Towards Personalized Federated Learning

Abstract

In parallel with the rapid adoption of Artificial Intelligence (AI) empowered by advances in AI research, there have been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest towards privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of Personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges and opportunities and envision promising future trajectories of research towards new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.

Accepted by IEEE Transactions on Neural Networks and Learning Systems

References in corpus (5)

• Distilling the Knowledge in a Neural Network
• Learning under Concept Drift: A Review
• Improving fairness in machine learning systems: What do industry practitioners need?
• FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems
• FL-Market: Trading Private Models in Federated Learning

Cited by in corpus (60)

• Vertical Federated Learning: Concepts, Advances and Challenges
• Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities
• Towards Fairness-Aware Federated Learning
• Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey
• FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
• FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data
• FedICT: Federated Multi-task Distillation for Multi-access Edge Computing
• FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems
• Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers
• Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
• Async-HFL: Efficient and Robust Asynchronous Federated Learning in Hierarchical IoT Networks
• Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application
• Federated Continual Learning: Concepts, Challenges, and Solutions
• Graph Federated Learning for CIoT Devices in Smart Home Applications
• FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification
• Behavioral Authentication for Security and Safety
• FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Quality
• Federated Data Analytics: A Study on Linear Models
• Towards Fleet-wide Sharing of Wind Turbine Condition Information through Privacy-preserving Federated Learning
• DACFL: Dynamic Average Consensus Based Federated Learning in Decentralized Topology
• Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
• Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting
• You Can Backdoor Personalized Federated Learning
• Exploring the Landscape of Ubiquitous In-home Health Monitoring: A Comprehensive Survey
• Personalized Graph Federated Learning with Differential Privacy
• A collaborative ensemble construction method for federated random forest
• Personalized Federated Continual Learning via Multi-granularity Prompt
• EchoPFL: Asynchronous Personalized Federated Learning on Mobile Devices with On-Demand Staleness Control
• Federated Learning for Commercial Image Sources
• Personalized Federated Learning with Multi-branch Architecture
• UNIDEAL: Curriculum Knowledge Distillation Federated Learning
• Maximizing Uncertainty for Federated learning via Bayesian Optimisation-based Model Poisoning
• A Federated Learning Benchmark on Tabular Data: Comparing Tree-Based Models and Neural Networks
• DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations
• pFedGame -- Decentralized Federated Learning using Game Theory in Dynamic Topology
• Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning
• Flotilla: A scalable, modular and resilient federated learning framework for heterogeneous resources
• Towards Fast and Stable Federated Learning: Confronting Heterogeneity via Knowledge Anchor
• The Evolution and Future Perspectives of Artificial Intelligence Generated Content
• FedPref: Federated Learning Across Heterogeneous Multi-objective Preferences
• Prospects of federated machine learning in fluid dynamics
• Federated Loss Exploration for Improved Convergence on Non-IID Data
• Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling
• Advancing Ubiquitous Wireless Connectivity through Channel Twinning
• FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworks
• Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data
• NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search
• Privacy-Preserving Personalized Federated Learning for Distributed Photovoltaic Disaggregation under Statistical Heterogeneity
• FL-APU: A Software Architecture to Ease Practical Implementation of Cross-Silo Federated Learning
• FedCoSR: Personalized Federated Learning with Contrastive Shareable Representations for Label Heterogeneity in Non-IID Data
• Fair Decentralized Learning
• Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization
• PPFL: A Personalized Federated Learning Framework for Heterogeneous Population
• Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data
• FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning
• FedDPG: An Adaptive Yet Efficient Prompt-tuning Approach in Federated Learning Settings
• Wind turbine condition monitoring based on intra- and inter-farm federated learning
• RAB${}^2$-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clients
• Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning
• MMiC: Mitigating Modality Incompleteness in Clustered Federated Learning