NSLab-CUK/Unified-Graph-Transformer
Unified Graph Transformer (UGT) is a novel Graph Transformer model specialised in preserving both local and global graph structures and developed by NS Lab @ CUK based on pure PyTorch backend.
This project helps machine learning researchers and practitioners analyze complex graph-structured data by focusing on both immediate connections and broader network patterns. It takes your graph data (like social networks, biological structures, or citation graphs) and processes it to produce improved, unified numerical representations (embeddings) of nodes and graphs. These representations can then be used for tasks like grouping similar nodes, classifying nodes, or classifying entire graphs.
No commits in the last 6 months.
Use this if you are a machine learning researcher or data scientist working with graph data and need to generate highly accurate node or graph embeddings that capture both local and global structural information for downstream tasks.
Not ideal if you are a business user without a technical background in machine learning or if your data is not graph-structured.
Stars
28
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jul 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/NSLab-CUK/Unified-Graph-Transformer"
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...
snap-stanford/relgt
Relational Graph Transformer
omron-sinicx/crystalframer
The official code respository for "Rethinking the role of frames for SE(3)-invariant crystal...