vijaydwivedi75/gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
This project offers a new way to design Graph Neural Networks (GNNs) that can better understand the structure and position of data points in a graph. It takes any existing 'message-passing' GNN model as input and enhances it with learnable structural and positional encodings. This is for researchers and practitioners in machine learning who are working on advanced GNN applications and want to improve model performance on complex graph datasets.
267 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner developing or applying Graph Neural Networks and want to improve their ability to capture intricate structural and positional information within your graph data.
Not ideal if you are looking for a pre-trained, out-of-the-box solution for a specific graph task without needing to delve into GNN architecture modifications.
Stars
267
Forks
37
Language
Python
License
MIT
Category
Last pushed
Feb 10, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/vijaydwivedi75/gnn-lspe"
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...
snap-stanford/relgt
Relational Graph Transformer
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]