Home » AI Researchs » Research Team » Machine learning

Introduction

“The most important general-purpose technology of our era is Artificial Intelligence, particularly Machine Learning” – Harvard Business Review, 2017/7.

Our research group focuses on some fundamental problems of Machine Learning in general and Deep Learning in particular. We also study to use modern technologies from Machine Learning to other application areas. See the slides here for more detail.

Contact: Assoc. Prof. Than Quang Khoat, Email: khoattq@soict.hust.edu.vn

Research Directions

  • Continual learning: Explore new models and methods that can help a machine to learn continually from tasks to tasks, or when the data may come sequentially and infinitely.
  • Deep generative models: Explore novel models that can generate realistic data (images, videos, music, art, materials,…). Some recent models include Generative Adversarial Nets (GAN), Variational Autoencoders (VAE), Diffusion probabilistic models (DPM).
  • Theoretical foundation of Deep Learning: Explore why deep neural networks often generalize well, why overparameterized models can generalize really well in practice. Explore conditions for high generalization of machine learning models.
  • Representation learning: Explore novel ways to learn a latent representation of data, for which it can boost the performance of different machine learning models in different applications.
  • Recommender system: Explore the efficiency of modern machine learning models in recommender systems.

Some Research Problems

  • Why does catastrophic forgetting appear and how to avoid it when learning continually from tasks to tasks? What is an efficient way to balance different sources of knowledge?
  • Why are noises and sparsity really challenging when working with data streams, for which the data may come sequentially and infinitely? How to overcome those challenges?
  • Explore novel models that can generate realistic data (images, videos, music, art, materials,…).
  • Why can those generative models generalize well although most are unsupervised in nature?
  • Can adversarial models really generalize when different players use different losses?
  • Why do deep neural networks often generalize well?
  • Why do deep neural networks often suffer from adversarial attacks or noises? What are the fundamental roots and how to overcome them?
  • Why can overparameterized models generalize really well in practice?
  • What are the necessary conditions for high generalization of machine learning models?
  • What are the criteria for ensuring that a learnt latent representation of data is good? What are good criteria for learning new latent space?
  • Does self-supervised learning really generalize?
  • Why extreme sparsity is an extreme challenge in recommender systems? How to efficiently deal with sparsity?
  • Can modeling high-order interactions between users and items help improve the effectiveness of recommender systems?
  • Can modeling sequential behaviors of online users help improve the effectiveness of recommender systems?

Team Members

Assoc. Prof. Than Quang Khoat
Team Leader

MS. Ngo Van Linh
Member

Projects and Solutions

[VINIF2019] Human Knowledge in Machine Learning Models for Big Data or Infinite Streams
[ONRG2018] Learning an effective representation for the hidden semantics

Latest Publications

Publications in 2026

  1. Pham Khanh Chi, Tran Vuong Hoang, Dinh Viet Sang, Ngo Van Linh. A framework for neural topic modeling using hierarchical clustering and contrastive learning with optimal transport. Neurocomputing. 132530. 24/12/2025
  2. Dao Bao-Ngoc, Le Minh, Nguyen Quang, Ngo Dinh Luyen, Le Hai Nam, Ngo Van Linh. WAVE++: Capturing within-task variance for continual relation extraction with adaptive prompting. Neurocomputing. 132915. 31/01/2026
  3. Nguyen Tung, Doan Duy-Tung, Luong Huu-Thanh, Ngo Van Linh. Sub-document neural topic model. Knowledge-Based Systems. 114762. 24/10/2025

