Mengde Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mengde Han has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Tianqing Zhu
City University of Macau
2 shared publications - Wanlei Zhou
City University of Macau
2 shared publications - Huan Huo
University of Technology Sydney, Sydney, Australia
1 shared publication - Jing Li
Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
1 shared publication Lefeng Zhang
Faculty of Data Science, City University of Macau, Macau, China
1 shared publication- Philip S. Yu
University of Illinois Chicago
1 shared publication
Latest Publications
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (2) , 1110-1123
Vertical Federated Unlearning via Backdoor Certification
Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method is particularly pertinent when entities possess datasets with identical sample identifiers but diverse attributes. Recent privacy regulations emphasize an individual's right to be forgotten, which necessitates the ability for models to unlearn specific training data. The primary challenge is to develop a mechanism to eliminate the influence of a specific client from a model without erasing all relevant data from other clients. Our research investigates the removal of a single client's contribution within the VFL framework. We introduce an innovative modification to traditional VFL by employing a mechanism that inverts the typical learning trajectory with the objective of extracting specific data contributions. This approach seeks to optimize model performance using gradient ascent, guided by a pre-defined constrained model. We also introduce a backdoor mechanism to verify the effectiveness of the unlearning procedure. Our method avoids fully accessing the initial training data and avoids storing parameter updates. Empirical evidence shows that the results align closely with those achieved by retraining from scratch. Utilizing gradient ascent, our unlearning approach addresses key challenges in VFL, laying the groundwork for future advancements in this domain. All the code and implementations related to this paper are publicly available at https://github.com/mengdehan/VFL-unlearn.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (2) , 1110-1123
Vertical Federated Unlearning via Backdoor Certification
Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method is particularly pertinent when entities possess datasets with identical sample identifiers but diverse attributes. Recent privacy regulations emphasize an individual's right to be forgotten, which necessitates the ability for models to unlearn specific training data. The primary challenge is to develop a mechanism to eliminate the influence of a specific client from a model without erasing all relevant data from other clients. Our research investigates the removal of a single client's contribution within the VFL framework. We introduce an innovative modification to traditional VFL by employing a mechanism that inverts the typical learning trajectory with the objective of extracting specific data contributions. This approach seeks to optimize model performance using gradient ascent, guided by a pre-defined constrained model. We also introduce a backdoor mechanism to verify the effectiveness of the unlearning procedure. Our method avoids fully accessing the initial training data and avoids storing parameter updates. Empirical evidence shows that the results align closely with those achieved by retraining from scratch. Utilizing gradient ascent, our unlearning approach addresses key challenges in VFL, laying the groundwork for future advancements in this domain. All the code and implementations related to this paper are publicly available at https://github.com/mengdehan/VFL-unlearn.
- 15 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (4) , 1763-1774
Fairness in Semi-Supervised Learning: Unlabeled Data Help to Reduce Discrimination
A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for building fair models with sacrifice in accuracy, most are geared toward either supervised or unsupervised learning. Yet two observations inspired us to wonder whether semi-supervised learning might be useful to solve discrimination problems. First, previous study showed that increasing the size of the training set may lead to a better trade-off between fairness and accuracy. Second, the most powerful models today require an enormous of data to train which, in practical terms, is likely possible from a combination of labeled and unlabeled data. Hence, in this paper, we present a framework of fair semi-supervised learning in the pre-processing phase, including pseudo labeling to predict labels for unlabeled data, a re-sampling method to obtain multiple fair datasets and lastly, ensemble learning to improve accuracy and decrease discrimination. A theoretical decomposition analysis of bias, variance and noise highlights the different sources of discrimination and the impact they have on fairness in semi-supervised learning. A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.
- 15 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (4) , 1763-1774
Fairness in Semi-Supervised Learning: Unlabeled Data Help to Reduce Discrimination
A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for building fair models with sacrifice in accuracy, most are geared toward either supervised or unsupervised learning. Yet two observations inspired us to wonder whether semi-supervised learning might be useful to solve discrimination problems. First, previous study showed that increasing the size of the training set may lead to a better trade-off between fairness and accuracy. Second, the most powerful models today require an enormous of data to train which, in practical terms, is likely possible from a combination of labeled and unlabeled data. Hence, in this paper, we present a framework of fair semi-supervised learning in the pre-processing phase, including pseudo labeling to predict labels for unlabeled data, a re-sampling method to obtain multiple fair datasets and lastly, ensemble learning to improve accuracy and decrease discrimination. A theoretical decomposition analysis of bias, variance and noise highlights the different sources of discrimination and the impact they have on fairness in semi-supervised learning. A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.