NeurIPS 2018 accepted papers on Federated learning and privacy
18 of the 1,008 papers accepted at NeurIPS 2018 (1.8%) are on Federated learning and privacy, compared with 1.0% at NeurIPS 2017. They fall into 3 topics.
See NeurIPS 2018 in the interactive map
Submitting to NeurIPS? Checklist →
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 · 15 papers
- cpSGD: Communication-efficient and differentially-private distributed SGD (184 citations)
- Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences (154 citations)
- Differentially Private Testing of Identity and Closeness of Discrete Distributions (42 citations)
- Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited (36 citations)
- Differentially Private k-Means with Constant Multiplicative Error (28 citations)
- Differentially Private Uniformly Most Powerful Tests for Binomial Data (24 citations)
- Local Differential Privacy for Evolving Data (23 citations)
- Model-Agnostic Private Learning (21 citations)
- Differentially Private Bayesian Inference for Exponential Families (20 citations)
- Differentially Private Change-Point Detection (15 citations)
- Data-dependent PAC-Bayes priors via differential privacy (9 citations)
- Differential Privacy for Growing Databases (5 citations)
and 3 more in the interactive map.
Privacy attacks and secure learning · 2 papers
Communication-efficient FL · 1 paper
- COLA: Decentralized Linear Learning (42 citations)
