AI Research & Development

My R&D works on Artificial Intelligence can be largely divided into 3 categories:

1. Generative AI

2. General Artificial Intelligence, including but not limited to models, optimizations, etc

3. Leveraging AI to solve challenges in the real-world problems

Generative AI

1. X Ni, H Xie, Y Yang, S Wang, W Wang, Y Liu. IPFC: An Attentive Face Completion Network with Identity Preserving. International Symposium on Electrical, Electronics and Information. 2022

2. M. Zhang, X. Liu, C. Liu, X. Zhang and H. Xie, "FST-Net: Exploiting Frequency Spatial Temporal Information for Low-Quality Fake Video Detection," 2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI), Washington, DC, USA, 2021, pp. 536-543.

3. Y Yang, X Ni, Y Hao, C Liu, W Wang, Y Liu, H Xie. Mf-gan: Multi-conditional fusion generative adversarial network for text-to-image synthesis. International Conference on Multimedia Modeling, pp. 41-53, 2022

4. X Zhang, S Wang, C Liu, M Zhang, X Liu, H Xie. Thinking in patch: Towards generalizable forgery detection with patch transformation. PRICAI 2021: Trends in Artificial Intelligence. 2021

5. P Zhou, B Finley, LH Lee, Y Liao, H Xie, P Hui. Towards user-centered metrics for trustworthy AI in immersive cyberspace. arXiv preprint arXiv:2203.03718

6. H Li, P Zhou, Y Lin, Y Hao, H Xie, Y Liao. TKN: Transformer-based Keypoint Prediction Network For Real-time Video Prediction. arXiv preprint arXiv:2303.09807

7. C. Luo, B. Zou, X. Lyu, and H. Xie, “Indoor scene reconstruction: From panorama images to cad models,” in 2019 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), 2019, pp. 317–320.

Information Retrieval Using Knowledge Graphs, Graph Learning

1. Y Zhao, X Wang, J Chen, Y Wang, W Tang, X He, H Xie. Time-aware path reasoning on knowledge graph for recommendation. ACM Transactions on Information Systems. 41 (2), 1-26

2. W Tang, B Xu, Y Zhao, Z Mao, Y Liu, Y Liao, H Xie. UniRel: Unified representation and interaction for joint relational triple extraction. arXiv preprint arXiv:2211.09039

3. Y. Wang, H. Zhang, and H. Xie, “A model of text-enhanced knowledge graph representation learning with collaborative attention,” in Proceedings of The Eleventh Asian Conference on Machine Learning, ser. Proceedings of Machine Learning Research, vol. 101, Nagoya, Japan: PMLR, Nov. 2019, pp. 220–235.

4. Y. Wang, H. Zhang, Y. Liu, and H. Xie, “Kg-to-text generation with slot-attention and link-attention,” in Natural Language Processing and Chinese Computing, Cham: Springer International Publishing, 2019, pp. 223–234, isbn: 978-3-030-32233-5.

5. Y. Wang, H. Zhang, Y. Li, and H. Xie, “Simplified representation learning model based on parameter-sharing for knowledge graph completion.,” in CCIR, ser. Lecture Notes in Computer Science, vol. 11772, Springer, 2019, pp. 67–78

6. Y. Wang, H. Zhang, and H. Xie, “Geography-enhanced link prediction framework for knowledge graph completion,” in Knowledge Graph and Semantic Computing: Knowledge Computing and Language Understanding, Singapore: Springer Singapore, 2019, pp. 198–210. 

7. Y. Wang, Y. Liu, H. Zhang, and H. Xie, “Leveraging lexical semantic information for learning concept-based multiple embedding representations for knowledge graph completion,” in Web and Big Data, Cham: Springer International Publishing, 2019, pp. 382–397.

8. Y. Wang, Y. Liu, and H. Xie, “A novel distributed knowledge reasoning model,” in Artificial Intelligence and Security, Cham: Springer International Publishing, 2019, pp. 237–247.

AI Enablers for Ultra-Efficient Learning and Security

We designed a zero-shot learning algorithm to alleviate the requirement for large-amount of training data, published results in NeurIPS 2019. 

