Skip to content

pvarshney1729/CS224W-Project

Repository files navigation

Unifying Text and Structure to Enhance GNNs on Text-Augmented Graphs

This project was undertaken as part of CS 224W : Machine Learning with Graphs at Stanford, Fall 2023.

Authors: Abhinav Lalwani, Ananjan Nandi, Prateek Varshney

This repository contains the following Colabs:

  • CS224W_Project_Text_Augmented_Graphs_Arxiv.ipynb: contains code for experiments using various techniques for combining textual and graph information, tested on the OGBN-Arxiv dataset
  • CS224W_Project_Text_Augmented_Graphs_Products.ipynb: This Colab contains code for experiments using various techniques for combining textual and graph information, tested on the OGBN-Products dataset
  • KGC.ipynb : This notebook can be used to run RotatE on the WN18RR and CoDex-M datasets, and save the trained models.
  • KGC_Ensemble.ipynb: This notebook can be used to obtain results for dynamic ensembling of SimKGC and RotatE on the WN18RR and CoDex-M datasets.
  • Embeddings_Arxiv.ipynb: contains the code to dump the resultant embeddings for an LM model pretrained on OGBN Arxiv
  • Embeddings_Products.ipynb: contains the code to dump the resultant embeddings for an LM model pretrained on OGBN Products
  • LM_Trainer_Arxiv.ipynb: contains the code to train an LM on OGBN-Arxiv
  • LM_Trainer_Products.ipynb: contains the code to train an LM on OGBN-Products

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published