Xuan-Son Vu

About Me

Hey there, welcome!

I am a Senior Researcher at WASP Media & Language Arena funded by WASP, working with Assoc. Prof. Johanna, Co-PI, and senior AI/ML lead at Devr INC. I received my Ph.D in Privacy-aware Machine Learning under the supervision of Assoc. Prof. Lili Jiang and Prof. Erik Elmroth. Previously I have worked with Assis. Prof. Monowar, Prof. Iryna Gurevych on NLP, Prof. Seong-Bae Park on Machine Learning, and Assoc. Prof. Ha-Quang Thuy on Opinion Mining.

Before that, I obtained a M.Sc. degree in the Computer Science Department at School of Computer Sci. and Eng., Kyungpook National University, with focus on NLP and Machine Learning. I also obtained a bachelor's degree from the Department of Information Technology at University of Engineering and Technology, Vietnam National University.

Research Interest

My research interest has been primarily focused on privacy enhancing tech - both for free text and multimodal data to power downstream applications. My awards and honours include the 3rd place for best paper awards at CICLING 2019, best student paper award and best inquisitive mind award at CICLING 2018. I received the best paper award at the 40th Conference of the Korea Information Processing Society in 2014. I am also a co-founder in multiple projects such as AIcovidVN, AIHUB.ML, MLOpsVN.

Projects / Grants

• 2023:2029: Project "Mormor Karl är 27 år: automatisk pseudonymisering av forskningsdata" has been given almost SEK 18 million (>$1.7M) in grants from the Swedish Research Council (VR). Project research area: Privacy, Adversarial Learning, NLP

Academic Activities

• 2023:
• Nov 2023: Organizing a special session at ICONIP2023: Reliable & Secure ML.
• Workshop Chair of IEEE-BigDataService2023
• 2022:
• Nov 2022: Organizing a special session at ICONIP2022: Reliable & Secure ML.
• May 2022: member of a grading commettee (undergraduate level) at The Ho Chi Minh City University of Technology
• PC member of SoICT2022, IJCAI2022 (cert), ICONIP'22
• Publicity Chairs of IEEE-BigDataService2022
• Dec 2021: Organizing Co-chair of VLSP2021
• Dec 2021: Organizing a special session at ICONIP2021: Reliable & Secure ML
• Dec 2021: Session Chair at RIVF2021

PhD/Intern students

• Arezoo Hatefi (PhD student): co-supervisor with Prof. Frank Drewes
• Adil Bin Bhutto (Intern), B.Tech. in Computer Science and Enginnering final year student at Tezpur University (a Central University), India. [Period: February 2021 - April 2022].
• Khanh-Tung Tran (Intern), Ho Chi Minh City University of Technology (HCMUT), Vietnam

Publications

Here are some of my publications:

• Optimized and Adaptive Federated Learning for Straggler-Resilient Device Selection
  Sourasekhar Banerjee, Xuan-Son Vu, Monowar Bhuyan
  In: Proceedings of IJCNN 2022 (to appear)
  
• Cformer: Semi-Supervised Text Clustering Based on Pseudo Labeling
  Arezoo Hatefi, Xuan-Son Vu, Monowar Bhuyan, Frank Drewes
  In: Proceedings of CIKM 2021
  
• ICDAR2021 Competition on Multimodal Emotion Recognition on Comics Scenes
  Nhu-Van Nguyen, Xuan-Son Vu, Christophe Rigaud, Lili Jiang, Jean-Christophe Buri
  In: Proceedings of the 16th International Conference on Document Analysis and Recognition (ICDAR)
  [challenge's page]
• Modular Graph Transformer Networks for Multi-Label Image Classification
  Hoang D. Nguyen, Xuan-Son Vu, Duc-Trong Le
  In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI2021)
  [github], [poster] , [slides]
• WINFRA: A Web-Based Platform for Semantic Data Retrieval and Data Analytics
  Addi Ait-Mlouk, Xuan-Son Vu, Lili Jiang
  In: Mathematics (Special Issue "Applied Data Analytics"), 2020, 8(11), 2090; doi:10.3390/math8112090
  
