AAAI 2024 accepted papers on Federated learning and privacy

Personalized and heterogeneous FL · 42 papers

• FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning (114 citations)
• FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning (82 citations)
• Federated Graph Learning under Domain Shift with Generalizable Prototypes (46 citations)
• CLIP-Guided Federated Learning on Heterogeneity and Long-Tailed Data (38 citations)
• FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels (38 citations)
• Federated Learning with Extremely Noisy Clients via Negative Distillation (33 citations)
• FedMut: Generalized Federated Learning via Stochastic Mutation (33 citations)
• FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning (30 citations)
• Exploring One-Shot Semi-supervised Federated Learning with Pre-trained Diffusion Models (28 citations)
• Exploiting Label Skews in Federated Learning with Model Concatenation (27 citations)
• FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise (22 citations)
• Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning (21 citations)

and 30 more in the interactive map.

Privacy attacks and secure learning · 26 papers

• No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation (32 citations)
• A Huber Loss Minimization Approach to Byzantine Robust Federated Learning (25 citations)
• Towards the Robustness of Differentially Private Federated Learning (23 citations)
• Disguise without Disruption: Utility-Preserving Face De-identification (22 citations)
• Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective (19 citations)
• Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authentication (17 citations)
• High-Fidelity Gradient Inversion in Distributed Learning (16 citations)
• Concealing Sensitive Samples against Gradient Leakage in Federated Learning (13 citations)
• LR-XFL: Logical Reasoning-Based Explainable Federated Learning (12 citations)
• FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants (11 citations)
• A Privacy Preserving Federated Learning (PPFL) Based Cognitive Digital Twin (CDT) Framework for Smart Cities (10 citations)
• Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks (10 citations)

and 14 more in the interactive map.

Communication-efficient FL · 13 papers

• FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update (73 citations)
• Efficient Asynchronous Federated Learning with Prospective Momentum Aggregation and Fine-Grained Correction (31 citations)
• On the Role of Server Momentum in Federated Learning (15 citations)
• z-SignFedAvg: A Unified Stochastic Sign-Based Compression for Federated Learning (12 citations)
• A Primal-Dual Algorithm for Hybrid Federated Learning (10 citations)
• FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing (9 citations)
• TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients (9 citations)
• Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users (6 citations)
• FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning (4 citations)
• Federated X-armed Bandit (3 citations)
• Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts (3 citations)
• Algorithmic Foundation of Federated Learning with Sequential Data (2 citations)

and 1 more in the interactive map.

Differential privacy · 9 papers

• DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction) (12 citations)
• Online Sensitivity Optimization in Differentially Private Learning (5 citations)
• Wasserstein Differential Privacy (5 citations)
• Analysis of Differentially Private Synthetic Data: A Measurement Error Approach (3 citations)
• Protect Your Score: Contact-Tracing with Differential Privacy Guarantees (3 citations)
• Finding ε and δ of Traditional Disclosure Control Systems (2 citations)
• A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacy (1 citation)
• Instance-Wise Laplace Mechanism via Deep Reinforcement Learning (Student Abstract)
• A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility