Graph ML Papers Hub

Organized index of landmark and recent papers. Read the learn notes first, then dive into primary sources.

Foundations

GCN - Kipf & Welling (2017)
MPNN - Gilmer et al. (2017)
GraphSAGE - Hamilton et al. (2017)
GAT - Veličković et al. (2018)
GIN - Xu et al. (2019)
ChebNet - Defferrard et al. (2016)

Theory & Limits

Geometric Deep Learning Blueprint - Bronstein et al. (2021)
Over-Squashing - Topping et al. (2022)
Beyond Homophily - Zhu et al. (2020)
NGNN - Zhang et al. (2022)

Heterogeneous & Temporal

R-GCN - Schlichtkrull et al. (2018)
HGT - Hu et al. (2020)
TGN - Rossi et al. (2020)

Graph Transformers

Graphormer - Ying et al. (2021)
GPS - Rampášek et al. (2022)
GRIT - Ma et al. (2023)

Self-Supervised & Foundation Models

GraphMAE - Hou et al. (2022)
GraphGPT - Liu et al. (2023)
OneForAll - Liu et al. (2023)

LLM + Graph

GraphRAG - Edge et al. (Microsoft, 2024)
Text-Attributed Graphs - Chen et al. (2023)
G-Retriever (2024)
Think-on-Graph (2024)

Benchmarks & Surveys

OGB - Hu et al. (2020)
Graph Representation Learning Survey - Hamilton (2017)
Graph Representation Learning (book) - Hamilton
Geometric Deep Learning (book) - Bronstein et al.

Deep dive: Recent Advances learn page