Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning

Abstract

Federated learning is a new learning paradigm that decouples data collection and model training via multi-party computation and model aggregation. As a flexible learning setting, federated learning has the potential to integrate with other learning frameworks. We conduct a focused survey of federated learning in conjunction with other learning algorithms. Specifically, we explore various learning algorithms to improve the vanilla federated averaging algorithm and review model fusion methods such as adaptive aggregation, regularization, clustered methods, and Bayesian methods. Following the emerging trends, we also discuss federated learning in the intersection with other learning paradigms, termed federated X learning, where X includes multitask learning, meta-learning, transfer learning, unsupervised learning, and reinforcement learning. In addition to reviewing state-of-the-art studies, this paper also identifies key challenges and applications in this field, while also highlighting promising future directions.

To appear in the International Journal of Machine Learning and Cybernetics

References in corpus (8)

• A Survey on Deep Semi-supervised Learning
• Graph Self-Supervised Learning: A Survey
• Multi-Center Federated Learning: Clients Clustering for Better Personalization
• FedMood: Federated Learning on Mobile Health Data for Mood Detection
• Differentially Private Federated Knowledge Graphs Embedding
• FedCVT: Semi-supervised Vertical Federated Learning with Cross-view Training
• FedICT: Federated Multi-task Distillation for Multi-access Edge Computing
• Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios

Cited by in corpus (5)

• Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations
• Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights
• FedBrain-Distill: Communication-Efficient Federated Brain Tumor Classification Using Ensemble Knowledge Distillation on Non-IID Data
• From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0
• GC-Fed: Gradient Centralized Federated Learning with Partial Client Participation