Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactions

by   Anson Bastos, et al.
Association for Computing Machinery
Indian Institute of Technology Hyderabad
RWTH Aachen University

Learning on evolving(dynamic) graphs has caught the attention of researchers as static methods exhibit limited performance in this setting. The existing methods for dynamic graphs learn spatial features by local neighborhood aggregation, which essentially only captures the low pass signals and local interactions. In this work, we go beyond current approaches to incorporate global features for effectively learning representations of a dynamically evolving graph. We propose to do so by capturing the spectrum of the dynamic graph. Since static methods to learn the graph spectrum would not consider the history of the evolution of the spectrum as the graph evolves with time, we propose a novel approach to learn the graph wavelets to capture this evolving spectra. Further, we propose a framework that integrates the dynamically captured spectra in the form of these learnable wavelets into spatial features for incorporating local and global interactions. Experiments on eight standard datasets show that our method significantly outperforms related methods on various tasks for dynamic graphs.


K-Core based Temporal Graph Convolutional Network for Dynamic Graphs

Graph representation learning is a fundamental task of various applicati...

Temporal Graph Networks for Deep Learning on Dynamic Graphs

Graph Neural Networks (GNNs) have recently become increasingly popular d...

MOHONE: Modeling Higher Order Network Effects in KnowledgeGraphs via Network Infused Embeddings

Many knowledge graph embedding methods operate on triples and are theref...

WalkingTime: Dynamic Graph Embedding Using Temporal-Topological Flows

Increased attention has been paid over the last four years to dynamic ne...

Call Graph Evolution Analytics over a Version Series of an Evolving Software System

Call Graph evolution analytics can aid a software engineer when maintain...

Sub-Graph Learning for Spatiotemporal Forecasting via Knowledge Distillation

One of the challenges in studying the interactions in large graphs is to...

Visualizing Evolving Trees

Evolving trees arise in many real-life scenarios from computer file syst...

Please sign up or login with your details

Forgot password? Click here to reset