Memory-Based Graph Networks

Amir Hosein Khasahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris
2/21/2020
cs.LGcs.NEstat.ML

Official code: amirkhas/GraphMemoryNet (106 stars, last commit 2022-06-22).

Abstract

Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph. We also introduce two new networks based on this layer: memory-based GNN (MemGNN) and graph memory network (GMN) that can learn hierarchical graph representations. The experimental results shows that the proposed models achieve state-of-the-art results in eight out of nine graph classification and regression benchmarks. We also show that the learned representations could correspond to chemical features in the molecule data. Code and reference implementations are released at: https://github.com/amirkhas/GraphMemoryNet

View on arXivView PDF

Code Implementations(1)

amirkhas/GraphMemoryNetOfficial100%

Memory-Based Graph Networks

10622PythonFeb 13, 20204 years ago

Similar Papers

Graph Property Prediction on Open Graph Benchmark: A Winning Solution by Graph Neural Architecture Search

88% match1 repo212022

Hierarchical Graph Pooling with Structure Learning

87% match1 repo3452019

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training

86% match1 repo3312020

Graph Neural Networks: A Review of Methods and Applications

86% match1 repo16.8k2018

Learning From Graph-Structured Data: Addressing Design Issues and Exploring Practical Applications in Graph Representation Learning

86% match2024

A Theory of Link Prediction via Relational Weisfeiler-Leman

86% match1 repo132023

Cite this paper

@article{khasahmadi2020memorybased,
  title  = {Memory-Based Graph Networks},
  author = {Amir Hosein Khasahmadi and Kaveh Hassani and Parsa Moradi and Leo Lee and Quaid Morris},
  year   = {2020},
  eprint = {2002.09518},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2002.09518}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2002.09518.svg)](https://codeofpaper.com/paper/2002.09518)

Discussion