An Evolution Kernel Method for Graph Classification through Heat Diffusion Dynamics

2023-06-26 · Xue Liu, Dan Sun, Wei Wei, Zhiming Zheng

Autonomous individuals establish a structural complex system through pairwise connections and interactions. Notably, the evolution reflects the dynamic nature of each complex system since it recodes a series of temporal changes from the past, the present into the future. Different systems follow distinct evolutionary trajectories, which can serve as distinguishing traits for system classification. However, modeling a complex system's evolution is challenging for the graph model because the graph is typically a snapshot of the static status of a system, and thereby hard to manifest the long-term evolutionary traits of a system entirely. To address this challenge, we suggest utilizing a heat-driven method to generate temporal graph augmentation. This approach incorporates the physics-based heat kernel and DropNode technique to transform each static graph into a sequence of temporal ones. This approach effectively describes the evolutional behaviours of the system, including the retention or disappearance of elements at each time point based on the distributed heat on each node. Additionally, we propose a dynamic time-wrapping distance GDTW to quantitatively measure the distance between pairwise evolutionary systems through optimal matching. The resulting approach, called the Evolution Kernel method, has been successfully applied to classification problems in real-world structural graph datasets. The results yield significant improvements in supervised classification accuracy over a series of baseline methods.

📄 PDF Abstract BibTeX arXiv:2306.14688

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Classification

Fractional Heat Kernel for Semi-Supervised Graph Learning with Small Training Sample Size

2025-10-06 · Farid Bozorgnia, Vyacheslav Kungurtsev, Shirali Kadyrov, Mohsen Yousefnezhad arxiv

In this work, we introduce novel algorithms for label propagation and self-training using fractional heat kernel dynamics with a source term. We motivate the methodology through the classical correspondence of informatio…

Graph Neural Network Graph Learning

Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning

2020-07-27 · Bingbing Xu, Hua-Wei Shen, Qi Cao, Keting Cen 외

Graph convolutional networks gain remarkable success in semi-supervised learning on graph structured data. The key to graph-based semisupervised learning is capturing the smoothness of labels or features over nodes exert…

Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs

2021-04-27 · Semin Kwak, Nikolas Geroliminis, Pascal Frossard

Multivariate time series forecasting poses challenges as the variables are intertwined in time and space, like in the case of traffic signals. Defining signals on graphs relaxes such complexities by representing the evol…

Multivariate Time Series Forecasting Prediction Time Series Time Series Forecasting+1

Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion

2026-06-16 · Xuling Zhang, Peng Wang, Daiyan Li, Aoran Huang 외 arxiv

Most graph neural network (GNN) cores rely on graph convolutions, typically implemented as message passing between direct (single-hop) neighbors. In many real-world graphs, edges can be noisy or poorly defined, limiting …

Graph Neural Network

One-Shot Data Selection for Medical Image Classification via Graph Coverage

2026-06-20 · Zahiriddin Rustamov, Nadia Badawi, Rafat Damseh, Nazar Zaki arxiv

Training medical image classifiers on entire datasets is wasteful when annotation budgets are limited: not all samples contribute equally, yet acquiring expert labels is expensive. Active learning reduces annotation cost…

Medical Image Classification Active Learning