AAAI 2026 accepted papers on Federated learning and privacy
115 of the 4,417 papers accepted at AAAI 2026 (2.6%) are on Federated learning and privacy, compared with 3.1% at AAAI 2025. They fall into 4 topics.
See AAAI 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Personalized and heterogeneous FL · 59 papers
- FedALT: Federated Fine-Tuning Through Adaptive Local Training with Rest-of-World LoRA (5 citations)
- Causally-Aware Attribute Completion for Incomplete Federated Graph Clustering (3 citations)
- Data Heterogeneity and Forgotten Labels in Split Federated Learning (3 citations)
- Federated Graph-level Clustering Network with Attribute Inference (2 citations)
- Federated Incomplete Multi-View Clustering with Tensorized Low-Rank Constraint (2 citations)
- Incomplete Multi-View Unsupervised Federated Feature Selection via Cooperative Particle Swarm Optimization and Tensor-Aligned Learning (2 citations)
- Personalized Federated Graph-Level Clustering Network (2 citations)
- Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework (2 citations)
- TransFR: Transferable Federated Recommendation with Adapter Tuning on Pre-trained Language Models (2 citations)
- Breaking the Aggregation Bottleneck in Federated Recommendation: A Personalized Model Merging Approach (1 citation)
- Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs (1 citation)
- Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation (1 citation)
and 47 more in the interactive map.
Privacy attacks and secure learning · 23 papers
- Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models (4 citations)
- Anti-adversarial Learning: Desensitizing Prompts for Large Language Model (3 citations)
- LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping (2 citations)
- DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain Skew (1 citation)
- FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training (1 citation)
- InfoDecom: Decomposing Information for Defending Against Privacy Leakage in Split Inference (1 citation)
- PCFormer: Accelerating Privacy-preserving Transformer Inference by Partition and Combination (1 citation)
- Poisoning with a Pill: Circumventing Detection in Federated Learning (1 citation)
- PRISM: Privacy-Aware Routing for Adaptive Cloud–Edge LLM Inference via Semantic Sketch Collaboration (1 citation)
- ReBoot: Encrypted Training of Deep Neural Networks with CKKS Bootstrapping (1 citation)
- Bant: Byzantine Antidote via Trial Function and Trust Scores
- Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
and 11 more in the interactive map.
Differential privacy · 18 papers
- An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses (1 citation)
- DP-GenG: Differentially Private Dataset Distillation Guided by DP-Generated Data (1 citation)
- Differentially Private Linear Programming: Reduced Sub-Optimality and Guaranteed Constraint Satisfaction
- Differentially Private Subspace Fine-Tuning for Large Language Models
- DP-NCB: Privacy Preserving Fair Bandits
- Efficient, Secure, Differentially Private Deep Learning in the Two-Server Model
- Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering
- Estimating the True Distribution of Data Collected with Randomized Response
- Improved Differentially Private Algorithms for Rank Aggregation
- PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure
- Privacy Preserving In-Context-Learning Framework for Large Language Models
- Private Frequency Estimation via Residue Number Systems
and 6 more in the interactive map.
Communication-efficient FL · 15 papers
- FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models (1 citation)
- FedCure: Mitigating Participation Bias in Semi-Asynchronous Federated Learning with Non-IID Data (1 citation)
- Ripple Shapley: Data Influence Attribution in One Federated Training Run (1 citation)
- Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Pack (1 citation)
- A Unified Convergence Analysis for Semi-Decentralized Learning: Sampled-to-Sampled vs. Sampled-to-All Communication
- BIQ: Bisection Interval Quantization for Communication-efficient Federated Learning
- Communication-Efficient Heterogeneous Federated Learning with Sparse Prototypes in Resource-Constrained Environments
- FedPM: Federated Learning Using Second-order Optimization with Preconditioned Mixing of Local Parameters
- FusedRec: Fused Embedding Communication for Distributed Recommendation Training on GPUs
- MSCFL: Model Structure-Aware Clustered Federated Learning for System Heterogeneity and Data Drift
- Personalized Federated Learning with Bidirectional Communication Compression via One-Bit Random Sketching
- Re-architecting Personalized Federated Learning for Demanding Edge Environments
and 3 more in the interactive map.