Xudong Han

Co-founder and CEO of LibrAI, Research at MBZUAI

About

I am the co-founder and CEO at LibrAI and a researcher at MBZUAI.

Previously, I did my Ph.D at The University of Melbourne, supervised by Prof. Trevor Cohn and Prof. Tim Baldwin, working on topics concerning fairness, especially in natural language processing. I received my master degree from The University of Melbourne, and bachelor degree from Shandong University (Weihai).

Experience

Education

2020/2 - 2023/12

Ph.D Candidate of Engineering


NLP group, School of Computing and Information Systems, The University of Melbourne, Australia.

2018/2 - 2019/12

Master of Science (Dean's honor list)


Data Science, School of Mathematics and Statistics, The University of Melbourne, Australia.

2013/9 - 2017/6

Banchelor of Engineering


Computer Science and Technology, Shandong University (Weihai), China.

Work

2019 - 2021

Tutor


Statistical Machine Learning, School of Computing and Information Systems, The University of Melbourne.

2019 Semester 2

Tutor


Web Search and Text Analysis, School of Computing and Information Systems, The University of Melbourne.

2015 - 2016

Chair


AI & Robotic Student Club, Shandong University (Weihai).

2013 - 2017

Class Monitor


Class 2, Computer Science and Technology, Shandong University (Weihai).

Research in progress

Publications

  • Han, Xudong, Timothy Baldwin and Trevor Cohn (to appear). Everybody Needs Good Neighbours: An Unsupervised Locality-based Method for Bias Mitigation. In Proceedings of The 11th International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda.
  • Han, Xudong, Timothy Baldwin and Trevor Cohn (to appear). Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP. In Proceedings of The 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), Dubrovnik, Croatia.
  • Han, Xudong, Aili Shen, Yitong Li, Lea Frermann, Timothy Baldwin and Trevor Cohn. 2022. FairLib: A Unified Framework for Assessing and Improving Fairness, In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) Demo Session, Abu Dhabi.
  • Shen, Aili, Xudong Han, Trevor Cohn, Timothy Baldwin and Lea Frermann. 2022. Does Representational Fairness Imply Empirical Fairness? In Findings of AACL-IJCNLP 2022, virtual.
  • Han, Xudong, Aili Shen, Trevor Cohn, Timothy Baldwin and Lea Frermann. 2022. Systematic Evaluation of Predictive Fairness , In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2022), virtual.
  • Han, Xudong, Aili Shen, Yitong Li, Lea Frermann, Timothy Baldwin and Trevor Cohn. 2022. Towards Fair Dataset Distillation, In Proceedings of the Third Workshop on Simple and Efficient Natural Language Processing (SustainNLP 2022), Abu Dhabi, UAE.
  • Han, Xudong, Timothy Baldwin and Trevor Cohn. 2022. Balancing out Bias: Achieving Fairness Through Balanced Training, In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), Abu Dhabi, UAE.
  • Shen, Aili*, Xudong Han*, Trevor Cohn, Timothy Baldwin and Lea Frermann. 2022. Connecting Loss Difference with Equal Opportunity for Fair Models, In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL HLT 2022). [code]
  • Subramanian, Shivashankar, Xudong Han, Timothy Baldwin, Trevor Cohn and Lea Frermann (2021) Evaluating Debiasing Techniques for Intersectional Biases, In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP2021), Online and Punta Cana, Dominican Republic, pp. 2492–2498.
  • Han, Xudong, Timothy Baldwin and Trevor Cohn (2021) Decoupling Adversarial Training for Fair NLP, In Findings of the Association for Computational Linguistics (ACL-IJCNLP 2021), virtual, pp. 471–477. [code]
  • Han, Xudong, Timothy Baldwin and Trevor Cohn (2021) Diverse Adversaries for Mitigating Bias in Training, In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), virtual, pp. 2760—2765. [code]
  • Han, Xudong, Philip Schulz, and Trevor Cohn (2019) “Grounding learning of modifier dynamics: An application to color naming.” In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). [code]
  • Yang, Fei, Xudong Han, Jiying Lang, Weigang Lu, Lei Liu, Lei Zhang, and Jingchang Pan. “Commodity Recommendation for Users Based on E-commerce Data.” In Proceedings of the 2nd International Conference on Big Data Research, pp. 146-149. ACM, 2018.