13 citations · 23 across the 3 of their papers we have counts for
8 papers
A Practical, Progressively-Expressive GNN
Lingxiao Zhao, Louis Härtel, Neil Shah +1
Message passing neural networks (MPNNs) have become a dominant flavor of graph neural networks (GNNs) in recent years. Yet, MPNNs come with notable limitations; namely, they are at…
Graph Anomaly Detection with Unsupervised GNNs
Lingxiao Zhao, Saurabh Sawlani, Arvind Srinivasan +1
Graph-based anomaly detection finds numerous applications in the real-world. Thus, there exists extensive literature on the topic that has recently shifted toward deep detection mo…
Fast Attributed Graph Embedding via Density of States
Saurabh Sawlani, Lingxiao Zhao, Leman Akoglu
Given a node-attributed graph, how can we efficiently represent it with few numerical features that expressively reflect its topology and attribute information? We propose A-DOGE,…
On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insights
Lingxiao Zhao, Leman Akoglu
It is common practice of the outlier mining community to repurpose classification datasets toward evaluating various detection models. To that end, often a binary classification da…
Connecting Graph Convolutional Networks and Graph-Regularized PCA
Lingxiao Zhao, Leman Akoglu
Graph convolution operator of the GCN model is originally motivated from a localized first-order approximation of spectral graph convolutions. This work stands on a different view;…
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Jiong Zhu, Yujun Yan, Lingxiao Zhao +3
We investigate the representation power of graph neural networks in the semi-supervised node classification task under heterophily or low homophily, i.e., in networks where connect…