Graph translator#241
Open
Hinataee wants to merge 2 commits into
Open
Conversation
…out the correctness for the other backends)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces the initial implementation of the GraphTranslator example, including code for pre-training a graph neural network, generating node summaries using a large language model, and 2-statge training for GraphTranslator. The main changes are the addition of new scripts for the Producer and Translator phases, as well as a comprehensive README with setup and usage instructions.
Producer Phase Implementation (Data preparation):
Embeddings_GraphSAGE.pyto pre-train a GraphSAGE model for node embeddings using link prediction on the OGBN-Arxiv dataset, with integration of BERT node embeddings and TensorLayerX for training.producer.pyto generate node summaries and neighbor summaries using ChatGLM2-6B, including dataset parsing, prompt construction, and result serialization.Translator Phase:
graphtranslator_trainer.py: Training Phase, which trains the Translator model for GraphModel-Text (Stage 1) and GraphModel-LLM alignment (Stage 2).graphtranslator_eval.py: Generate and Evaluate Phase, which generates predictions and evaluates the accuracy of the generated predictions.