Graph Representation Learning

By William L. Hamilton. Synthesis Lectures on Artificial Intelligence and Machine Learning, 2020

1,249 citations recorded by the source corpus.

Abstract Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learnin...

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/45f4585f12ed7310c2dbc487a2aa1ba23c568071

How researchers see this paper

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

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

A Survey of Machine Unlearning (2022, positive): “Graph representation learning is a well-established research direction in machine learning, specifically in deep learning [20, 64].”
Adversarial Graph Augmentation to Improve Graph Contrastive Learning (2021, methodology): “1, the graph representation is obtained by pooling the ﬁnal set of node representations as, For design choices regarding aggregation, update and pooling functions we refer the reader to [3,7,8].”
DEBAGREEMENT: A comment-reply dataset for (dis)agreement detection in online debates (2021, methodology): “Modeling online discussion forums as graphs of interactions between users enables researchers to: i) translate the (dis)agreement detection task into a sign link prediction one [45], ii) use recent advances in GRL methods [20], and iii) leverage existing signed graph embedding methods [41, 15, 30] t”
Long Range Graph Benchmark (2022, positive): “This has led to a rapid rise of interest in the development of graph neural networks (GNNs) [24, 42, 9, 61] for deep learning on geometric and graph domains.”
Explainability in Graph Neural Networks: A Taxonomic Survey (2020, neutral): “cules, and financial data [27], [28], [29].”
Revisiting Heterophily For Graph Neural Networks (2022, background): “Generally, the Laplacian matrices (Lsym, Lrw, L̂sym, L̂rw) can be regarded as HP filters [11] and affinity matrices (Asym, Arw, Âsym, Ârw) can be treated as LP filters [34, 14].”
Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence (2023, background): “GAE is an unsupervised learning framework that can convert graph structures into lowdimensional vectors and reconstruct graph structures using encoded information and is often used for graph embedding (GE) and graph structure generation [26].”
Self-Supervised Learning of Graph Neural Networks: A Unified Review (2021, background): “Given the success in the image domain and natural language modeling, various variations of graph autoencoder [85] are pro-”
ETA Prediction with Graph Neural Networks in Google Maps (2021, background): “As the road network is naturally modelled by a graph of road segments and intersections, ETA prediction is amenable to graph representation learning [1, 2, 10] approaches, particularly graph neural networks (GNNs) [8, 15, 25].”
Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, background): “As a general definition, a graph is simply a collection of objects (i.e., vertices or nodes), along with a set of interactions between the pairs of these objects (i.e., edges or links) [9].”
Rethinking Graph Transformers with Spectral Attention (2021, background): “The prevailing strategy for graph neural networks (GNNs) has been to directly encode graph structure structure through a sparse message-passing process [17, 19].”