AAAI 2025 accepted papers on Federated learning and privacy

Personalized and heterogeneous FL · 57 papers

• Exploring Vacant Classes in Label-Skewed Federated Learning (21 citations)
• FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning (18 citations)
• Asynchronous Federated Clustering with Unknown Number of Clusters (15 citations)
• Cross-Silo Feature Space Alignment for Federated Learning on Clients with Imbalanced Data (15 citations)
• Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach (15 citations)
• FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis (13 citations)
• PFedCS: A Personalized Federated Learning Method for Enhancing Collaboration among Similar Classifiers (13 citations)
• DCHM: Dynamic Collaboration of Heterogeneous Models Through Isomerism Learning in a Blockchain-Powered Federated Learning Framework (11 citations)
• FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning (11 citations)
• Federated Learning with Sample-level Client Drift Mitigation (11 citations)
• Fed-DFA: Federated Distillation for Heterogeneous Model Fusion Through the Adversarial Lens (10 citations)
• Federated Graph-Level Clustering Network (10 citations)

and 45 more in the interactive map.

Privacy attacks and secure learning · 27 papers

• Federated Unlearning with Gradient Descent and Conflict Mitigation (23 citations)
• A New Federated Learning Framework Against Gradient Inversion Attacks (12 citations)
• Label-Free Backdoor Attacks in Vertical Federated Learning (12 citations)
• MFL-Owner: Ownership Protection for Multi-modal Federated Learning via Orthogonal Transform Watermark (10 citations)
• SADBA: Self-Adaptive Distributed Backdoor Attack Against Federated Learning (10 citations)
• BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities (9 citations)
• Breaking Data Silos in Parkinson’s Disease Diagnosis: An Adaptive Federated Learning Approach for Privacy-Preserving Facial Expression Analysis (7 citations)
• Federated Graph Condensation with Information Bottleneck Principles (7 citations)
• Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning (5 citations)
• Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage (5 citations)
• Mjölnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion (5 citations)
• A Privacy-Preserving Framework for Generative Model-driven Synthetic Datasets (4 citations)

and 15 more in the interactive map.

Communication-efficient FL · 16 papers

• Decentralized Federated Learning with Model Caching on Mobile Agents (6 citations)
• GAS: Generative Activation-Aided Asynchronous Split Federated Learning (6 citations)
• FedPop: Federated Population-based Hyperparameter Tuning (5 citations)
• FedSPU: Personalized Federated Learning for Resource-Constrained Devices with Stochastic Parameter Update (5 citations)
• TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning (5 citations)
• An Efficient and Accurate Dynamic Sparse Training Framework Based on Parameter-Freezing (3 citations)
• DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game (3 citations)
• EFSkip: A New Error Feedback with Linear Speedup for Compressed Federated Learning with Arbitrary Data Heterogeneity (2 citations)
• FedCross: Intertemporal Federated Learning Under Evolutionary Games (2 citations)
• Tackling Intertwined Data and Device Heterogeneities in Federated Learning with Unlimited Staleness (1 citation)
• WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling (1 citation)
• A High-Efficiency Federated Learning Method Using Complementary Pruning for D2D Communication (Student Abstract)

and 4 more in the interactive map.

Differential privacy · 9 papers

• Federated t-SNE and UMAP for Distributed Data Visualization (5 citations)
• DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately (4 citations)
• Federated Assemblies (2 citations)
• Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning (2 citations)
• Differentially Private Prototypes for Imbalanced Transfer Learning (1 citation)
• Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processes (1 citation)
• Federated Binary Matrix Factorization Using Proximal Optimization (1 citation)
• DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
• Improving Private Random Forest Prediction Using Matrix Representation