Fast Graph Representation Learning with PyTorch Geometric

Fey, Matthias; Lenssen, Jan Eric

doi:10.48550/arxiv.1903.02428

Cited by 478 publications

(528 citation statements)

References 19 publications

Supporting

Mentioning

528

Contrasting

Order By: Relevance

“…All of the experiments were implemented using Python 3.8, Pytorch 1.7.1 and Pytorch Geometric 1.7.0 [60]. The code base that was used to perform these experiments is available 4 .…”

Section: Methodsmentioning

confidence: 99%

BLDNet: A Semi-supervised Change Detection Building Damage Framework using Graph Convolutional Networks and Urban Domain Knowledge

Ismail¹,

Awad²

2022

Preprint

View full text Add to dashboard Cite

Change detection is instrumental to localize damage and understand destruction in disaster informatics. While convolutional neural networks are at the core of recent change detection solutions, we present in this work, BLDNet, a novel graph formulation for building damage change detection and enable learning relationships and representations from both local patterns and non-stationary neighborhoods. More specifically, we use graph convolutional networks to efficiently learn these features in a semisupervised framework with few annotated data. Additionally, BLDNet formulation allows for the injection of additional contextual building meta-features. We train and benchmark on the xBD dataset to validate the effectiveness of our approach. We also demonstrate on urban data from the 2020 Beirut Port Explosion that performance is improved by incorporating domain knowledge building meta-features.

show abstract

“…All of the experiments were implemented using Python 3.8, Pytorch 1.7.1 and Pytorch Geometric 1.7.0 [60]. The code base that was used to perform these experiments is available 4 .…”

Section: Methodsmentioning

confidence: 99%

BLDNet: A Semi-supervised Change Detection Building Damage Framework using Graph Convolutional Networks and Urban Domain Knowledge

Ismail¹,

Awad²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The experiments were implemented using Python 3.8, Pytorch 1.7.1 and Pytorch Geometric 1.7.0 [17]. The code 2 was executed on a virtual machine running on 8 cores of an AMD EPYC 7551 32-Core Processor with an Nvidia V100 32GB GPU.…”

Section: Methodsmentioning

confidence: 99%

Towards Cross-Disaster Building Damage Assessment with Graph Convolutional Networks

Ismail¹,

Awad²

2022

Preprint

View full text Add to dashboard Cite

In the aftermath of disasters, building damage maps are obtained using change detection to plan rescue operations. Current convolutional neural network approaches do not consider the similarities between neighboring buildings for predicting the damage. We present a novel graph-based building damage detection solution to capture these relationships. Our proposed model architecture learns from both local and neighborhood features to predict building damage. Specifically, we adopt the sample and aggregate graph convolution strategy to learn aggregation functions that generalize to unseen graphs which is essential for alleviating the time needed to obtain predictions for new disasters. Our experiments on the xBD dataset and comparisons with a classical convolutional neural network reveal that while our approach is handicapped by class imbalance, it presents a promising and distinct advantage when it comes to cross-disaster generalization.

show abstract

“…Our model is built upon Pytorch [28] and PyG (PyTorch Geometric) library [29]. We train MGAE for 200 epochs with Adam [30] optimizer and early stopping with a patience of 50 epochs.…”

Section: Methodsmentioning

confidence: 99%

MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs

Tan¹,

Liu²,

Hu³

et al. 2022

Preprint

View full text Add to dashboard Cite

We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these missing edges during training. MGAE has two core designs. First, we find that masking a high ratio of the input graph structure, e.g., 70%, yields a nontrivial and meaningful self-supervisory task that benefits downstream applications. Second, we employ a graph neural network (GNN) as an encoder to perform message propagation on the partially-masked graph. To reconstruct the large number of masked edges, a tailored cross-correlation decoder is proposed. It could capture the cross-correlation between the head and tail nodes of anchor edge in multigranularity. Coupling these two designs enables MGAE to be trained efficiently and effectively. Extensive experiments on multiple open datasets (Planetoid and OGB benchmarks) demonstrate that MGAE generally performs better than state-ofthe-art unsupervised learning competitors on link prediction and node classification.Preprint. Under review.

show abstract

Fast Graph Representation Learning with PyTorch Geometric

Cited by 478 publications

References 19 publications

BLDNet: A Semi-supervised Change Detection Building Damage Framework using Graph Convolutional Networks and Urban Domain Knowledge

BLDNet: A Semi-supervised Change Detection Building Damage Framework using Graph Convolutional Networks and Urban Domain Knowledge

Towards Cross-Disaster Building Damage Assessment with Graph Convolutional Networks

MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs

Contact Info

Product

Resources

About