Yijun Bian

Postdoc,
Machine Learning Section,
Department of Computer Science,
University of Copenhagen

Contact me

Emails: yjbian92@{gmail, hotmail}.com
Location: Copenhagen, Denmark

Biography

I am currently a MSCA postdoc advised by Prof. Yevgeny Seldin at the Department of Computer Science, University of Copenhagen (UCPH), funded by the European Union (the FairML project, and CORDIS). I obtained my Ph.D. degree from the Department of Computer Science and Technology, University of Science and Technology of China (USTC), and was very fortunate to be supervised by Prof. Huanhuan Chen. My research interests span the areas of machine learning, ensemble methods, and fairness in machine learning.

Publications

Works listed as first/corresponding author (*) and equal contributions (#); see Google Scholar.

Preprints

1. Yijun Bian#*, Yujie Luo#*, and Ping Xu, "Approximating discrimination within models when faced with several non-binary sensitive attributes", arXiv preprint arXiv:2408.06099, 2024. Under Review. [arXiv]

2. Yijun Bian#*, Yujie Luo#, "Does machine bring in extra bias in learning? Approximating fairness in models promptly", arXiv preprint arXiv:2405.09251, 2024. Under Review. [arXiv]

3. Jinghan Huang, Qiufeng Chen, Yijun Bian, Pengli Zhu, Nanguang Chen, Moo K. Chung, Anqi Qiu*, "Advancing graph neural networks with HL-HGAT: A Hodge-Laplacian and attention mechanism approach for heterogeneous graph-structured data", arXiv preprint arXiv:2403.06687, 2024. [arXiv]

4. Yijun Bian*, Kun Zhang, Anqi Qiu, and Nanguang Chen, "Increasing fairness via combination with learning guarantees", arXiv preprint arXiv:2301.10813, 2023. [arXiv]

5. Abhijith Sharma#, Yijun Bian#*, Phil Munz, and Apurva Narayan, "Adversarial patch attacks and defences in vision-based tasks: A survey", arXiv preprint arXiv:2206.08304, 2022. [arXiv][TechRxiv]

Journal articles

1. Ming Chen, Yijun Bian, Nanguang Chen, and Anqi Qiu*, "Orthogonal mixed-effects modeling for high-dimensional longitudinal data: An unsupervised learning approach", IEEE Transactions on Medical Imaging, accepted. [paper][code][doi]

2. Yijun Bian, Qingquan Song, Mengnan Du, Jun Yao, Huanhuan Chen*, and Xia Hu, "Subarchitecture ensemble pruning in neural architecture search", IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 12, pp. 7928-7936, Dec 2022. [arXiv][paper][code][doi]

3. Yijun Bian and Huanhuan Chen*, "When does diversity help generalization in classification ensembles?" IEEE Transactions on Cybernetics, vol. 52, no. 9, pp. 9059–9075, Sept 2022. [arXiv][paper][doi]

4. Yijun Bian, Yijun Wang, Yaqiang Yao, and Huanhuan Chen*, "Ensemble pruning based on objection maximization with a general distributed framework", IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 9, pp. 3766–3774, Sept 2020. [arXiv][paper][code][doi]

Conference paper

1. Abhijith Sharma, Yijun Bian, Vatsal Nanda, Phil Munz, and Apurva Narayan, "Vulnerability of CNNs against multi-patch attacks", Proceedings of the 2023 ACM Workshop on Secure and Trustworthy Cyber-Physical Systems (SaT-CPS’23), pp. 23–32, Apr 2023. [paper][doi]

Experiences

Education

• Ph.D. in Computer Science and Technology, University of Science and Technology of China, 2020

• B.Sc. in Computational Mathematics, Northwest A&F University, 2014

Experiences

• Postdoctoral research fellow @NUS, Mar 2023 to Jul 2024

• Algorithm engineer @SIMIT, Dec 2020 to Mar 2023

• Graduate research assistant @USTC, Sept 2014 to Nov 2020

• Visiting research scholar @TAMU, Nov 2018 to Apr 2019

• Teaching assistant @USTC, Mar 2016 to Jul 2016

Presentations

• "Developing Fair ML Models from Theoretical Aspects", Aarhus Summer School on Learning Theory, Aug 2024. [slides]

• "Increasing Fairness via Combination with Learning Guarantees", Fall 2023 LeT-All Mentorship Workshop, Oct 2023. [slides]

Professional Activities

Journal reviewer

1. Information Sciences, since May 2024

2. Scientific Reports, since Jun 2023

3. IEEE Transactions on Pattern Analysis and Machine Intelligence, since May 2023

4. Journal of Supercomputing, since Mar 2023

5. IEEE Transactions on Emerging Topics in Computational Intelligence, since Sept 2021

6. Neural Networks, since Nov 2020

7. IEEE Transactions on Neural Networks and Learning Systems, since Aug 2016

Open-source contributor

• AdaNet (Google’s open-source project), merged pull request, Oct 2019

• OpenNE, merged pull request, Aug 2019

• AutoKeras, merged pull requests a and b in the blocks branch, Jun 2019

Released code of projects

• SAEP, official released code for "Subarchitecture ensemble pruning in neural architecture search".

• EPFD, official released code for "Ensemble pruning based on objection maximisation with a general distributed framework".

• PyEnsemble, an open-source library for ensemble learning methods, diversity measures, and ensemble pruning methods.

Selected Honours & Awards

• Awardee of Marie Skłodowska-Curie Actions (MSCA) Postdoctoral Fellowship 2022

• Seal of Excellence under the HORIZON Europe MSCA call 2022, European Commission, Apr 2023

• GDC Technology Scholarship, USTC, Oct 2019

• International Exchange Funding for Excellent Students, USTC, Apr 2018

• First-class Academic Scholarship, USTC, Sept 2015

• Outstanding Undergraduate Graduation Thesis (Design), NWAFU, Jun 2014

• President Scholarship, NWAFU, Dec 2013

• Merit Student, for three consecutive years, NWAFU, Dec 2011 to Dec 2013

• First Prize Professional Scholarship, four times in a row, NWAFU, Mar 2011, Oct 2011 to Oct 2013