pyg-team/pytorch_geometric

Please add implementation for HyperGCN

Open

#1,334 opened on Jun 17, 2020

View on GitHub
 (7 comments) (1 reaction) (0 assignees)Python (3,514 forks)batch import
0 - Priority P0examplefeaturehelp wantednn

Repository metrics

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

Description

🚀 Feature

Please add implementation for HGCN (https://github.com/HazyResearch/hgcn) and HGNN (https://github.com/facebookresearch/hgnn), if feasible and at your convenience.

Motivation

From http://snap.stanford.edu/hgcn/: Graph convolutional neural networks (GCNs) map nodes in a graph to Euclidean embeddings, which have been shown to incur a large distortion when embedding real-world graphs with scale-free or hierarchical structure. Hyperbolic geometry offers an exciting alternative, as it enables embeddings with much smaller distortion.

Additional context

Contributor guide

Research direction
Read the HGCN and HGNN papers to understand the hyperbolic graph convolution operations, then implement the models following the existing GNN framework in PyTorch Geometric.
Tech stack
pythonpytorch
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Over 1 week
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
PythonPyTorchGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
35