Learning from graphs with structural variation
We study the effect of structural variation in graph data on the predictive performance of graph kernels. To this end, we introduce a novel, noise-robust adaptation of the GraphHopper kernel and validate it on benchmark data, obtaining modestly improved predictive performance on a range of datasets. Next, we investigate the performance of the state-of-the-art Weisfeiler-Lehman graph kernel under increasing synthetic structural errors and find that the effect of introducing errors depends strongly on the dataset.
Code (1)
Similar Papers 제목 키워드 기반
GraphTune: A Learning-based Graph Generative Model with Tunable Structural Features
Generative models for graphs have been actively studied for decades, and they have a wide range of applications. Recently, learning-based graph generation that reproduces real-world graphs has been attracting the attenti…
Graph GenerationDenoising Variational Graph of Graphs Auto-Encoder for Predicting Structured Entity Interactions
The interactions between structured entities play important roles in a wide range of applications such as chemistry, material science, biology, and medical science. Recently, graph-based methods have been exploited to ef…
DenoisingV-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs
GNN explanation method aims to identify an explanatory subgraph which contains the most informative components of the full graph. However, a major limitation of existing GNN explainers is that they are not robust to the …
Variational Graph Generator for Multi-View Graph Clustering
Multi-view graph clustering (MGC) methods are increasingly being studied due to the explosion of multi-view data with graph structural information. The critical point of MGC is to better utilize view-specific and view-co…
ClusteringGraph ClusteringUnified Embeddings of Structural and Functional Connectome via a Function-Constrained Structural Graph Variational Auto-Encoder
Graph theoretical analyses have become standard tools in modeling functional and anatomical connectivity in the brain. With the advent of connectomics, the primary graphs or networks of interest are structural connectome…