICLR 2020.

Robust Federated Learning in a Heterogeneous Environment

Scalable and Differentially Private Distributed Aggregation in the Shuffled Model

Variational Federated Multi-Task Learning

Bayesian Nonparametric Federated Learning of Neural Networks. ICLR 2019.

Differentially Private Learning with Adaptive Clipping

Semi-Cyclic Stochastic Gradient Descent

Asynchronous Federated Optimization

Agnostic Federated Learning

Federated Optimization in Heterogeneous Networks

Partitioned Variational Inference: A unified framework encompassing federated and continual learning

Learning Rate Adaptation for Federated and Differentially Private Learning

Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets

An Efficient Framework for Clustered Federated Learning

Adaptive Federated Learning in Resource Constrained Edge Computing Systems Citation: 146

Adaptive Federated Optimization

Local SGD converges fast and communicates little

Don’t Use Large Mini-Batches, Use Local SGD

Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD

Local SGD With a Communication Overhead Depending Only on the Number of Workers

Federated Accelerated Stochastic Gradient Descent

Tighter Theory for Local SGD on Identical and Heterogeneous Data

STL-SGD: Speeding Up Local SGD with Stagewise Communication Period

Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms

Don't Use Large Mini-Batches, Use Local SGD

Understanding Unintended Memorization in Federated Learning

Non-IID and Model Personalization

The Non-IID Data Quagmire of Decentralized Machine Learning. 2019-10

Federated Learning with Non-IID Data

FedCD: Improving Performance in non-IID Federated Learning. 2020

Life Long Learning: FedFMC: Sequential Efficient Federated Learning on Non-iid Data. 2020

Robust Federated Learning: The Case of Affine Distribution Shifts. 2020

Personalized Federated Learning with Moreau Envelopes. 2020

Personalized Federated Learning using Hypernetworks. 2021

Ensemble Distillation for Robust Model Fusion in Federated Learning. 2020 Researcher: Tao Lin, ZJU, EPFL https://tlin-tao-lin.github.io/index.html

Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning. 2020

Towards Flexible Device Participation in Federated Learning for Non-IID Data. 2020 Keywords: inactive or return incomplete updates in non-IID dataset

XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning. 2020

NeurIPS 2020 submission: An Efficient Framework for Clustered Federated Learning. 2020 Researcher: AVISHEK GHOSH, UCB, PhD

Continual Local Training for Better Initialization of Federated Models. 2020

FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data. 2020 Researcher: Wotao Yin, UCLA

Global Multiclass Classification from Heterogeneous Local Models. 2020 Researcher: Stanford https://stanford.edu/~pilanci/

Multi-Center Federated Learning. 2020

Federated learning with hierarchical clustering of local updates to improve training on non-IID data. 2020

Federated Learning with Only Positive Labels. 2020 Researcher: Felix Xinnan Yu, Google New York Keywords: positive labels Limited Labels

Federated Semi-Supervised Learning with Inter-Client Consistency. 2020

(*) FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning. CMU ECE. 2020-04-07

(*) Adaptive Personalized Federated Learning

Semi-Federated Learning

Survey of Personalization Techniques for Federated Learning. 2020-03-19

Device Heterogeneity in Federated Learning: A Superquantile Approach. 2020-02

Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework

Three Approaches for Personalization with Applications to Federated Learning

Personalized Federated Learning: A Meta-Learning Approach

Towards Federated Learning: Robustness Analytics to Data Heterogeneity Highlight: non-IID + adversarial attacks

Salvaging Federated Learning by Local Adaptation Highlight: an experimental paper that evaluate FL can help to improve the local accuracy

FOCUS: Dealing with Label Quality Disparity in Federated Learning. 2020-01

Overcoming Noisy and Irrelevant Data in Federated Learning. ICPR 2020.

Real-Time Edge Intelligence in the Making: A Collaborative Learning Framework via Federated Meta-Learning. 2020-01

(*) Think Locally, Act Globally: Federated Learning with Local and Global Representations. NeurIPS 2019 Workshop on Federated Learning distinguished student paper award

Federated Learning with Personalization Layers

Federated Adversarial Domain Adaptation

Federated Evaluation of On-device Personalization

Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating

Overcoming Forgetting in Federated Learning on Non-IID Data

Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints

Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data

Improving Federated Learning Personalization via Model Agnostic Meta Learning

Measure Contribution of Participants in Federated Learning

(*) Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification

Multi-hop Federated Private Data Augmentation with Sample Compression

Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications

Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms

Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data

Robust and Communication-Efficient Federated Learning from Non-IID Data

High Dimensional Restrictive Federated Model Selection with multi-objective Bayesian Optimization over shifted distributions

Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge

Federated Meta-Learning with Fast Convergence and Efficient Communication

Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters

Towards Efficient Scheduling of Federated Mobile Devices under Computational and Statistical Heterogeneity

Client Adaptation improves Federated Learning with Simulated Non-IID Clients

Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization

Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity. ICDCS 2021.

