Khoa D. Doan is currently an Assistant Professor of Computer Science in the College of Engineering and Computer Science at VinUniversity, Hanoi, Vietnam. Prior to his current appointment, he worked as an AI Researcher at Baidu Research, USA. He received his PhD in Computer Science at Virginia Tech, and MS in Computer Science at the University of Maryland, College Park. In the past, he worked as a senior Software Engineer at various enterprise software companies, and as a senior Data Scientist/Researcher in high-performance and distributed computing projects at NASA and various advertising companies, such as Criteo AI Lab. Besides research, he also spends time engaging and advising AI technology with startups.
More information about him can be found at https://khoadoan.me.
His research focuses on developing computational frameworks that enable existing complex machine learning models to be more suitable for practical uses in various domains such as computational advertising, computer vision, and natural language processing. Specifically, his research focuses on improving the following aspects of existing models: (i) training, (i) inference, (iii) realistic assumptions, and (iv) security understanding. Currently, his research activities include, but are not limited to, the following three themes: deep information retrieval and its applications, generative models, and robust and reliable machine learning. He has been a program committee member for premier conferences such as ICML, CVPR, ECCV, ICCV, ICLR, and NeurIPS.
- D. Doan, Y. Lao, & P. Li, “Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class”. Thirty-Sixth Conference on Neural Information Processing Systems 2022 (NeurIPS).
- K. D. Doan & C. K. Reddy, “Unified Learning of Multipurpose Energy Based Generative Hashing Network”. Sixteenth Asian Conference on Computer Vision 2022 (ACCV).
- K. D. Doan, Y. Peng, & P. Li, “One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching”. 2022 Conference on Computer Vision and Pattern Recognition (CVPR).
- K. D. Doan, Y. Lao, & P. Li, “Backdoor Attack with Imperceptible Input and Latent Modification”. Thirty-fifth Conference on Neural Information Processing Systems 2021 (NeurIPS).
- K. D. Doan, Y. Lao, W. Zhao, & P. Li, “LIRA: Learnable, Imperceptible and Robust Backdoor Attacks”. 2021 IEEE International Conference on Computer Vision (ICCV).
- K. D. Doan, S. Manchanda, S. Mahapatra, & CK. Reddy, “Interpretable Graph Similarity Computation via Differentiable Optimal Alignment of Node Embeddings”, In Proceedings of International ACM SIGIR conference on research and development in Information Retrieval 2021 (SIGIR).
- K. Doan & C. K. Reddy. Efficient Implicit Unsupervised Text Hashing using Adversarial Autoencoder. In Proceedings of The Web Conference, 2020 (WWW).
- K. Doan, P. Yadav & C. K. Reddy. Adversarial Factorization Autoencoder for Look-alike Modeling. In Proceedings of ACM International Conference on Information and Knowledge Management, 2019 (CIKM).
For the full list of publications please visit Google Scholar
SELECTED AWARDS AND HONORS
- Criteo Research Award – Virginia Tech 2018
- NSF Urban Computing Fellowship – Virginia Tech 2016-2017
- Graduation Honor, Summer Cum Laude – Webster University 2006
- 2021: PhD in Computer Science, Virginia Tech.
- 2015: MS in Computer Science, University of Maryland, College Park.
- 2006: BS in Computer Science with a Minor in Mathematics, Webster University.