NeurIPS is a top tier academic conference in the AI domain (according to Google Scholar, NeurIPS is ranked #1 in AI conferences/journals).

Based on this research, we lead main AI players in China and established a national industrial standard on deep learning with small data set (T/CESA 1034–2019).

1. J. Ni, S. Zhang, and H. Xie, “Dual adversarial semantics-consistent network for generalized zero-shot learning,” in Neural Information Processing Systems (NeurIPS), vol. 32, Dec. 2019, pp. 6143–6154.

We also designed numerous enabling technologies for AI to learn fast and efficiently. For instance, Mercury speeds up model learning by 218%, Guided Dropout significantly improves false positives, precision-recall curve and average precision without increasing the amount of computation.

2. Mercury: Fast and Optimal Device Placement for Large Deep Learning Models. H Xu, P Zhou, H Xie, Y Liao. Proceedings of the 52nd International Conference on Parallel Processing, pp. 412-422. 2023

3. Guided Dropout: Improving Deep Networks Without Increased Computation. Y Liu, Y Li, Z Xu, X Liu, H Xie, H Zeng. INTELLIGENT AUTOMATION AND SOFT COMPUTING 36 (3), 2519-2528

4. Celeritas: Fast optimizer for large dataflow graphs. H Xu, Y Liao, H Xie, P Zhou. arXiv preprint arXiv:2208.00184

5. Towards Secure Multi-Agent Deep Reinforcement Learning: Adversarial Attacks and Countermeasures. C Zheng, C Zhen, H Xie, S Yang. 2022 IEEE Conference on Dependable and Secure Computing (DSC), 1-8

AI for Understanding the Physical World

We study how Artificial Intelligence can help solve challenges in health care, by collaborating with distinguished researchers from top tier hospitals (AnDing Hospital, TianTan Hospital) and medical research institutions (CCMU).

1. On exploring multiplicity of primitives and attributes for texture recognition in the wild. W Zhai, Y Cao, J Zhang, H Xie, D Tao, ZJ Zha. in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 1, pp. 403-420, Jan. 2024

2. W. Zhai, Y. Cao, H. Xie and Z. -J. Zha, "Deep Texton-Coherence Network for Camouflaged Object Detection," in IEEE Transactions on Multimedia, vol. 25, pp. 5155-5165, 2023

3. TKN: Transformer-based Keypoint Prediction Network For Real-time Video Prediction. H Li, P Zhou, Y Lin, Y Hao, H Xie, Y Liao. arXiv preprint arXiv:2303.09807

4. W. Zhai, Y. Cao, Z.-J. Zha, H. Xie, and F. Wu, “Deep structure-revealed network for texture recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2020, pp. 11 007–11 016. 

AI for Health Care

We designed and implemented a system allowing Internet applications and individuals to search close contacts (e.g., same flight, same shuttle bus) with Covid-19 positive passengers during the pandemic; served approx. 1 billion queries in less than a month.

1. M. Hu, H. Lin, J. Wang, C. Xu, A. J. Tatem, B. Meng, X. Zhang, Y. Liu, P. Wang, G. Wu, H. Xie, and S. Lai, “Risk of Coronavirus Disease 2019 Transmission in Train Passengers: an Epidemiological and Modeling Study,” Clinical Infectious Diseases, vol. 72, no. 4, pp. 604–610, Feb. 2021, issn: 1058-4838.

We study how Artificial Intelligence can help solve challenges in health care, by collaborating with distinguished researchers from top tier hospitals (AnDing Hospital, TianTan Hospital, etc) and research institutions (for instance, CMU).

2. R Bai, Y Guo, X Tan, L Feng, H Xie. An EEG-based depression detection method using machine learning model. International Journal of Pharma Medicine and Biological Sciences 10 (1), 17-22

3. L. Chen, Y. Liu, W. Xiao, Y. Wang, and H. Xie, “SpeakerGAN: Speaker identification with conditional generative adversarial network,” Neurocomputing, vol. 418, pp. 211–220, 2020.

