An Evolution Kernel Method for Graph Classification through Heat Diffusion Dynamics

by   Xue Liu, et al.

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.


page 1

page 2

page 6

page 7

page 8

page 10


Dynamic Graph Node Classification via Time Augmentation

Node classification for graph-structured data aims to classify nodes who...

Spectral Descriptors for Graph Matching

In this paper, we consider the weighted graph matching problem. Recently...

Predicting traffic signals on transportation networks using spatio-temporal correlations on graphs

Forecasting multivariate time series is challenging as the variables are...

On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions

In this work we formalize the (pure observational) task of predicting no...

Dynamic Graphs Generators Analysis : an Illustrative Case Study

In this work, we investigate the analysis of generators for dynamic grap...

Visualization of Unsteady Flow Using Heat Kernel Signatures

We introduce a new technique to visualize complex flowing phenomena by u...

How morphological development can guide evolution

Organisms result from multiple adaptive processes occurring and interact...

Please sign up or login with your details

Forgot password? Click here to reset