pyg-team/pytorch_geometric

`VarMisuse` Dataset + Examples

Open

#3,693 opened on Dec 14, 2021

View on GitHub
 (9 comments) (3 reactions) (0 assignees)Python (3,514 forks)batch import
0 - Priority P0featuregood first issue

Repository metrics

Stars
 (19,985 stars)
PR merge metrics
 (Avg merge 35d 1h) (14 merged PRs in 30d)

Description

🚀 Feature

Motivation

paper "LEARNING TO REPRESENT PROGRAMS WITH GRAPHS" which encode computer programs as graphs, with rich semantic information, however, most code implementation on this dataset VarMisuse is based on TensorFlow, like tf-gnn-samples

Pitch

include VarMisuse dataset in PyG framework as a class under torch_geometric.datasets

Additional context

raw dataset provided by author: VarMisuse

more papers/models on this dataset: GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation ON THE BOTTLENECK OF GRAPH NEURAL NETWORKS AND ITS PRACTICAL IMPLICATIONS

Contributor guide

Research direction
Implement a new dataset class for VarMisuse under torch geometric.datasets, following PyG's dataset conventions (e.g., InMemoryDataset). Download the raw data from Microsoft, parse the program graphs into PyG Data objects, and handle train/val/test splits. Refer to existing datasets like GNNBenchmarkDataset for structure.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorchPyG
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60