Trapped in the Net: Where is a Foundation Model for Graphs? | by Salvatore Raieli | Nov, 2024

|LLM|TRANSFORMER|FOUNDATION MODEL|GRAPH|NETWORK|

Disconnected from the opposite modalities graphs wait for his or her AI revolution: is it coming?

“If the muse is stable, every little thing else will comply with.” – Unknown

“The loftier the constructing, the deeper should the muse be laid.” – Thomas à Kempis

Basis fashions have modified synthetic intelligence in recent times. A basis mannequin is a mannequin skilled with big quantities of information (normally by unsupervised studying) that may be tailored to totally different duties. Fashions resembling BERT or GPT led to a revolution through which one mannequin might then be tailored for all duties in a site, simplifying AI entry and decreasing the necessity for knowledge for a single job. We’ve got basis fashions for textual content and different modalities, however for modalities resembling graphs and tabular knowledge, we don’t. On this paper we focus on why we would not have a basis mannequin for graphs and the way we would get one, particularly, we’ll reply these questions:

• Why do we would like a basis mannequin for graphs? Why can we not have one?