Keith Bonawitz

Artificial Intelligence · 2008–2019

A researcher in the Science corpus: 6 papers; trusts 8 researchers and is trusted by 33 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 433 citations into it; #5,788 of 35,345 by trust here, #1,011 by citations
• Privacy & Security — 223 citations into it; #372 of 709 by trust here, #46 by citations
• Federated & Distributed Learning — 132 citations into it; #136 of 319 by trust here, #13 by citations
• Efficiency & Compression — 37 citations into it
• Information Theory — 14 citations into it
• Molecular Biology — 6 citations into it

Whom Keith Bonawitz trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. H. Brendan McMahan
2. Johannes Blömer
3. Jakub Konecný
4. David Chaum
5. S. Jammalamadaka
6. Cynthia Dwork
7. Mihir Bellare
8. Henry Corrigan-Gibbs
9. Sebastian Caldas
10. Reza Shokri

Who trusts Keith Bonawitz overall

1. Peter Kairouz
2. Jinhyun So
3. Qinbin Li
4. Chaoyang He
5. H. Brendan McMahan
6. Lingjuan Lyu
7. Jakub Konecný
8. Amir Salman Avestimehr
9. Tian Li
10. Nguyen Binh Truong

Papers from Keith Bonawitz's perspective

Ordered by how strongly the researchers Keith Bonawitz trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Gradient-based learning applied to document recognition
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. Learning Multiple Layers of Features from Tiny Images
7. ImageNet: A large-scale hierarchical image database
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Going deeper with convolutions
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Church: a language for generative models (2008) — 843 citations
• Practical Secure Aggregation for Privacy-Preserving Machine Learning (2017) — 4,229 citations
• Towards Federated Learning at Scale: System Design (2019) — 3,255 citations
• Advances and Open Problems in Federated Learning (2019) — 9,019 citations
• Practical Secure Aggregation for Federated Learning on User-Held Data (2016) — 662 citations
• Federated Learning with Autotuned Communication-Efficient Secure Aggregation (2019) — 84 citations