Vertical Federated Learning

SecureBoost: A Lossless Federated Learning Framework

Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator

A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression

Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption

Entity Resolution and Federated Learning get a Federated Resolution.

Multi-Participant Multi-Class Vertical Federated Learning

A Communication-Efficient Collaborative Learning Framework for Distributed Features

Asymmetrical Vertical Federated Learning Researcher: Tencent Cloud, Libin Wang

VAFL: a Method of Vertical Asynchronous Federated Learning, ICML workshop on FL, 2020

Decentralized FL

Central Server Free Federated Learning over Single-sided Trust Social Networks

Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent

Multi-consensus Decentralized Accelerated Gradient Descent

Decentralized Bayesian Learning over Graphs. 2019-05

BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning

Biscotti: A Ledger for Private and Secure Peer-to-Peer Machine Learning

Matcha: Speeding Up Decentralized SGD via Matching Decomposition Sampling

Hierarchical FL

Client-Edge-Cloud Hierarchical Federated Learning

(FL startup: Tongdun, HangZhou, China) Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework. 2020-02

HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning

Hierarchical Federated Learning Across Heterogeneous Cellular Networks

Enhancing Privacy via Hierarchical Federated Learning

Federated learning with hierarchical clustering of local updates to improve training on non-IID data. 2020

Federated Hierarchical Hybrid Networks for Clickbait Detection

Matcha: Speeding Up Decentralized SGD via Matching Decomposition Sampling (in above section as well)

Neural Architecture Search

[FedNAS: Federated Deep Learning via Neural Architecture Search. CVPR 2020. 2020-04-18](https://arxiv.org/pdf/2004.08546.pdf

Real-time Federated Evolutionary Neural Architecture Search. 2020-03

Federated Neural Architecture Search. 2020-06-14

Differentially-private Federated Neural Architecture Search. 2020-06

Transfer Learning

Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data

Secure Federated Transfer Learning. IEEE Intelligent Systems 2018.

FedMD: Heterogenous Federated Learning via Model Distillation

Secure and Efficient Federated Transfer Learning

Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data

Decentralized Differentially Private Segmentation with PATE. 2020-04
Highlights: apply the ICLR 2017 paper "Semisupervised knowledge transfer for deep learning from private training data"

Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning. 2020

(FL startup: Tongdun, HangZhou, China) Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework. 2020-02

Cooperative Learning via Federated Distillation over Fading Channels

(*) Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer

Federated Reinforcement Distillation with Proxy Experience Memory

Continual Learning

Federated Continual Learning with Adaptive Parameter Communication. 2020-03

Semi-Supervised Learning

Federated Semi-Supervised Learning with Inter-Client Consistency. 2020

Semi-supervised knowledge transfer for deep learning from private training data. ICLR 2017

Scalable private learning with PATE. ICLR 2018.

Domain Adaptation

Federated Adversarial Domain Adaptation. ICLR 2020.

Reinforcement Learning

Federated Deep Reinforcement Learning

Bayesian Learning

Differentially Private Federated Variational Inference. NeurIPS 2019 FL Workshop. 2019-11-24.

Causal Learning

Towards Causal Federated Learning For Enhanced Robustness and Privacy. ICLR 2021 DPML Workshop

Trustworthy AI: adversarial attack, privacy, fairness, incentive mechanism, etc.

Adversarial Attack and Defense

An Overview of Federated Deep Learning Privacy Attacks and Defensive Strategies. 2020-04-01 Citation: 0

How To Backdoor Federated Learning. 2018-07-02. AISTATS 2020 Citation: 128

Can You Really Backdoor Federated Learning?. NeruIPS 2019. 2019-11-18 Highlight: by Google Citation: 9

DBA: Distributed Backdoor Attacks against Federated Learning. ICLR 2020. Citation: 66

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks. ICML 2021.

Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning. ACM CCS 2017. 2017-02-14 Citation: 284

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates Citation: 112

Deep Leakage from Gradients. NIPS 2019 Citation: 31

Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning. 2018-12-03 Citation: 46

Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning. INFOCOM 2019 Citation: 56 Highlight: server-side attack

Analyzing Federated Learning through an Adversarial Lens. ICML 2019.. Citation: 60 Highlight: client attack

Mitigating Sybils in Federated Learning Poisoning. 2018-08-14. RAID 2020 Citation: 41 Highlight: defense

RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasets, AAAI 2019 Citation: 34

(*) A Framework for Evaluating Gradient Leakage Attacks in Federated Learning. 2020-04-22 Researcher: Wenqi Wei, Ling Liu, GaTech

(*) Local Model Poisoning Attacks to Byzantine-Robust Federated Learning. 2019-11-26

NeurIPS 2020 Submission: Backdoor Attacks on Federated Meta-Learning Researcher: Chien-Lun Chen, USC

Towards Realistic Byzantine-Robust Federated Learning. 2020-04-10

Data Poisoning Attacks on Federated Machine Learning. 2020-04-19

Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning. 2020-04-27

Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data. 2020-06-22 Researcher: Suhas Diggavi, UCLA (https://scholar.google.com/citations?hl=en&user=hjTzNuQAAAAJ&view_op=list_works&sortby=pubdate)

(*) NeurIPS 2020 submission: FedMGDA+: Federated Learning meets Multi-objective Optimization. 2020-06-20

(*) NeurIPS 2020 submission: Free-rider Attacks on Model Aggregation in Federated Learning. 2020-06-26

FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications. 2020-06-28

Privacy-preserving Weighted Federated Learning within Oracle-Aided MPC Framework. 2020-05-17 Citation: 0

BASGD: Buffered Asynchronous SGD for Byzantine Learning. 2020-03-02

Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees. 2020-02-25 Citation: 1

Learning to Detect Malicious Clients for Robust Federated Learning. 2020-02-01

Robust Aggregation for Federated Learning. 2019-12-31 Citation: 9

Towards Deep Federated Defenses Against Malware in Cloud Ecosystems. 2019-12-27

Attack-Resistant Federated Learning with Residual-based Reweighting. 2019-12-23

Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer. 2019-12-24 Citation: 1

Free-riders in Federated Learning: Attacks and Defenses. 2019-11-28

Robust Federated Learning with Noisy Communication. 2019-11-01 Citation: 4

Abnormal Client Behavior Detection in Federated Learning. 2019-10-22 Citation: 3

Eavesdrop the Composition Proportion of Training Labels in Federated Learning. 2019-10-14 Citation: 0

Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging. 2019-09-11

An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning. 2019-08-22

Secure Distributed On-Device Learning Networks With Byzantine Adversaries. 2019-06-03 Citation: 3

Robust Federated Training via Collaborative Machine Teaching using Trusted Instances. 2019-05-03 Citation: 2

Dancing in the Dark: Private Multi-Party Machine Learning in an Untrusted Setting. 2018-11-23 Citation: 4

Inverting Gradients - How easy is it to break privacy in federated learning? 2020-03-31 Citation: 3

Quantification of the Leakage in Federated Learning. 2019-10-12 Citation: 1

Privacy

Practical Secure Aggregation for Federated Learning on User-Held Data. NIPS 2016 workshop Highlight: cryptology

Differentially Private Federated Learning: A Client Level Perspective. NIPS 2017 Workshop

Exploiting Unintended Feature Leakage in Collaborative Learning. S&P 2019. 2018-05-10 Citation: 105

(x) Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning. 2018-05

A Hybrid Approach to Privacy-Preserving Federated Learning. AISec 2019. 2018-12-07 Citation: 35

A generic framework for privacy preserving deep learning. PPML 2018. 2018-11-09 Citation: 36

Federated Generative Privacy. IJCAI 2019 FL workshop. 2019-10-08 Citation: 4

Enhancing the Privacy of Federated Learning with Sketching. 2019-11-05 Citaiton: 0

Federated Learning with Bayesian Differential Privacy. 2019-11-22 Citation: 5

HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning. AISec 2019. 2019-12-12 https://aisec.cc/

Private Federated Learning with Domain Adaptation. NeurIPS 2019 FL workshop. 2019-12-13

iDLG: Improved Deep Leakage from Gradients. 2020-01-08 Citation: 3

Anonymizing Data for Privacy-Preserving Federated Learning. 2020-02-21

Practical and Bilateral Privacy-preserving Federated Learning. 2020-02-23 Citation: 0

Decentralized Policy-Based Private Analytics. 2020-03-14 Citation: 0

FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection. DASFAA 2020. 2020-03-24 Citation: 0

Learn to Forget: User-Level Memorization Elimination in Federated Learning. 2020-03-24

LDP-Fed: Federated Learning with Local Differential Privacy. EdgeSys 2020. 2020-04-01 Researcher: Ling Liu, GaTech Citation: 1

PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networks. 2020-04-05 Citation: 0

Local Differential Privacy based Federated Learning for Internet of Things. 2020-04-09 Citation: 0

Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise. 2020-04.

