NeurIPS 2023 accepted papers on Federated learning and privacy
130 of the 3,584 papers accepted at NeurIPS 2023 (3.6%) are on Federated learning and privacy, compared with 3.0% at NeurIPS 2022. They fall into 4 topics.
See NeurIPS 2023 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 · 57 papers
- Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger (22 citations)
- Privacy Auditing with One (1) Training Run (7 citations)
- Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models (6 citations)
- Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection (5 citations)
- Functional Renyi Differential Privacy for Generative Modeling (5 citations)
- Have it your way: Individualized Privacy Assignment for DP-SGD (5 citations)
- Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation (5 citations)
- Unleashing the Power of Randomization in Auditing Differentially Private ML (4 citations)
- Gaussian Differential Privacy on Riemannian Manifolds (3 citations)
- Practical Differentially Private Hyperparameter Tuning with Subsampling (3 citations)
- Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy (3 citations)
- (Amplified) Banded Matrix Factorization: A unified approach to private training (2 citations)
and 45 more in the interactive map.
Communication-efficient FL · 27 papers
- FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks (16 citations)
- Convergence Analysis of Sequential Federated Learning on Heterogeneous Data (13 citations)
- Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction (11 citations)
- DELTA: Diverse Client Sampling for Fasting Federated Learning (8 citations)
- Zeroth-Order Methods for Nondifferentiable, Nonconvex, and Hierarchical Federated Optimization (5 citations)
- EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning (4 citations)
- Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data (4 citations)
- SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning (4 citations)
- Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices (3 citations)
- Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds (3 citations)
- Federated Multi-Objective Learning (3 citations)
- FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout (3 citations)
and 15 more in the interactive map.
Personalized and heterogeneous FL · 26 papers
- Dynamic Personalized Federated Learning with Adaptive Differential Privacy (39 citations)
- FedFed: Feature Distillation against Data Heterogeneity in Federated Learning (27 citations)
- Towards Personalized Federated Learning via Heterogeneous Model Reassembly (13 citations)
- Eliminating Domain Bias for Federated Learning in Representation Space (11 citations)
- DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning (7 citations)
- FedL2P: Federated Learning to Personalize (7 citations)
- Spectral Co-Distillation for Personalized Federated Learning (7 citations)
- Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Federated Object Detection (6 citations)
- Structured Federated Learning through Clustered Additive Modeling (6 citations)
- Adaptive Test-Time Personalization for Federated Learning (5 citations)
- One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning (5 citations)
- PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning. (5 citations)
and 14 more in the interactive map.
Privacy attacks and secure learning · 20 papers
- A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning (31 citations)
- Ethical Considerations for Responsible Data Curation (13 citations)
- Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training (8 citations)
- RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks (7 citations)
- Students Parrot Their Teachers: Membership Inference on Model Distillation (6 citations)
- Federated Spectral Clustering via Secure Similarity Reconstruction (3 citations)
- Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release (2 citations)
- Robust and Actively Secure Serverless Collaborative Learning (2 citations)
- Strategic Data Sharing between Competitors (2 citations)
- Understanding Deep Gradient Leakage via Inversion Influence Functions (2 citations)
- Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense (1 citation)
- Incentives in Private Collaborative Machine Learning (1 citation)
and 8 more in the interactive map.