Investigating Neighborhood Modeling and Asymmetry Preservation in Digraph Representation Learning

12/22/2021
by   Honglu Zhou, et al.
0

Graph Neural Networks (GNNs) traditionally exhibit poor performance for directed graphs (digraphs) due to notable challenges in 1) modeling neighborhoods and 2) preserving asymmetry. In this paper, we address these challenges in traditional GNNs by leveraging hyperbolic collaborative learning from multi-ordered and partitioned neighborhoods, and regularizers inspired by socio-psychological factors. Our resulting formalism, Digraph Hyperbolic Network (D-HYPR) learns node representations in hyperbolic space to avoid structural and semantic distortion of real-world digraphs. We conduct comprehensive experimentation on 4 tasks: link prediction, node classification, sign prediction, and embedding visualization. D-HYPR statistically significantly outperforms the current state of the art on a majority of tasks and datasets, while achieving competitive performance otherwise. Our code and data will be available.

READ FULL TEXT
research
06/09/2022

Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

Graph Neural Networks (GNNs) have been widely applied to various fields ...
research
10/15/2021

ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network

Graph Neural Networks (GNNs) have been widely studied in various graph d...
research
10/28/2019

Hyperbolic Graph Neural Networks

Learning from graph-structured data is an important task in machine lear...
research
11/04/2022

Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations

In recent years, graph neural networks (GNNs) have emerged as a promisin...
research
08/31/2020

Distance Encoding – Design Provably More Powerful Graph Neural Networks for Structural Representation Learning

Learning structural representations of node sets from graph-structured d...
research
07/06/2022

Text Enriched Sparse Hyperbolic Graph Convolutional Networks

Heterogeneous networks, which connect informative nodes containing text ...
research
04/06/2021

Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs

Learning representations for graphs plays a critical role in a wide spec...

Please sign up or login with your details

Forgot password? Click here to reset