Welcome to Lingkai Kong (孔令恺)’s homepage! I am a Ph.D student in the School of Computational Science and Engineering at Georgia Institute of Technology. I am working with Prof. Chao Zhang. I recieved my B.E. in Information Engineering from Southeast University.
My research spans across machine learning, natural language processing and data mining. I am particularly interested in making trustworthy intelligent system in open-world settings. Toward this goal, I am currently working on the following research thrusts:
Email: lkkong [at] gatech [dot] edu
Uncertainty Quantification in Deep Learning
Lingkai Kong, Harshavardhan Kamarthi, Peng Chen, B Aditya Prakash and Chao Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), 2023 (Conference Tutorial)
[Tutorial page]
When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez, Chao Zhang and B Aditya Prakash
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD)
DyGen: Fine-Tuning Language Models with Noisy Labels by Dynamics-Enhanced Generative Modeling
Yuchen Zhuang, Yue Yu, Lingkai Kong, Xiang Chen and Chao Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD)
Autoregressive Diffusion Model for Graph Generation
Lingkai Kong, Jiaming Cui, Haotian Sun, Yuchen Zhuang, B Aditya Prakash and Chao Zhang
International Conference on Machine Learning (ICML), 2023
End-to-End Stochastic Optimization with Energy-based Model
Lingkai Kong, Jiaming Cui, Yuchen Zhuang, Rui Feng, B Aditya Prakash and Chao Zhang
Advances in Neural Information Processing Systems (NeurIPS), 2022 (Selected as Oral)
[Paper]
[Code]
AcTune: Uncertainty-Aware Active Self-Training for Active Fine-Tuning of Pretrained Language Models
Yue Yu, Lingkai Kong, Jieyu Zhang, Rongzhi Zhang, Chao Zhang
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2022
[Paper]
[Code]
CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez, Chao Zhang and B Aditya Prakash
The Web Conference (WWW), 2022
[Paper]
[Code]
When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez, Chao Zhang and B Aditya Prakash
Advances in Neural Information Processing Systems (NeurIPS), 2021
[Paper]
[Code]
Data Efficient Estimation for Quality of Transmission Through Active Learning in Fiber-Wireless Integrated Network
Shuang Yao, Chin-Wei Hsu, Lingkai Kong, Qi Zhou, Shuyi Shen, Rui Zhang, Shang-Jen Su, Yahya Alfadhli, and Gee-Kung Chang
Journal of Lightwave Technology, Vol. 39, No.18, pp. 5691-5698, Sept. 2021
[Paper]
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
Lingkai Kong, Haoming Jiang, Yuchen Zhuang, Jie Lyu, Tuo Zhao and Chao Zhang
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
[Paper]
[Code]
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
Lingkai Kong, Jimeng Sun and Chao Zhang
International Conference on Machine Learning (ICML), 2020
[Paper]
[Code]
[Video]
Learning Deep Hidden Nonlinear Dynamics from Aggregate Data
Yisen Wang, Bo Dai, Lingkai Kong, Sarah Erfani, James Bailey and Hongyuan Zha
Conference on Uncertainty in Artificial Intelligence (UAI), 2018
[Paper]
Wide-range Dimmable Clipped Flip-OFDM For Indoor Visible Light Communication
Liang Wu, Lingkai Kong, Zaichen Zhang, Jian Dang and Huaping Liu
IEEE/CIC International Conference on Communications in China (ICCC), 2018
[Paper]
A Novel OFDM Scheme for VLC Systems under LED Nonlinear Constraints
Lingkai Kong, Congcong Cao, Siyuan Zhang, Mengchao Li and Liang Wu
EAI International Conference On Communications and Networking in China (ChinaCom), 2016
[Paper]
Program Committee/Reviewer: NeurIPS 2023, KDD 2021-2023, ACL 2021-2023, EMNLP 2020-2023, NAACL 2021-2022