Publications in 2025

  1. Quang Duc Nguyen, Tung Nguyen, Duc Anh Nguyen, Linh Ngo Van, Sang Dinh, Thien Huu Nguyen. GloCOM: A Short Text Neural Topic Model via Global Clustering Context. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. 1109–1124. Albuquerque, New Mexico. 28/04/2025
  2. Tung Nguyen, Tue Le, Hoang Tran Vuong, Quang Duc Nguyen, Duc Anh Nguyen, Linh Ngo Van, Sang Dinh, Thien Huu Nguyen. Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. 4507–4524. Albuquerque, New Mexico. 28/04/2025
  3. Cui Wei, Ullah Ismat, Lin Weiming, Zhang Jupei, Chen Zhaowei, Yang Shuyi, Peng Wei, Zhuang Yin, Chen Wenjin, Cao Yi, Zhang Shujun, Jin Shengyang, Yang Liang. Multifunctional Sr2+/Zn2+ Co‐Doped Mesoporous Silica Nanoparticles in Injectable Hydrogel for Ameliorating Osteoporotic Osseointegration. Advanced Healthcare Materials. 15/06/2025
  4. Tue Le, Hoang Tran Vuong, Tung Nguyen, Linh Ngo Van, Sang Dinh, Trung Le, Thien Huu Nguyen. Multi-Surrogate-Objective Optimization for Neural Topic Models. Findings of the Association for Computational Linguistics: EMNLP 2025. 135–151. 04/11/2025
  5. Lichuan Xiang, Quan Nguyen-Tri, Lan-Cuong Nguyen, Hoang Pham, Khoat Than, Long Tran-Thanh, Hongkai Wen. DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle. International Conference on Learning Representations. Singapore. 24/04/2025
  6. Luong Tinh Son, Le Thanh-Thien, Doan Thang Viet, Van Linh Ngo, Nguyen Thien Huu, Diep Nguyen Thi Ngoc. ToVo: Toxicity Taxonomy via Voting. Findings of the Association for Computational Linguistics: NAACL 2025. 201-212. 28/04/2025
  7. Doan Tung, To Hiep, Vuong Hong, Visani Muriel, Takasu Atsuhiro, Than Khoat. Generalized ordered Wasserstein distance for sequential data. Pattern Recognition. 111952. 31/05/2025
  8. Hoang Tran Vuong, Tue Le, Tu Vu, Tung Nguyen, Linh Van Ngo, Sang Dinh, Thien Huu Nguyen. HiCOT: Improving Neural Topic Models via Optimal Transport andContrastive Learning. Findings of the Association for Computational Linguistics: ACL 2025. 13894–13920. 27/07/2025
  9. Minh Le, Tien Ngoc Luu, An Nguyen The, Thanh-Thien Le, Trang Nguyen, Tung Thanh Nguyen, Linh Ngo Van, Thien Huu Nguyen. Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective. Proceedings of the AAAI Conference on Artificial Intelligence. 24384-24392. USA. 23/02/2025
  10. Tu Vu, Manh Do, Tung Nguyen, Linh Ngo Van, Sang Dinh, Thien Huu Nguyen. Topic Modeling for Short Texts via Optimal Transport-Based Clustering. Findings of the Association for Computational Linguistics: ACL 2025. 7666–7680. 27/07/2025
  11. Anh Nguyen Hoang, Tran Quyen, Nguyen Thanh Xuan, Diep Nguyen Thi Ngoc, Van Linh Ngo, Nguyen Thien Huu, Le Trung. Mutual-pairing Data Augmentation for Fewshot Continual Relation Extraction. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. 4057-4075. 28/04/2025
  12. Nguyen Tung, Pham Duy-Tung, Nguyen Quang Duc, Ngo Van Linh, Nguyen Duc Anh, Dinh Viet Sang. TopiCOT: Neural topic model aligning with pre-trained clustering and optimal transport. Neurocomputing. 131268. 13/08/2025
