AAAI 2022 accepted papers on Federated learning and privacy
28 of the 1,319 papers accepted at AAAI 2022 (2.1%) are on Federated learning and privacy, compared with 1.6% at AAAI 2021. They fall into 4 topics.
See AAAI 2022 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Differential privacy · 10 papers
- DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy (29 citations)
- Differentially Private Normalizing Flows for Synthetic Tabular Data Generation (16 citations)
- The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection (14 citations)
- Differentially Private Regret Minimization in Episodic Markov Decision Processes (7 citations)
- Private Rank Aggregation in Central and Local Models (6 citations)
- PrivateMail: Supervised Manifold Learning of Deep Features with Privacy for Image Retrieval (6 citations)
- Subspace Differential Privacy (6 citations)
- Locally Private k-Means Clustering with Constant Multiplicative Approximation and Near-Optimal Additive Error (4 citations)
- Incorporating Item Frequency for Differentially Private Set Union (3 citations)
- Local Differential Privacy for Belief Functions (3 citations)
Communication-efficient FL · 9 papers
- SplitFed: When Federated Learning Meets Split Learning (696 citations)
- Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better (97 citations)
- SpreadGNN: Decentralized Multi-Task Federated Learning for Graph Neural Networks on Molecular Data (59 citations)
- Efficient Device Scheduling with Multi-Job Federated Learning (35 citations)
- Is Your Data Relevant?: Dynamic Selection of Relevant Data for Federated Learning (30 citations)
- Coordinating Momenta for Cross-Silo Federated Learning (23 citations)
- Implicit Gradient Alignment in Distributed and Federated Learning (21 citations)
- SmartIdx: Reducing Communication Cost in Federated Learning by Exploiting the CNNs Structures (21 citations)
- DISTREAL: Distributed Resource-Aware Learning in Heterogeneous Systems (12 citations)
Personalized and heterogeneous FL · 7 papers
- FedProto: Federated Prototype Learning across Heterogeneous Clients (751 citations)
- HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images (157 citations)
- FedSoft: Soft Clustered Federated Learning with Proximal Local Updating (116 citations)
- Seizing Critical Learning Periods in Federated Learning (45 citations)
- FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition (37 citations)
- Cross-Modal Federated Human Activity Recognition via Modality-Agnostic and Modality-Specific Representation Learning (34 citations)
- Federated Nearest Neighbor Classification with a Colony of Fruit-Flies (4 citations)
