Deep Gaussian Embedding of Attributed Graphs: Unsupervised Inductive Learning via Ranking

By Aleksandar Bojchevski, Stephan Günnemann. 2017

59 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

In Graph Learning

Citations in the corpus

Fast Graph Representation Learning with PyTorch Geometric (2019, background): “…datasets 3 (Kersting et al., 2016), e.g. , PROTEINS or IMDB-BINARY, the citation graphs Cora, CiteSeer, PubMed and Cora-Full (Sen et al., 2008; Bojchevski & Günnemann, 2018), the Coauthor CS/Physics and Amazon Computers/Photo datasets from Shchur et al. (2018), the molecule datasets QM7b…”
Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks (2019, methodology): “Cora, CiteSeer, PubMed and Cora Full (Sen et al., 2008; Bojchevski & Günnemann, 2018) are citation network datasets where nodes represent documents, and edges represent (undirected) citation links.”
Pitfalls of Graph Neural Network Evaluation (2018, methodology): “Datasets For our experiments, we used the four well-known citation network datasets: PubMed [Namata et al., 2012], CiteSeer and CORA from Sen et al. [2008], as well as the extended version of CORA from Bojchevski and Günnemann [2018], denoted as CORA-Full.”
Attention-based Graph Neural Network for Semi-supervised Learning (2018, background): “Graph2Gauss [1] represents a node as a Gaussian distribution, and minimizes the divergence between connected pairs.”
Adversarial Examples on Graph Data: Deep Insights into Attack and Defense (2019, methodology): “We use the widely used CORA-ML, CITESEER [ Bojchevski and G¨unnemann, 2018 ] and Polblogs [ Adamic and Glance, 2005 ] datasets.”
LASAGNE: Locality and Structure Aware Graph Node Embedding (2017, background): “Most recent representation learning methods for graph vertices construct vectors on the basis of local neighborhood information [24], [28], [8], [12], [17], [1], [30], [6].”
MOTIFNET: A MOTIF-BASED GRAPH CONVOLUTIONAL NETWORK FOR DIRECTED GRAPHS (2018, methodology): “We tested our approach on the directed CORA citation network [13].”
Dual-Primal Graph Convolutional Networks (2018, methodology): “For this experiment, we used a directed version of the CORA graph [32,4], of which we took a subset containing 1118 vertices (each represented by a 8710-dimensional feature vector) and 4155 directed edges.”