  13. Than Khoat, Phan Dat, Vu Giang. Gentle local robustness implies generalization. Machine Learning. 25/03/2025
  14. Nguyen Xuan Thanh, Anh Duc Le, Quyen Tran, Thanh-Thien Le, Linh Ngo Van, Thien Huu Nguyen. Few-Shot, No Problem: Descriptive Continual Relation Extraction. Proceedings of the AAAI Conference on Artificial Intelligence. 25282-25290. USA. 24/02/2025
  15. Anh Duc Le, Nam Le Hai, Thanh Xuan Nguyen, Linh Ngo Van, Nguyen Thi Ngoc Diep, Sang Dinh, Thien Huu Nguyen. Enhancing Discriminative Representation in Similar Relation Clusters for Few-Shot Continual Relation Extraction. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. 2450–2467. Albuquerque, New Mexico. 28/04/2025
  16. Quyen Tran, Tung Lam Tran, Khanh Doan, Toan Tran, Dinh Phung, Khoat Than, Trung Le. Boosting Multiple Views for pretrained-based Continual Learning. International Conference on Learning Representations. Singapore. 24/04/2025
  17. Tien Phat Nguyen, Vu Minh Ngo, Tung Nguyen, Linh Van Ngo, Duc Anh Nguyen, Sang Dinh, Trung Le. XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments. Findings of the Association for Computational Linguistics: EMNLP 2025. 5561–5575. 04/11/2025
  18. Toan Ngoc Nguyen, Nam Le Hai, Nguyen Doan Hieu, Dai An Nguyen, Linh Ngo Van, Thien Huu Nguyen, Sang Dinh. Improving Vietnamese-English Cross-Lingual Retrieval for Legal and General Domains. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. 142–153. Albuquerque, New Mexico. 28/04/2025
  19. Minh Le, An Nguyen, Huy Nguyen, Trang Nguyen, Trang Pham, Linh Van Ngo, Nhat Ho. Mixture of Experts Meets Prompt-Based Continual Learning. Advances in Neural Information Processing Systems. 1-38. 09/12/2024
  20. Hieu Nguyen Manh, Anh Vu Lam, Van Hung Pham, Hai Nam Le, Van Linh Ngo, Diep Nguyen Thi Ngoc, Nguyen Thien Huu. MaGiX: A Multi-Granular Adaptive Graph Intelligence Framework for Enhancing Cross-Lingual RAG. Findings of the Association for Computational Linguistics: EMNLP 2025. 5202-5219. Suzhou, China. 04/11/2025
  21. Le Tue, Hoang Tran Vuong, Quyen Tran, Linh Ngo Van, Mehrtash Harandi, and Trung Le. Token-Level Self-Play with Importance-Aware Guidance for Large Language Models. The Thirty-ninth Annual Conference on Neural Information Processing Systems, NeurIPS 2025. 1-36. 01/12/2025
  22. Lan-Cuong Nguyen, Quan Nguyen-Tri, Bang Khanh, Dung D. Le, Long Tran-Thanh, Khoat Than. Provably Improving Generalization of Few-shot models with Synthetic Data. International Conference on Machine Learning (ICML). Canada. 12/07/2025
  23. Pham Thanh Duc, Hai Nam Le, Van Linh Ngo, Diep Nguyen Thi Ngoc, Dinh Sang, Nguyen Thien Huu. Mitigating Non-Representative Prototypes and Representation Bias in Few-Shot Continual Relation Extraction. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 10791-10809. Vienna, Austria. 27/07/2025
  24. Minh-Phuc Truong, Hai An Vu, Tu Vu, Nguyen Thi Ngoc Diep, Linh Ngo Van, Thien Huu Nguyen, Trung Le. EMO: Embedding Model Distillation via Intra-Model Relation and Optimal Transport Alignments. the Association for Computational Linguistics: EMNLP 2025. 7606-7618. 04/11/2025

