Skip to content
Log in
Open access

Feature-Graph-Guided Adaptive Sparse NMF with Anchor Dual Graphs Under the Logarithmic Framework for Data Clustering

Quanrun Li Tao Ma Fangchen Xu Zilin Wang
Aug 2026 · Mathematics · 0 citations · 38 references

TL;DR

This paper proposes a feature-graph-guided adaptive Log-L2,1 sparse NMF with anchor dual graphs under a logarithmic framework that jointly integrate sample structure preservation, feature structure preservation, and feature-aware sparse learning within a unified graph-NMF model.

Abstract

Graph-based nonnegative matrix factorization (GNMF) has been widely used for dimensionality reduction and data clustering because it can preserve the intrinsic geometric structure of data. However, many existing GNMF-based methods still rely on full sample similarity graphs, resulting in high computational costs; moreover, their sparsity constraints usually treat all features uniformly, making it difficult to distinguish structurally important features from redundant or noisy ones. To address these issues, this paper proposes a feature-graph-guided adaptive Log-L2,1 sparse NMF with anchor dual graphs under a logarithmic framework. Specifically, anchor-based representations are simultaneously constructed in the sample and feature spaces to approximate the corresponding full-scale graphs. The sample anchor graph preserves the local manifold structure among samples, whereas the feature anchor graph plays a dual role: it preserves structural relationships among features and provides degree information for generating the adaptive weights gi of the row-wise Log-L2,1 penalty imposed on the basis matrix U. Consequently, structurally well-connected features receive weaker sparsity penalties, while weakly connected and potentially redundant features are more strongly suppressed. In addition, a logarithmic reconstruction framework is introduced to reduce the influence of large residuals caused by noise and outliers. These mechanisms jointly integrate sample structure preservation, feature structure preservation, and feature-aware sparse learning within a unified graph-NMF model. To optimize the model, multiplicative update rules are derived, while the nonnegativity of the factor matrices is inherently preserved throughout the iterations. Extensive evaluations on several benchmark datasets demonstrate the effectiveness and robustness of the proposed method.

DOI Semantic Scholar
Read PDF

Similar papers

2026

Adaptive Feature-Weighted Topological Manifold Graph Learning for Multi-View Data Clustering

Existing graph-based multi-view clustering methods commonly employ view weights as global multipliers over both local graph construction and cross-view consensus graph learning. Such a design may over-penalize weakly aligned views, thereby hindering adaptive feature selection and degrading view-specific manifold preserving. In this paper, we propose to learn Adaptive Feature-weighted Topological Manifold graph for multi-view data Clustering (AF-TMC), which structurally decouples local feature-aware graph learning from global topological fusion. Specifically, AF-TMC restricts view weights to the topological manifold alignment term, while independently learns adaptive feature-weight matrices and affinity graphs for individual views. A unified consensus manifold graph and spectral embedding are then jointly optimized to capture shared cluster structures across multi-view representations. On model optimization, we devise an efficient block coordinate descent algorithm, where each subproblem admits a closed-form update or a tractable simplex projection. Comprehensive experiments on eight datasets verify the effectiveness of AF-TMC, which achieves strong overall performance against representative multi-view clustering methods. Analyses on convergence behavior, parameter sensitivity, consensus manifold graph visualization, and adaptive feature ranking substantiate the robustness and interpretability of AF-TMC.

Yifu Chen, Yihao Wang, Pengxin Xu et al. · 0 citations
Preprint Jul 2026

Distance-Preserving Embeddings in Inhomogeneous Random Graphs

This approach demonstrates that models trained on small-scale random graphs learn to extract universal distance-preserving features, achieving robust generalization to large-scale, real-world networks that match or exceed the fidelity of classical, exact landmark-based embeddings.

My Le, Luana Ruiz, Souvik Dhara · 0 citations