| LightGBM: A Highly Efficient Gradient Boosting Decision Tree G Ke, Q Meng, T Finley, T Wang, W Chen, W Ma, Q Ye, TY Liu Advances in Neural Information Processing Systems, 3148-3156, 2017 | 3733 | 2017 |
| A communication-efficient parallel algorithm for decision tree Q Meng, G Ke, T Wang, W Chen, Q Ye, ZM Ma, TY Liu Advances in Neural Information Processing Systems, 1279-1287, 2016 | 78 | 2016 |
| Deep subdomain adaptation network for image classification Y Zhu, F Zhuang, J Wang, G Ke, J Chen, J Bian, H Xiong, Q He IEEE transactions on neural networks and learning systems 32 (4), 1713-1722, 2020 | 71 | 2020 |
| DeepGBM: A deep learning framework distilled by GBDT for online prediction tasks G Ke, Z Xu, J Zhang, J Bian, TY Liu Proceedings of the 25th ACM SIGKDD International Conference on Knowledge …, 2019 | 61* | 2019 |
| Rethinking Positional Encoding in Language Pre-training G Ke, D He, TY Liu International Conference on Learning Representations (ICLR) 2021, 2020 | 59* | 2020 |
| Invertible image rescaling M Xiao, S Zheng, C Liu, Y Wang, D He, G Ke, J Bian, Z Lin, TY Liu European Conference on Computer Vision, 126-144, 2020 | 48 | 2020 |
| Do Transformers Really Perform Bad for Graph Representation? C Ying, T Cai, S Luo, S Zheng, G Ke, D He, Y Shen, TY Liu arXiv preprint arXiv:2106.05234, 2021 | 24 | 2021 |
| Transformers with Competitive Ensembles of Independent Mechanisms A Lamb, D He, A Goyal, G Ke, CF Liao, M Ravanelli, Y Bengio arXiv preprint arXiv:2103.00336, 2021 | 7 | 2021 |
| Mc-bert: Efficient language pre-training via a meta controller Z Xu, L Gong, G Ke, D He, S Zheng, L Wang, J Bian, TY Liu arXiv preprint arXiv:2006.05744, 2020 | 7 | 2020 |
| Less is More: Pre-training a Strong Siamese Encoder Using a Weak Decoder S Lu, C Xiong, D He, G Ke, W Malik, Z Dou, P Bennett, T Liu, A Overwijk arXiv preprint arXiv:2102.09206, 2021 | 5 | 2021 |
| Taking Notes on the Fly Helps Language Pre-Training Q Wu, C Xing, Y Li, G Ke, D He, TY Liu International Conference on Learning Representations, 2020 | 5* | 2020 |
| Stable, fast and accurate: Kernelized attention with relative positional encoding S Luo, S Li, T Cai, D He, D Peng, S Zheng, G Ke, L Wang, TY Liu Advances in Neural Information Processing Systems 34, 2021 | 2 | 2021 |
| How could Neural Networks understand Programs? D Peng, S Zheng, Y Li, G Ke, D He, TY Liu arXiv preprint arXiv:2105.04297, 2021 | 1 | 2021 |
| Revisiting Language Encoding in Learning Multilingual Representations S Luo, K Gao, S Zheng, G Ke, D He, L Wang, TY Liu arXiv preprint arXiv:2102.08357, 2021 | 1 | 2021 |
| First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track C Ying, M Yang, S Zheng, G Ke, S Luo, T Cai, C Wu, Y Wang, Y Shen, ... | 1 | 2021 |
| LightMC: A Dynamic and Efficient Multiclass Decomposition Algorithm Z Liu, G Ke, J Bian, T Liu arXiv preprint arXiv:1908.09362, 2019 | 1 | 2019 |
| Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder S Lu, D He, C Xiong, G Ke, W Malik, Z Dou, P Bennett, TY Liu, A Overwijk Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021 | | 2021 |
| Awardee Solution of KDD Cup 2021 OGB Large-Scale Challenge Graph-Level Track C Ying, M Yang, S Zheng, G Ke, S Luo, T Cai, C Wu, Y Wang, Y Shen, ... arXiv preprint arXiv:2106.08279, 2021 | | 2021 |
| LazyFormer: Self Attention with Lazy Update C Ying, G Ke, D He, TY Liu arXiv preprint arXiv:2102.12702, 2021 | | 2021 |
| Light Multi-Segment Activation for Model Compression Z Xu, G Ke, J Zhang, J Bian, TY Liu AAAI, 6542-6549, 2020 | | 2020 |
Tie-Yan LiuAssistant Managing Director, Microsoft Research Asia; IEEE Fellow, ACM Distinguished MemberVerified email at microsoft.com
