collaborators

9 papers

cs.LG2026

De-attribute to Forget for LLM Unlearning

Xinyang Lu, Jiabao Pan, Rachael Hwee Ling Sim +3

The rapid development of large language models (LLMs) has raised concerns on the use of inappropriate data for training, which has led to a growing interest in LLM unlearning. Many…

cs.LG2026

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning

Jiangwei Chen, Xinyuan Niu, Rachael Hwee Ling Sim +3

Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining…

cs.LG2026

Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning

Rachael Hwee Ling Sim, Jue Fan, Xiao Tian +3

Collaborative machine learning involves training high-quality models using datasets from a number of sources. To incentivize sources to share data, existing data valuation methods…

cs.LG2026

Is Data Shapley Not Better than Random in Data Selection? Ask NASH

Xiao Tian, Jue Fan, Rachael Hwee Ling Sim +3

Data selection studies the problem of identifying high-quality subsets of training data. While some existing works have considered selecting the subset of data with top- Data Sh…

cs.LG2026

INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy

Xiao Tian, Jue Fan, Rachael Hwee Ling Sim +1

Differential privacy (DP) is widely employed in machine learning to protect confidential or sensitive training data from being revealed. As data owners gain greater control over th…

cs.LG2026

WaterDrum: Watermarking for Data-centric Unlearning Metric

Xinyang Lu, Xinyuan Niu, Gregory Kang Ruey Lau +7

Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of private, copyrighted, or harmful data from…