Decentralized Differentially Private Segmentation with PATE. MICCAI 2020 Under Review. 2020-04
Highlights: apply the ICLR 2017 paper "Semisupervised knowledge transfer for deep learning from private training data"

Enhancing Privacy via Hierarchical Federated Learning. 2020-04-23

Privacy Preserving Distributed Machine Learning with Federated Learning. 2020-04-25 Citation: 0

Exploring Private Federated Learning with Laplacian Smoothing. 2020-05-01 Citation: 0

Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learning. 2020-05-05 Citation: 0

Efficient Privacy Preserving Edge Computing Framework for Image Classification. 2020-05-10 Citation: 0

A Distributed Trust Framework for Privacy-Preserving Machine Learning. 2020-06-03 Citation: 0

Secure Byzantine-Robust Machine Learning. 2020-06-08

ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing. 2020-06-08

Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control. 2020-06-09 Citation: 0

(*) Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties. 2020-06-12 Citation: 0

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators. 2020-06-15 Citation: 0

Federated Learning with Differential Privacy:Algorithms and Performance Analysis Citation: 2

Fairness

Fair Resource Allocation in Federated Learning. ICLR 2020.

Hierarchically Fair Federated Learning

Towards Fair and Privacy-Preserving Federated Deep Models

Interpretability

Interpret Federated Learning with Shapley Values.

Incentive Mechanism

Record and reward federated learning contributions with blockchain. IEEE CyberC 2019

FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC. ICDCS 2020

Toward an Automated Auction Framework for Wireless Federated Learning Services Market

Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism

Motivating Workers in Federated Learning: A Stackelberg Game Perspective

Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

A Learning-based Incentive Mechanism forFederated Learning

A Crowdsourcing Framework for On-Device Federated Learning

System Challenges: communication and computational resource constrained, software and hardware heterogeneity, and FL wireless communication system

Communication Efficiency

Federated Learning: Strategies for Improving Communication Efficiency Highlights: optimization

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. ICLR 2018. 2017-12-05 Highlights: gradient compression Citation: 298

NeurIPS 2020 submission: Artemis: tight convergence guarantees for bidirectional compression in Federated Learning. 2020-06-25 Highlights: bidirectional gradient compression

Scheduling Policy and Power Allocation for Federated Learning in NOMA Based MEC. 2020-06-21

(x) Federated Mutual Learning. 2020-06-27 Highlights: Duplicate to Deep Mutual Learning. CVPR 2018

A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning. 2020-06-19 Researcher: Peter Richtárik

Federated Learning With Quantized Global Model Updates. 2020-06-18 Researcher: Mohammad Mohammadi Amiri, Princeton, Information Theory and Machine Learning Highlights: model compression

Federated Learning with Compression: Unified Analysis and Sharp Guarantees. 2020-07-02 Highlight: non-IID, gradient compression + local SGD Researcher: Mehrdad Mahdavi, Jin Rong’s PhD http://www.cse.psu.edu/~mzm616/

Evaluating the Communication Efficiency in Federated Learning Algorithm. 2020-04-06

Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning. 2020-05-21

Ternary Compression for Communication-Efficient Federated Learning. 2020-05-07

Gradient Statistics Aware Power Control for Over-the-Air Federated Learning. 2020-05-04

Communication-Efficient Decentralized Learning with Sparsification and Adaptive Peer Selection. 2020-02-22

(*) RPN: A Residual Pooling Network for Efficient Federated Learning. ECAI 2020.

Intermittent Pulling with Local Compensation for Communication-Efficient Federated Learning. 2020-01-22

Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning. 2019-11-12

L-FGADMM: Layer-Wise Federated Group ADMM for Communication Efficient Decentralized Deep Learning

Gradient Sparification for Asynchronous Distributed Training. 2019-10-24

High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning