Dynamic Graph Structure Learning via Resistance Curvature Flow

• URL: http://arxiv.org/abs/2601.08149v1
• Date: Tue, 13 Jan 2026 02:23:32 GMT
• Title: Dynamic Graph Structure Learning via Resistance Curvature Flow
• Authors: Chaoqun Fei, Huanjiang Liu, Tinglve Zhou, Yangyang Li, Tianyong Hao,
• Abstract summary: Geometric Representation Learning aims to approximate the non-Euclidean topology of high-dimensional data through discrete graph structures.<n>Traditional static graph construction methods based on Euclidean distance often fail to capture the intrinsic curvature characteristics of the data manifold.<n>This paper proposes a novel geometric evolution framework: Resistance Curvature Flow (RCF)
• Score: 8.07689343442439
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Geometric Representation Learning (GRL) aims to approximate the non-Euclidean topology of high-dimensional data through discrete graph structures, grounded in the manifold hypothesis. However, traditional static graph construction methods based on Euclidean distance often fail to capture the intrinsic curvature characteristics of the data manifold. Although Ollivier-Ricci Curvature Flow (OCF) has proven to be a powerful tool for dynamic topological optimization, its core reliance on Optimal Transport (Wasserstein distance) leads to prohibitive computational complexity, severely limiting its application in large-scale datasets and deep learning frameworks. To break this bottleneck, this paper proposes a novel geometric evolution framework: Resistance Curvature Flow (RCF). Leveraging the concept of effective resistance from circuit physics, RCF transforms expensive curvature optimization into efficient matrix operations. This approach achieves over 100x computational acceleration while maintaining geometric optimization capabilities comparable to OCF. We provide an in-depth exploration of the theoretical foundations and dynamical principles of RCF, elucidating how it guides the redistribution of edge weights via curvature gradients to eliminate topological noise and strengthen local cluster structures. Furthermore, we provide a mechanistic explanation of RCF's role in manifold enhancement and noise suppression, as well as its compatibility with deep learning models. We design a graph optimization algorithm, DGSL-RCF, based on this framework. Experimental results across deep metric learning, manifold learning, and graph structure learning demonstrate that DGSL-RCF significantly improves representation quality and downstream task performance.

Related papers

• On Multi-Step Theorem Prediction via Non-Parametric Structural Priors [50.16583672681106]
  In this work, we explore training-free theorem prediction through the lens of in-context learning (ICL)<n>We propose Theorem Precedence Graphs, which encode temporal dependencies from historical solution traces as directed graphs, and impose explicit topological constraints that effectively prune the search space during inference.<n>Experiments on the FormalGeo7k benchmark show that our method achieves 89.29% accuracy, substantially outperforming ICL baselines and matching state-of-the-art supervised models.
  arXiv  Detail & Related papers  (2026-03-05T06:08:50Z)
• Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration [67.12978375116599]
  We show that the steps of gradient descent (GD) reduce to those of generalized perceptron algorithms.<n>This helps explain the optimization dynamics and the implicit acceleration phenomenon observed in neural networks.
  arXiv  Detail & Related papers  (2025-12-12T14:16:35Z)
• Efficient Curvature-aware Graph Network [8.665262442928217]
  We propose a novel graph curvature measure--Effective Resistance Curvature--which quantifies the ease of message passing along graph edges.<n>We prove the low computational complexity of effective resistance curvature and establish its substitutability for Ollivier-Ricci curvature.
  arXiv  Detail & Related papers  (2025-11-03T10:51:58Z)
• Curvature Learning for Generalization of Hyperbolic Neural Networks [51.888534247573894]
  Hyperbolic neural networks (HNNs) have demonstrated notable efficacy in representing real-world data with hierarchical structures.<n>Inappropriate curvatures may cause HNNs to converge to suboptimal parameters, degrading overall performance.<n>We propose a sharpness-aware curvature learning method to smooth the loss landscape, thereby improving the generalization of HNNs.
  arXiv  Detail & Related papers  (2025-08-24T07:14:30Z)
• Geometry-Aware Spiking Graph Neural Network [24.920334588995072]
  We propose a Geometry-Aware Spiking Graph Neural Network that unifies spike-based neural dynamics with adaptive representation learning.<n>Experiments on multiple benchmarks show that GSG achieves superior accuracy, robustness, and energy efficiency compared to both Euclidean SNNs and manifold-based GNNs.
  arXiv  Detail & Related papers  (2025-08-09T02:52:38Z)
• Flows and Diffusions on the Neural Manifold [0.0]
  Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling.<n>In this work, we extend these advances to weight space learning by leveraging recent techniques to incorporate structural priors derived from optimization dynamics.<n>We unify several trajectory inference techniques towards matching a gradient flow, providing a theoretical framework for treating optimization paths as inductive bias.
  arXiv  Detail & Related papers  (2025-07-14T02:26:06Z)
• Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel [55.82768375605861]
  We establish a generalization bound for gradient flow that aligns with the classical Rademacher complexity for kernel methods.<n>Unlike static kernels such as NTK, the LPK captures the entire training trajectory, adapting to both data and optimization dynamics.
  arXiv  Detail & Related papers  (2025-06-12T23:17:09Z)
• Discrete Curvature Graph Information Bottleneck [15.867882286328774]
  We propose a novel Discrete Curvature Graph Information Bottleneck (CurvGIB) framework to optimize the information transport structure.<n>CurvGIB advances the Variational Information Bottleneck (VIB) principle for Ricci curvature optimization to learn the optimal information transport pattern.<n>Experiments on various datasets demonstrate the superior effectiveness and interpretability of CurvGIB.
  arXiv  Detail & Related papers  (2024-12-28T03:33:55Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• On the Generalization Capability of Temporal Graph Learning Algorithms: Theoretical Insights and a Simpler Method [59.52204415829695]
  Temporal Graph Learning (TGL) has become a prevalent technique across diverse real-world applications. This paper investigates the generalization ability of different TGL algorithms. We propose a simplified TGL network, which enjoys a small generalization error, improved overall performance, and lower model complexity.
  arXiv  Detail & Related papers  (2024-02-26T08:22:22Z)
• Revealing Decurve Flows for Generalized Graph Propagation [108.80758541147418]
  This study addresses the limitations of the traditional analysis of message-passing, central to graph learning, by defining em textbfgeneralized propagation with directed and weighted graphs. We include a preliminary exploration of learned propagation patterns in datasets, a first in the field.
  arXiv  Detail & Related papers  (2024-02-13T14:13:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.