Benchmarking External Generalization of SPD Matrix Learning for Resting-State fMRI Connectome Prediction
研究通过引入六个rs-fMRI数据集的年龄预测基准，评估了SPD矩阵学习方法在外部数据集上的泛化能力，发现整体性能受年龄范围不匹配和队列异质性影响显著。
0 citationsRead paper
Selected work
Representative Papers
CutClean: Neural Network Pruning for Privacy-Preserving Inference
This study addresses the issue of sensitive attribute privacy leakage during neural network inference by proposing CutClean, a privacy-aware pruning method. The approach innovatively introduces an auxiliary linear privacy head to quantify private information flow and integrates progressive pruning with sparsity training to precisely eliminate privacy-related features during model compression. Experimental results demonstrate that CutClean significantly enhances model sparsity while effectively mitigating privacy leakage risks and maintaining high target classification accuracy. Consequently, this method achieves a favorable trade-off among privacy protection, model lightweighting, and task performance, offering a robust solution for deploying secure and efficient neural networks in privacy-sensitive scenarios.
0 citationsRead paper
Recent publications
Latest Papers
Benchmarking External Generalization of SPD Matrix Learning for Resting-State fMRI Connectome Prediction
研究通过引入六个rs-fMRI数据集的年龄预测基准，评估了SPD矩阵学习方法在外部数据集上的泛化能力，发现整体性能受年龄范围不匹配和队列异质性影响显著。
0 citationsRead paper
CutClean: Neural Network Pruning for Privacy-Preserving Inference
This study addresses the issue of sensitive attribute privacy leakage during neural network inference by proposing CutClean, a privacy-aware pruning method. The approach innovatively introduces an auxiliary linear privacy head to quantify private information flow and integrates progressive pruning with sparsity training to precisely eliminate privacy-related features during model compression. Experimental results demonstrate that CutClean significantly enhances model sparsity while effectively mitigating privacy leakage risks and maintaining high target classification accuracy. Consequently, this method achieves a favorable trade-off among privacy protection, model lightweighting, and task performance, offering a robust solution for deploying secure and efficient neural networks in privacy-sensitive scenarios.
0 citationsRead paper