snap-stanford/relgt
Relational Graph Transformer
This project offers a sophisticated tool for building predictive models from multi-table relational data, like customer databases or financial transactions, which can be visualized as complex networks. It takes in structured relational datasets, optionally with time-sensitive information, and helps generate accurate predictions or insights. This is ideal for data scientists and machine learning engineers who need to analyze intricate relationships within large datasets.
No commits in the last 6 months.
Use this if you need to build state-of-the-art predictive models on multi-table relational data where understanding complex relationships and temporal patterns is crucial.
Not ideal if your data is simple, fits neatly into a single table, or if you lack experience with advanced machine learning model development.
Stars
65
Forks
15
Language
Python
License
MIT
Category
Last pushed
Jul 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/snap-stanford/relgt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SamsungSAILMontreal/nino
Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [ICLR 2025]
graphdeeplearning/graphtransformer
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to...
vijaydwivedi75/gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional...
omron-sinicx/crystalframer
The official code respository for "Rethinking the role of frames for SE(3)-invariant crystal...
SamsungSAILMontreal/ghn3
Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]