Publications in 2024

  1. Thanh-Thien Le, Viet Dao, Linh Nguyen, Thi-Nhung Nguyen, Linh Ngo Van, Thien Nguyen. SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 3632–3644. 16/06/2024
  2. Sikandar Ali Qalati, Domitilla Magni, and Faiza Siddiqui. Senior Management's Sustainability Commitment and Environmental Performance: Revealing the Role of Green Human Resource Management Practices.. Business Strategy and the Environment. 02/08/2024
  3. Thanh-Thien Le, Manh Nguyen, Tung Thanh Nguyen, Linh Ngo Van, Thien Huu Nguyen. Continual Relation Extraction via Sequential Multi-Task Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 18444-18452. 22/02/2024
  4. T. K. Lai, and I. L. Ngo. A new design and optimization of VD-ECF micro-pump: Advancements in electrohydraulic performance. Physics of Fluids. 29/07/2024
  5. Tung Nguyen, Tung Pham, Linh Ngo Van , Ha-Bang Ban , Khoat Than. Out-of-vocabulary handling and topic quality control strategies in streaming topic models. Neurocomputing. 128757. 19/10/2024
  6. T. K. Lai, and I. L. Ngo. An investigation on the thermo-electrohydraulic performance of novel ECF micro-pump.. International Journal of Heat and Mass Transfer. 29/09/2024
  7. Cuong Quoc Dang, Dung Trung Nguyen, Dat Ha Mai, Duc Van Vu, Anh Ngoc Hoang, Uyen Thu Nguyen, Thiep Van Nguyen, Tan Xuan Phan, Tung Phong Doan, and Cuong Dinh Hoang. From Synthesis to Realism: Enhancing Logistics with Computer Vision and Domain-Adversarial Training. ICIIT '24: Proceedings of the 2024 9th International Conference on Intelligent Information Technology. 327-333. Hồ Chí Minh City, VIet Nam. 23/02/2024
  8. Sikandar Ali Qalati, MengMeng Jiang, Samuel Gyedu, and Emmanuel Kwaku Manu. Do Strong Innovation Capability and Environmental Turbulence Influence the Nexus Between Customer Relationship Management and Business Performance?. Business Strategy and the Environment. 02/07/2024
  9. T. K. Lai, and I. L. Ngo. An investigation on the electrohydraulic performance of novel ECF micro-pump with NACAshaped electrodes. Theoretical and Computational Fluid Dynamics. 29/02/2024
  10. Hoàng Thanh Hải, Thân Quang Khoát. A DEEP LEARNING APPROACH FOR CREDIT SCORING. TNU Journal of Science and Technology. 14/05/2024
  11. Duy-Tung Pham, Thien Trang Nguyen Vu, Tung Nguyen, Linh Ngo Van, Duc Anh Nguyen, Thien Huu Nguyen. NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization. the 2024 Conference on Empirical Methods in Natural Language Processing. 7758–7772. 11/11/2024
  12. Tung Tran, Khoat Than, Danilo Vargas. Robust Visual Reinforcement Learning by Prompt Tuning. ACCV 2024. Lecture Notes in Computer Science.. 387–401. Hanoi. 08/12/2024
  13. Tinh Luong, Thanh-Thien Le, Linh Ngo, Thien Nguyen. Realistic Evaluation of Toxicity in Large Language Models. Association for Computational Linguistics ACL 2024. 1038–1047. 11/08/2024
  14. JYE Tin, WW Tan, AA Bakar, MS Mahali, FF Lothai, NF Mohammad, SSA Hassan & KF Chin. A Conceptual Design of Sustainable Solar Photovoltaic (PV) Powered Corridor Lighting System with IoT Application. ICREEM 2022. 09/03/2024
  15. Quyen Tran, Nguyen Xuan Thanh, Nguyen Hoang Anh, Nam Le Hai, Trung Le, Linh Van Ngo, Thien Huu Nguyen. Preserving Generalization of Language models in Few-shot Continual Relation Extraction. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 13771–13784. 11/11/2024
  16. Hieu Man, Chien Van Nguyen, Nghia Trung Ngo, Linh Ngo, Franck Dernoncourt, Thien Huu Nguyen. Hierarchical Selection of Important Context for Generative Event Causality Identification with Optimal Transports. Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 8122–8132. Torino, Italy. 20/05/2024
  17. Tung Doan, Tuan Phan, Phu Nguyen, Khoat Than, Muriel Visani, Atsuhiro Takasu. Partial ordered Wasserstein distance for sequential data. Neurocomputing. 127908-127925. 19/05/2024
  18. Trinh Thi Ha, Nguyen Trung Dung, Nguyen Thanh Huong, Tran Trong An, Pham Van Tuan, Vu Ngoc Hung, Chu Manh Hoang. Investigating the coupling length of two triangle hybrid gap plasmonic waveguides. The International Conference on Advanced Materials and Technology (ICAMT 2024). 10-13. Hanoi. 09/10/2024
  19. Viet Nguyen, Giang Vu, Tung Nguyen Thanh, Toan Tran, Khoat Than. On inference stability for diffusion models. AAAI Conference on Artificial Intelligence. Canada. 22/02/2024
  20. Viet Dao, Van-Cuong Pham, Quyen Tran, Thanh-Thien Le, Linh Ngo Van, Thien Huu Nguyen. Lifelong Event Detection via Optimal Transport. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 12610–12621. 12/11/2024