NeurIPS 2025 accepted papers on Federated learning and privacy
120 of the 5,812 papers accepted at NeurIPS 2025 (2.1%) are on Federated learning and privacy, compared with 2.5% at NeurIPS 2024. They fall into 4 topics.
See NeurIPS 2025 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 · 46 papers
- Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping (5 citations)
- FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA (2 citations)
- Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy (2 citations)
- Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix (1 citation)
- GeoClip: Geometry-Aware Clipping for Differentially Private SGD (1 citation)
- How Well Can Differential Privacy Be Audited in One Run? (1 citation)
- Private Training Large-scale Models with Efficient DP-SGD (1 citation)
- Struct-Bench: A Benchmark for Differentially Private Structured Text Generation (1 citation)
- Sum Estimation under Personalized Local Differential Privacy (1 citation)
- A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
- Adaptive Sigmoid Clipping for Balancing the Direction–Magnitude Mismatch Trade-off in Differentially Private Learning
- An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
and 34 more in the interactive map.
Personalized and heterogeneous FL · 45 papers
- Gains: Fine-grained Federated Domain Adaptation in Open Set (2 citations)
- Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings (2 citations)
- A Fair Federated Learning Method for Handling Client Participation Probability Inconsistencies in Heterogeneous Environments (1 citation)
- Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning (1 citation)
- FedFree: Breaking Knowledge-sharing Barriers through Layer-wise Alignment in Heterogeneous Federated Learning (1 citation)
- FedIGL: Federated Invariant Graph Learning for Non-IID Graphs (1 citation)
- FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization (1 citation)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (1 citation)
- FORLA: Federated Object-centric Representation Learning with Slot Attention (1 citation)
- MARS-VFL: A Unified Benchmark for Vertical Federated Learning with Realistic Evaluation (1 citation)
- OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction (1 citation)
- Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning (1 citation)
and 33 more in the interactive map.
Communication-efficient FL · 16 papers
- Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA (4 citations)
- FedEL: Federated Elastic Learning for Heterogeneous Devices (2 citations)
- Efficient Adaptive Federated Optimization (1 citation)
- FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling (1 citation)
- Bi-Directional Communication-Efficient Stochastic FL via Remote Source Generation
- Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
- Diffusion Federated Dataset
- Distributed mediation analysis with communication efficiency
- Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning
- Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
and 4 more in the interactive map.
Privacy attacks and secure learning · 13 papers
- Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning (2 citations)
- DictPFL: Efficient and Private Federated Learning on Encrypted Gradients (1 citation)
- Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning (1 citation)
- MARS: A Malignity-Aware Backdoor Defense in Federated Learning (1 citation)
- Tabula: A Tabular Self-Supervised Foundation Model for Single-Cell Transcriptomics (1 citation)
- An Investigation of Memorization Risk in Healthcare Foundation Models
- Competitive Advantage Attacks to Decentralized Federated Learning
- Deep Learning with Plausible Deniability
- Enhancing Privacy in Multimodal Federated Learning with Information Theory
- FedRACE: A Hierarchical and Statistical Framework for Robust Federated Learning
- FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
- More effort is needed to protect pedestrian privacy in the era of AI
and 1 more in the interactive map.