Lei Shu

Artificial Intelligence · with Liu · 2016–2022

A researcher in the Science corpus: 16 papers; trusts 660 researchers and is trusted by 57 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 382 citations into it; #3,722 of 35,345 by trust here, #4,682 by citations
• Natural Language Processing — 165 citations into it; #1,907 of 5,688 by trust here, #2,846 by citations
• Computer Vision and Pattern Recognition — 157 citations into it; #10,501 of 21,575 by trust here, #12,419 by citations
• Representation & Self-Supervised Learning — 92 citations into it
• Meta & Continual Learning — 88 citations into it; #209 of 1,041 by trust here, #254 by citations
• Model Architectures — 43 citations into it
• Reinforcement Learning — 31 citations into it
• Large Language Models — 26 citations into it; #367 of 799 by trust here, #564 by citations

Whom Lei Shu trusts overall

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

1. Diederik P. Kingma
2. B. Liu
3. Geoffrey E. Hinton
4. Yoshua Bengio
5. Ilya Sutskever
6. Alex Krizhevsky
7. Jimmy Ba
8. Zhiyuan Chen
9. Geli Fei
10. Yann LeCun

Who trusts Lei Shu overall

1. Bing Liu
2. Hu Xu
3. Zixuan Ke
4. Sepideh Esmaeilpour
5. Magdalena Biesialska
6. B. Liu
7. Ryota Yoshihashi
8. Da-Wei Zhou
9. Ting-En Lin
10. Poojan Oza

Papers from Lei Shu's perspective

Ordered by how strongly the researchers Lei Shu 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. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• DOC: Deep Open Classification of Text Documents (2017) — 345 citations
• Lifelong Learning CRF for Supervised Aspect Extraction (2017) — 105 citations
• Lifelong-RL: Lifelong Relaxation Labeling for Separating Entities and Aspects in Opinion Targets (2016) — 34 citations
• Open-world Learning and Application to Product Classification (2018) — 119 citations
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019) — 791 citations
• Continual Training of Language Models for Few-Shot Learning (2022) — 45 citations
• Continual Learning with Knowledge Transfer for Sentiment Classification (2021) — 36 citations
• Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (2021) — 159 citations
• CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (2021) — 68 citations
• Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP (2021) — 229 citations
• Modeling Multi-Action Policy for Task-Oriented Dialogues (2019) — 11 citations
• Unseen Class Discovery in Open-world Classification (2018) — 76 citations
• Incorporating the Structure of the Belief State in End-to-End Task-Oriented Dialogue Systems (2018)
• Lifelong Domain Word Embedding via Meta-Learning (2018) — 39 citations
• Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction (2018) — 358 citations
• Dual Attention Network for Product Compatibility and Function Satisfiability Analysis (2017) — 13 citations