Xixiang Lyu

Artificial Intelligence · 2021

A researcher in the Science corpus: 3 papers; trusts 28 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 88 citations into it; #32,307 of 35,345 by trust here, #24,417 by citations
• Safety, Robustness & Interpretability — 38 citations into it
• Computer Vision and Pattern Recognition — 27 citations into it
• Signal Processing — 24 citations into it
• Privacy & Security — 22 citations into it
• Computational Theory and Mathematics — 7 citations into it
• Model Architectures — 6 citations into it

Whom Xixiang Lyu trusts overall

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

1. Cynthia Dwork
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Kaiming He
5. Sergey Zagoruyko
6. Yoshua Bengio
7. Yuanshun Yao
8. Kang Liu
9. Brandon Tran
10. Yann LeCun

Who trusts Xixiang Lyu overall

1. Dongxian Wu

Papers from Xixiang Lyu's perspective

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

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. ImageNet: A large-scale hierarchical image database
4. Learning Multiple Layers of Features from Tiny Images
5. Gradient-based learning applied to document recognition
6. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
7. Long Short-Term Memory
8. Attention is All you Need (Neural Information Processing Systems)
9. Going deeper with convolutions
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks (2021) — 575 citations
• Privacy‐preserving federated learning based on multi‐key homomorphic encryption (2021) — 388 citations
• Anti-Backdoor Learning: Training Clean Models on Poisoned Data (2021) — 473 citations