GraphGPS: Navigating Graph Transformers | by Michael Galkin | Towards Data Science

Recipes for cooking the best graph transformers

GraphGPS: Navigating Graph Transformers | Towards Data Science Skip to content Artificial Intelligence GraphGPS: Navigating Graph Transformers Recipes for cooking the best graph transformers Michael Galkin Jun 14, 2022 15 min read Share Recent Advances in Graph ML In 2021, graph transformers (GT) won recent molecular property prediction challenges thanks to alleviating many issues pertaining to vanilla message passing GNNs. Here, we try to organize numerous freshly developed GT models into a single GraphGPS framework to enable general, powerful, and scalable graph transformers with linear comp

related reading

• [2205.12454] Recipe for a General, Powerful, Scalable Graph Transformerarxiv.org
• A Gentle Introduction to Graph Neural Networksdistill.pub
• [2207.02505] Pure Transformers are Powerful Graph Learnersarxiv.org
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Understanding Convolutions on Graphsdistill.pub
• Beyond Message Passing: a Physics-Inspired Paradigm for Graph Neural Networksthegradient.pub
• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• Let Your Graph Do the Talking: Encoding Structured Data for LLMsarxiv.org
• Transformers from Scratche2eml.school
• [2209.05582] Graph Neural Networks for Moleculesarxiv.org
• Graph Convolutional Networks | Thomas Kipf | Google DeepMindtkipf.github.io
• The Annotated Transformernlp.seas.harvard.edu