Towards Federated, Green, and Resilient 6G Non-Terrestrial Networks
本文研究了通过联邦、绿色和弹性方法解决5G/6G系统中地面与非地面网络集成的问题,采用统一控制管理及开放无线电接入网架构提升性能。
本文研究了通过联邦、绿色和弹性方法解决5G/6G系统中地面与非地面网络集成的问题,采用统一控制管理及开放无线电接入网架构提升性能。
本文提出了一种神经符号回归框架,通过深度学习和稀疏建模方法解决传统符号回归的可扩展性和噪声敏感问题。
This study addresses the persistence of structural gender bias in credit scoring models, even when explicit gender information is removed. Focusing on a Taiwanese credit default dataset, the authors propose an integrated approach combining SHAP-based interpretability with adversarial reverse modeling to identify and quantify the extent to which ostensibly non-sensitive financial features act as proxy variables for gender—a phenomenon termed “proxy leakage.” Their experiments successfully reconstruct gender information from purely financial features with a ROC AUC of 0.65, demonstrating that conventional statistical fairness methods may fail to mitigate such latent biases. The findings underscore the need for causal-aware frameworks and structural accountability mechanisms to effectively address implicit discrimination embedded in predictive models.
Comparing unordered 3D point clouds remains challenging due to their unstructured nature and geometric complexity; existing metrics—including Hausdorff and Chamfer distances, as well as KL-divergence approximations based on Gaussian Mixture Models (GMMs)—lack global statistical modeling capability, are sensitive to outliers, and suffer from divergence or numerical instability. Method: This paper establishes, for the first time, that the space of GMMs forms a statistical manifold, and accordingly proposes a bounded, numerically stable Modified Symmetric KL divergence (MSKL). MSKL possesses rigorously derived theoretical upper and lower bounds, overcoming the unboundedness and instability inherent in conventional KL-based approximations. Results: Experiments on MPI-FAUST and G-PCD datasets demonstrate that MSKL exhibits monotonic geometric sensitivity and significantly outperforms state-of-the-art geometric and probabilistic metrics in shape matching and retrieval tasks.
This work addresses the lack of geometric consistency and differentiability in similarity measures between Gaussian mixture models (GMMs). We propose a novel embedding of GMMs into the symmetric positive-definite (SPD) matrix manifold: for the first time, we rigorously prove that the K-component GMM manifold admits an isometric embedding into an SPD manifold, and under the pullback of the Fisher–Rao metric, we derive the first closed-form, differentiable, and geometrically consistent lower bound on the geodesic distance. The resulting metric combines theoretical rigor with computational tractability. Evaluated on the UIUC, KTH-TIPS, and UMD texture recognition benchmarks, our method achieves classification accuracies of 98.0%, 92.0%, and 93.3%, respectively—substantially outperforming conventional approaches based on KL divergence and Wasserstein distance. This establishes a new information-geometric paradigm for comparing GMMs.
本文研究了通过联邦、绿色和弹性方法解决5G/6G系统中地面与非地面网络集成的问题,采用统一控制管理及开放无线电接入网架构提升性能。
本文提出了一种神经符号回归框架,通过深度学习和稀疏建模方法解决传统符号回归的可扩展性和噪声敏感问题。
This study addresses the persistence of structural gender bias in credit scoring models, even when explicit gender information is removed. Focusing on a Taiwanese credit default dataset, the authors propose an integrated approach combining SHAP-based interpretability with adversarial reverse modeling to identify and quantify the extent to which ostensibly non-sensitive financial features act as proxy variables for gender—a phenomenon termed “proxy leakage.” Their experiments successfully reconstruct gender information from purely financial features with a ROC AUC of 0.65, demonstrating that conventional statistical fairness methods may fail to mitigate such latent biases. The findings underscore the need for causal-aware frameworks and structural accountability mechanisms to effectively address implicit discrimination embedded in predictive models.
Comparing unordered 3D point clouds remains challenging due to their unstructured nature and geometric complexity; existing metrics—including Hausdorff and Chamfer distances, as well as KL-divergence approximations based on Gaussian Mixture Models (GMMs)—lack global statistical modeling capability, are sensitive to outliers, and suffer from divergence or numerical instability. Method: This paper establishes, for the first time, that the space of GMMs forms a statistical manifold, and accordingly proposes a bounded, numerically stable Modified Symmetric KL divergence (MSKL). MSKL possesses rigorously derived theoretical upper and lower bounds, overcoming the unboundedness and instability inherent in conventional KL-based approximations. Results: Experiments on MPI-FAUST and G-PCD datasets demonstrate that MSKL exhibits monotonic geometric sensitivity and significantly outperforms state-of-the-art geometric and probabilistic metrics in shape matching and retrieval tasks.
This work addresses the lack of geometric consistency and differentiability in similarity measures between Gaussian mixture models (GMMs). We propose a novel embedding of GMMs into the symmetric positive-definite (SPD) matrix manifold: for the first time, we rigorously prove that the K-component GMM manifold admits an isometric embedding into an SPD manifold, and under the pullback of the Fisher–Rao metric, we derive the first closed-form, differentiable, and geometrically consistent lower bound on the geodesic distance. The resulting metric combines theoretical rigor with computational tractability. Evaluated on the UIUC, KTH-TIPS, and UMD texture recognition benchmarks, our method achieves classification accuracies of 98.0%, 92.0%, and 93.3%, respectively—substantially outperforming conventional approaches based on KL divergence and Wasserstein distance. This establishes a new information-geometric paradigm for comparing GMMs.