Learning Discrete Structures for Graph Neural Networks

Luca Franceschi, Mathias Niepert, Massimiliano Pontil, Xiao He
3/28/2019
cs.LGstat.ML

Official code: lucfra/LDS-GNN (201 stars, last commit 2024-03-06).

Abstract

Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such a graph-structure is available. In practice, however, real-world graphs are often noisy and incomplete or might not be available at all. With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph. This allows one to apply GCNs not only in scenarios where the given graph is incomplete or corrupted but also in those where a graph is not available. We conduct a series of experiments that analyze the behavior of the proposed method and demonstrate that it outperforms related methods by a significant margin.

View on arXivView PDF

Code Implementations(1)

lucfra/LDS-GNNOfficial100%

Learning Discrete Structures for Graph Neural Networks (TensorFlow implementation)

20141PythonMay 13, 20192 years agoNOASSERTION
graphgraph-neural-networks

Similar Papers

FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling

84% match1 repo5292018

CNN2GNN: How to Bridge CNN with GNN

83% match2024

Path Integral Based Convolution and Pooling for Heterogeneous Graph Neural Networks

83% match2023

From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited

82% match1 repo142023

Probability Passing for Graph Neural Networks: Graph Structure and Representations Joint Learning

82% match1 repo12024

Semi-Supervised Classification with Graph Convolutional Networks

82% match2 repos7.4k2016

Cite this paper

@article{franceschi2019learning,
  title  = {Learning Discrete Structures for Graph Neural Networks},
  author = {Luca Franceschi and Mathias Niepert and Massimiliano Pontil and Xiao He},
  year   = {2019},
  eprint = {1903.11960},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1903.11960}
}

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/1903.11960.svg)](https://codeofpaper.com/paper/1903.11960)

Discussion