Advances in Federated Learning

The field of federated learning is moving towards personalized and privacy-preserving approaches. Recent research has focused on developing novel algorithms and frameworks that can handle non-IID data distributions, mitigate model poisoning attacks, and ensure secure aggregation. Notably, techniques such as adaptive collaboration, distance-based aggregation, and pliable index coding have shown promise in improving the accuracy and efficiency of federated learning models. Furthermore, the integration of federated learning with other areas like graph neural networks and recommendation systems has led to the development of new architectures and methods. Some papers have proposed innovative solutions to address the challenges of federated learning, including CLoVE, which utilizes client embeddings derived from model losses to identify and separate clients from different clusters, and SABRE-FL, which filters poisoned prompt updates using an embedding-space anomaly detector. Other notable papers include Detect & Score, which proposes a method for privacy-preserving misbehaviour detection and contribution evaluation, and Flotilla, a scalable and modular federated learning framework. Overall, the field of federated learning is rapidly advancing, with a focus on developing more robust, efficient, and privacy-preserving methods for distributed machine learning.

Sources

CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings

SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning

Detect \& Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learning

Privacy-Preserving Federated Learning Scheme with Mitigating Model Poisoning Attacks: Vulnerabilities and Countermeasures

Asymptotically Optimal Secure Aggregation for Wireless Federated Learning with Multiple Servers

Who Should I Listen To? Adaptive Collaboration in Personalized Federated Learning

Accuracy and Security-Guaranteed Participant Selection and Beamforming Design for RIS-Assisted Federated Learning

Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning

Decentralized Pliable Index Coding For Federated Learning In Intelligent Transportation Systems

Cooperative Sheaf Neural Networks

Privacy-Preserving Quantized Federated Learning with Diverse Precision

A Full-Stack Platform Architecture for Self-Organised Social Coordination

Far From Sight, Far From Mind: Inverse Distance Weighting for Graph Federated Recommendation

DARTS: A Dual-View Attack Framework for Targeted Manipulation in Federated Sequential Recommendation

REDUS: Adaptive Resampling for Efficient Deep Learning in Centralized and Federated IoT Networks

Flotilla: A scalable, modular and resilient federated learning framework for heterogeneous resources

S2FGL: Spatial Spectral Federated Graph Learning

Fluid Democracy in Federated Data Aggregation

Built with on top of