YIJUN
Homepage
Publications
Activities

Publications

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

Preprints

  1. Yijun Bian*, Lei You, Yuya Sasaki, Haruka Maeda, and Akira Igarashi, "Revisiting some misconceptions and limitations in algorithmic fairness," arXiv preprint arXiv:2506.12556, 2025. [arXiv][code]

  2. Yijun Bian* and Yujie Luo, "Fast discrimination assessment for multiple non-binary sensitive attributes," [code][doc]

  3. Alina Basharat, Yijun Bian, Ping Xu*, and Zhi Tian, "Towards trustworthy federated learning," arXiv preprint arXiv:2503.03684, 2025. [arXiv]

  4. 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]

Conference papers

  1. Yijun Bian*, "Improving fairness with ensemble combination: Margin-dependent bounds," in Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency (FAccT ’26), pp. 352–381, June 25–28, 2026, Montreal, QC, Canada. [arXiv][code][doc][openreview][data][doi][slides]

  2. Lin Zhu#, Yijun Bian#, and Lei You*, "FairSHAP: Preprocessing for fairness through attribution-based data augmentation," in the 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026), May 2–5, 2026, Tangier, Morocco. [arXiv][code][openreview][openprint][poster]

  3. Lei You*, Yijun Bian, and Lele Cao, "Joint distribution-informed Shapley values for sparse counterfactual explanations," in the 40th International Conference on Learning Representations (ICLR 2026), April 23–27, 2026, Rio de Janeiro, RJ, Brazil. [arXiv][code][software][doc][openreview]

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

Journal articles

  1. Yijun Bian#* and Yujie Luo#, "Measuring model-induced discrimination via efficient fairness approximation," IEEE Transactions on Neural Networks and Learning Systems, accepted. [arXiv][code][doc]

  2. Jinghan Huang#, Qiufeng Chen#, Pengli Zhu, Yijun Bian, Nanguang Chen, Moo K. Chung, and Anqi Qiu*, "HL-HGAT: Heterogeneous graph attention network via Hodge-Laplacian operator," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 12, pp. 11022–11039, Dec 2025. [arXiv][code][paper][doi][pdf]

  3. 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, vol. 44, no. 1, pp. 207–220, Jan 2025. [paper][code][doi][pdf]

  4. 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][pdf]

  5. 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][pdf]

  6. 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][pdf]

Open-source code & official implementation for research papers

  • FairML, official code to reproduce the methodology funded by the FairML project.

  • AssessBias, official code for "Algorithmic fairness: Not a purely technical but socio-technical property."

  • PyFairness, an open-source library for fairness measures and ensemble methods, for reproducing our work.

  • ApproxBias, official released code for the efficient discrimination assessments from a manifold perspective.

  • 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.