dmlc/dgl

About adding KGCN as an example of Recommender Systems

Open

#1,138 opened on Dec 24, 2019

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (2,928 forks)batch import
help wanted

Repository metrics

Stars
 (12,665 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

🚀 Feature

Can kgcn be used as an example of a recommendation system? Examples of recommendation systems are few. KGCN involves neighbor sampling, which is a good example of Nodeflow. It's also not too complicated Hope to implement with Pytorch.

(www19)Knowledge Graph Convolutional Networks for Recommender Systems https://arxiv.org/abs/1904.12575 https://github.com/hwwang55/KGCN

Contributor guide

Research direction
Start by reading the KGCN paper (arXiv:1904.12575) and its official PyTorch implementation. Then adapt it to DGL by replacing manual neighbor sampling with DGL's built in sampler (e.g., NeighborSampler). Integrate it as a new example under the 'examples' directory in the DGL repository. Ensure the example demonstrates recommendation on a knowledge graph dataset (e.g., MovieLens 20M). Test with current DGL API and provide a script to reproduce results.
Tech stack
pythonpytorch
Domain
backendmachine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
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
PythonPyTorchBasic understanding of Graph Neural Networks
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40