Cross-Silo Federated Learning: Challenges and Opportunities

  title={Cross-Silo Federated Learning: Challenges and Opportunities},
  author={Chao Huang and Jianwei Huang and Xin Liu},
—Federated learning (FL) is an emerging technology that enables the training of machine learning models from multiple clients while keeping the data distributed and private. Based on the participating clients and the model training scale, federated learning can be classified into two types: cross-device FL where clients are typically mobile devices and the client number can reach up to a scale of millions; cross-silo FL where clients are organizations or companies and the client number is… 

Figures from this paper

Quantifying the Impact of Label Noise on Federated Learning

It is shown that label noise slows down the convergence of FL training, and the global model tends to overfit when the noise level is high, which is consistent with the the- oretical analysis.

Incentivizing Data Contribution in Cross-Silo Federated Learning

—In cross-silo federated learning, clients (e.g., organi- zations) train a shared global model using local data. However, due to privacy concerns, the clients may not contribute enough data points



Vertical Federated Learning: Challenges, Methodologies and Experiments

This paper proposes a general framework on VFL, and highlights the key differences between VFL and conventional FL, and discusses research challenges rooted in VFL systems under four aspects, i.e., security and privacy risks, expensive computation and communication costs, possible structural damage caused by model splitting, and system heterogeneity.

Advances and Open Problems in Federated Learning

Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

Federated Machine Learning: Concept and Applications

This work proposes building data networks among organizations based on federated mechanisms as an effective solution to allow knowledge to be shared without compromising user privacy.

A review of applications in federated learning

Federated Learning: Challenges, Methods, and Future Directions

The unique characteristics and challenges of federated learning are discussed, a broad overview of current approaches are provided, and several directions of future work that are relevant to a wide range of research communities are outlined.

Federated Learning on Non-IID Data: A Survey

A survey on security and privacy of federated learning

Robust Aggregation for Federated Learning

The experiments show that RFA is competitive with the classical aggregation when the level of corruption is low, while demonstrating greater robustness under high corruption, and establishes the convergence of the robust federated learning algorithm for the stochastic learning of additive models with least squares.

Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning

This work aims to develop a comprehensive systemization for poisoning attacks on FL by enumerating all possible threat models, variations of poisoning, and adversary capabilities, and presents a critical analysis of untargeted poisoning attacks under practical, production FL environments.

A Profit-Maximizing Model Marketplace with Differentially Private Federated Learning

This work focuses on the broker-centric design of a novel differentially private FL (DPFL)-based ML model marketplace, and proposes efficient algorithms that are both theoretically guaranteed and empirically validated for profit maximization.