tensorflow / tensorflow/gnn

Dynamically complete the features for nodes in the graph during training

Open
#776 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.5k
Forks
204
Avg merge
13m
Merged PRs (30d)
1

Description

I plan to use graph convolution for constructing item embeddings in a recommendation system. When generating the dataset, I found that attaching all features of the items to the nodes would result in an excessively large dataset, causing IO bottlenecks and low GPU utilization. Is there a way to generate a dataset only containing node IDs and dynamically complete the features for nodes in the graph during training?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files, tests, or entry points. Start by tracing how graph datasets provide node features to the training pipeline, then determine whether node IDs can be used to retrieve features dynamically without creating an oversized dataset. Done would be a clearly defined supported approach, with its behavior and validation requirements identified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, tensorflow
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.