• Multimodal Review Generation with Privacy and Fairness Awareness
  Xuan-Son Vu, Thanh-Son Nguyen, Duc-Trong Le, Lili Jiang
  In: Proceedings of the 28th International Conference on Computational Linguistics (COLING), 2020.
  [Inproceedings], [bibtex], [github], [poster]
• Reinforced Data Sampling for Model Diversification
  Hoang D. Nguyen, Xuan-Son Vu, Quoc-Tuan Truong, Duc-Trong Le
  arXiv preprint arXiv:2006.07100, [bibtex], [github]
• Privacy-Preserving Visual Content Tagging using Graph Transformer Networks
  Xuan-Son Vu, Duc-Trong Le, Christoffer Edlund, Lili Jiang, Hoang D. Nguyen
  In: Proceedings of the 28th ACM International Conference on Multimedia (ACM MM), 2020
  [Inproceedings], [bibtex], [github]
• ETNLP: a visual-aided systematic approach to select pre-trained embeddings for a downstream task
  Xuan-Son Vu, Thanh Vu, Son N. Tran, Lili Jiang
  In: Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP), 2019.
  [Inproceedings], [bibtex], [video], [github], [poster]
• Graph-based Interactive Data Federation System for Heterogeneous Data Retrieval and Analytics
  Xuan-Son Vu, Addi Ait-Mlouk, Erik Elmroth, Lili Jiang
  Demo Track, In: Proceedings of The 30th TheWebConf'19 (formerly WWW), May, 2019
  [Inproceedings], [bibtex], [video], [poster]
• dpUGC: Learn Differentially Private Representation for User Generated Contents
  Xuan-Son Vu, Son N. Tran, Lili Jiang
  In: Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing, April, 2019, 3rd place for best paper awards
  [Inproceedings], [bibtex], [slides]
• Generic Multilayer Network Data Analysis with the Fusion of Content and Structure
  Xuan-Son Vu, Abhishek Santra, Sharma Chakravarthy, Lili Jiang
  In: Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing, April, 2019.
  [Inproceedings], [bibtex], [poster]
• Improving Recurrent Neural Networks with Predictive Propagation for Sequence Labelling
  Son N. Tran, Qing Zhang, Anthony Nguyen, Xuan-Son Vu, Son Ngo
  In: Proceedings of the 25th International Conference on Neural Information Processing (ICONIP-2018)
  [Inproceedings], [bibtex], [pdf]
• NIHRIO at SemEval-2018 Task 3: A Simple and Accurate Neural Network Model for Irony Detection in Twitter
  Thanh Vu, Dat Quoc Nguyen, Xuan-Son Vu, Dai Quoc Nguyen, Michael Catt, Michael Trenell
  In: Proceedings of NAACL-HTL’18, at the 12nd International Workshop on Semantic Evaluation (SemEval-2018)
  [Inproceedings], [bibtex], [code]
• Self-adaptive Privacy Concern Detection for User-generated Content
  Xuan-Son Vu, Lili Jiang
  In: Proceedings of the 19th International Conference on Computational Linguistics and Intelligent Text Processing, March 2018, best student paper award, best why-boy award
  [Inproceedings], [bibtex]
• Lexical-semantic resources: yet powerful resources for automatic personality classification
  Xuan-Son Vu, Lucie Flekova, Lili Jiang, Iryna Gurevych
  In: Proceedings of the 9th Global WordNet Conference, January 2018
  [Inproceedings],[bibtex], slides
• Personality-Based Knowledge Extraction for Privacy-preserving Data Analysis
  Xuan-Son Vu, Lili Jiang, Anders Brändström, Erik Elmroth
  In: Proceedings of K-CAP 2017, December 2017, Austin, Texas, United States
  [Inproceedings], [bibtex], [video demo]
• Building a Vietnamese SentiWordNet Using Vietnamese Electronic Dictionary and String Kernel
  Xuan-Son Vu, Hyun-Je Song, Seong-Bae Park
  3rd Pacific Rim Knowledge Acquisition Workshop, PKAW 2014, Gold Cost, Qld, Australia, December 1-2, 2014.
  [Inproceedings].
• Improving Text-Based Image Search with Textual and Visual Features Combination
  Xuan-Son Vu, Thanh Vu, Huong Nguyen, and Quang-Thuy Ha.
  Proceedings of the Sixth International Conference KSE, 2014.
• Construction of Vietnamese SentiWordNet By Using Vietnamese Dictionary
  Xuan-Son Vu, Seong-Bae Park.
  The 40th Conference of the Korea Information Processing Society, accepted on April-9th-2014, pp. 745-748, best paper award, [code].
• Mining User/Movie Preferred Features Based on Reviews for Video Recommendation System
  Xuan-Son Vu, Seong-Bae Park.
  The 2nd Workshop on Future Researches of Computer Science and Engineering, Kyungpook National University Annual Workshop, South Korea, pp.21-24.

You can find some of my project code at my github homepage.

Teaching

I do enjoy a bit of teaching:

• Machine Learning Course 2019: give a lecture, assignments, grading.
• Machine Learning Course 2018: give a lecture, assignments, grading.
• Fundamentals of Artificial Intelligence, 2018: invited Lecture.

More About Me

Here are more facts about me:

• I do a bit photography in my sparetime.
• I enjoy running, playing board games, bowling.

Contact

Office

Room 439, MIT Building, Umeå University

Email

someone@somewhere in which someone is sonvx and somewhere is cs [dot] umu [dot] se