NeurIPS 2026 accepted papers on Federated learning and privacy
112 of the 6,080 papers accepted at NeurIPS 2026 (1.8%) are on Federated learning and privacy, compared with 2.1% at NeurIPS 2025. They fall into 4 topics.
See NeurIPS 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
Differential privacy · 47 papers
- Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy
- Breaking the Quality–Privacy Tradeoff in Tabular Data Generation via In-Context Learning
- Computationally Efficient Replicable Learning of Parities and Applications
- Differentially Private Model Merging
- GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents
- Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees
- Minimax Optimal Two-Sample Testing under Local Differential Privacy
- Minimax Private Estimation of Smooth Optimal-Transport Maps
- Online Differentially Private Consistent Clustering
- Optimal Rates for Differentially Private Hypothesis Testing with E-values
- PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
- Privacy Amplification Persists under Unlimited Synthetic Data Release
and 35 more in the interactive map.
Personalized and heterogeneous FL · 35 papers
- Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs
- Federated Concept-Based Models: Interpretable models with distributed supervision
- FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning
- HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
- Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning
- SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning
- Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks
- Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation
- BLEND: Balancing Personalization vs. Generalization in Federated Vision–Language Models
- Complexity-Aware LoRA Aggregation for Modality-Heterogeneous Federated Person Re-identification
- Efficient Collaborative LLM Fine-Tuning over Heterogeneous Mobile Devices via Many Backbones to One Side-Network Tuning
- E²Gen: Evidential Energy-Based Generation for Fair Federated Graph Learning
and 23 more in the interactive map.
Privacy attacks and secure learning · 19 papers
- A Unified Framework for Adversary-Aware Differential Privacy Bounds
- CLIOPATRA: Extracting Private Information from LLM Insights
- Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic
- Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning
- Position: Life-Logging Video Streams Make the Privacy–Utility Trade-off Inevitable
- Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
- Prune to Protect: Faster Training and Enhanced Privacy by Dynamic Data Pruning
- Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
- ASAP: Fast Adaptive Sliding Agnostic Poisoning Attack on Federated Learning
- Auditing Privacy Leakage in Tabular Foundation Model Embeddings
- Breaking BAD: Heterogeneous Byzantine-Robust Federated Learning via Gather and Scatter Scores
- Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift
and 7 more in the interactive map.
Communication-efficient FL · 11 papers
- ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation
- Principled Federated Random Forests for Heterogeneous Data
- A typed tensor language for federated learning
- Approximation Guarantees for Robust Aggregation in Federated Learning
- Beyond Flat Gossip: Tiered Gossip Learning for Scalable Collaborative AI
- Breaking the $\sqrt{d}$ Communication Barrier in Federated Sampling with Adaptive Hamiltonian Monte Carlo
- Energy Is All We Need: Beyond FLOPs in Model-Heterogeneous Federated Learning
- Mitigating Data Heterogeneity Effect in Client-Reshuffling-Based Federated Learning
- Nerve-Skeleton Message Passing for Federated Optimization with Overlapping Parameters
- On Communication-Efficient Training of Ensembles in Federated Learning