Individual-centered Partial Information in Social Networks

Seeded Graph Matching for the Correlated Gaussian Wigner Model via the Projected Power Method

Analysis of Convolutions, Non-linearity and Depth in Graph Neural...

The fundamental principle of Graph Neural Networks (GNNs) is to exploit the structural information of the data by aggregating the neighboring nodes using a `graph convolution' in conjunction with a...

A Simple Unified Method for Node Classification on Homophilous and...

In graph learning, there have been two predominant inductive biases regarding graph-inspired architectures: On the one hand, higher-order interactions and message passing work well on homophilous...

Companies using Twitter tools to keep ads away from Musk's tweets: NYT

Twitter has "adjacency controls" promoted by Elon Musk that help companies keep ads clear of certain content or users.

INTEGRATE: Distance based Graph Convolutional Networks for...

Recently, several successful methods for learning embeddings of large knowledge bases have been developed. They have been motivated through the inevitability of learning and reasoning about various...

Attentive Walk-Aggregating Graph Neural Networks

Graph neural networks (GNNs) have been shown to possess strong representation power, which can be exploited for downstream prediction tasks on graph-structured data, such as molecules and social...

Sampling random graph homomorphisms and applications to network data analysis