Private Wasserstein Distance with Random Noises

1 code implementation • 10 Apr 2024 • Wenqian Li, Haozhi Wang, Zhe Huang, Yan Pang

Wasserstein distance is a principle measure of data divergence from a distributional standpoint.

Teach Large Language Models to Forget Privacy

no code implementations • 30 Dec 2023 • Ran Yan, YuJun Li, Wenqian Li, Peihua Mai, Yan Pang, Yinchuan Li

Large Language Models (LLMs) have proven powerful, but the risk of privacy leakage remains a significant concern.

Privacy Preserving Zero-shot Generalization

Data Valuation and Detections in Federated Learning

1 code implementation • 9 Nov 2023 • Wenqian Li, Shuran Fu, Fengrui Zhang, Yan Pang

In scenarios involving numerous data clients within FL, it is often the case that only a subset of clients and datasets are pertinent to a specific learning task, while others might have either a negative or negligible impact on the model training process.

Data Valuation Federated Learning +1

Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs

no code implementations • 24 Apr 2023 • Yinchuan Li, Zhigang Li, Wenqian Li, Yunfeng Shao, Yan Zheng, Jianye Hao

Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions.

Active Learning

DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks

1 code implementation • 4 Mar 2023 • Wenqian Li, Yinchuan Li, Zhigang Li, Jianye Hao, Yan Pang

Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over the years.

Combinatorial Optimization

GFlowCausal: Generative Flow Networks for Causal Discovery

2 code implementations • 15 Oct 2022 • Wenqian Li, Yinchuan Li, Shengyu Zhu, Yunfeng Shao, Jianye Hao, Yan Pang

Causal discovery aims to uncover causal structure among a set of variables.

Active Learning Causal Discovery