4. Y. Zhang, Y. Wang, X. Wang, B. Zou, and H. Xie, “Text-based decision fusion model for detecting depression,” in 2020 2nd Symposium on Signal Processing Systems, ser. SSPS 2020, Guangdong, China: Association for Computing Machinery, 2020, pp. 101–106

5. B. Zou, Z. Lin, H. Wang, Y. Wang, X. Lyu, and H. Xie, “Joint prediction of group-level emotion and cohesiveness with multi-task loss,” in Proceedings of the 2020 5th International Conference on Mathematics and Artificial Intelligence, ser. ICMAI 2020, Chengdu, China: Association for Computing Machinery, 2020, pp. 24–28.

6. L. Zhang, J. Li, S. Wang, X. Duan, W. Yan, H. Xie, and S. Huang, “Spatio-temporal fusion for macro- and micro-expression spotting in long video sequences,” in 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) (FG), Los Alamitos, CA, USA: IEEE Computer Society, May 2020, pp. 734–741.

7. J. Ding, Z. Tian, X. wen Lyu, Q. Wang, B. Zou, and H. Xie, “Real-time micro-expression detection in unlabeled long videos using optical flow and lstm neural network.,” in CAIP (1), ser. Lecture Notes in Computer Science, vol. 11678, Springer, 2019, pp. 622–634.

AI for Public Safety in Physical World

1. M Sun, P Zhou, H Tian, Y Liao, H Xie. Spatial-temporal attention network for crime prediction with adaptive graph learning. International Conference on Artificial Neural Networks, pp. 656-669

2. Y Lu, P Zhou, Y Liao, H Xie. Spatiotemporal and Semantic Zero-inflated Urban Anomaly Prediction. arXiv preprint arXiv:2304.01569

3. X. Tang, B. Gong, Y. Yu, H. Yao, Y. Li, H. Xie, and X. Wang, “Joint modeling of dense and incomplete trajectories for citywide traffic volume inference,” in The World Wide Web Conference, ser. WWW ’19, San Francisco, CA, USA: Association for Computing Machinery, 2019, pp. 1806–1817.

AI for Public  Safety in Cyberspace

1. Y Yang, R Yang, Y Li, K Cui, Z Yang, Y Wang, J Xu, H Xie. RoSGAS: Adaptive Social Bot Detection with Reinforced Self-supervised GNN Architecture Search. ACM Transactions on the Web 17 (3), 1-31

2. Q Guo, H Xie, Y Li, W Ma, C Zhang. Social bots detection via fusing BERT and graph convolutional networks. Symmetry 14 (1), 30

3. Y. Jin, T. Yang, Y. Li, and H. Xie, “Effective android malware detection based on deep learning,” in Artificial Intelligence and Security, ser. Communications in Computer and Information Science, Hohhot, China: Springer Singapore, 2020, pp. 206–218.

4. Y. Zhao, Y. Li, T. Yang, and H. Xie, “Suzzer: A vulnerability-guided fuzzer based on deep learning,” in Information Security and Cryptology, Cham: Springer International Publishing, 2020, pp. 134–153, isbn: 978-3-030-42921-8.

5. Y. Jin, T. Yang, Y. Li, and H. Xie, “Effective android malware detection based on deep learning,” in Artificial Intelligence and Security, ser. Communications in Computer and Information Science, Hohhot, China: Springer Singapore, 2020, pp. 206–218.

6. Y. Li, H. Jin, X. Yu, H. Xie, Y. Xu, H. Xu, and H. Zeng, “Intelligent prediction of private information diffusion in social networks,” Electronics, vol. 9, no. 5, 2020, issn: 2079-9292. doi: 10.3390/electronics9050719.

7. T. Yang, X. Shi, Y. Li, B. Huang, H. Xie, and Y. Shen, “Workload allocation based on user mobility in mobile edge computing,” Journal on Big Data, vol. 2, no. 3, pp. 105–115, 2020, issn: 2579-0056. doi: 10.32604/jbd.2020.010958.