# DeepGraphLearning/graphvite

GraphVite: A General and High-performance Graph Embedding System

Repository: https://github.com/DeepGraphLearning/graphvite
Canonical: https://ross.abutalabs.com/products/graphvite
Homepage: https://graphvite.io
Language: C++
License: Apache-2.0
License Family: permissive
Topics: machine-learning, network-embedding, knowledge-graph, data-visualization, representation-learning, cuda, gpu
Last push: 2024-06-14T21:18:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2605, "days_push": 810, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1269, forks 154 (observed 2026-08-28T04:04:11.580120+00:00)

## What it is
GraphVite is a general, high-performance graph embedding engine written in C++ with Python bindings, supporting node embedding, knowledge graph embedding, and graph/high-dimensional data visualization. It provides training and evaluation pipelines with GPU acceleration and large speedups over existing implementations.

## Use cases
- train node embeddings like deepwalk or node2vec on large graphs
- learn knowledge graph embeddings with TransE or RotatE
- visualize high-dimensional graph data in 2D
- benchmark graph embedding models on standard datasets
- speed up network embedding training with GPUs
- download pre-trained graph embedding models

## When to choose
- you need fast, large-scale graph or knowledge graph embedding training
- you want GPU-accelerated node2vec/DeepWalk/LINE with benchmarks
- you need graph visualization of high-dimensional data

## When to avoid
- you need a pure-Python or Windows-native solution
- you need actively developed features beyond the supported models
- your graphs are tiny and CPU implementations suffice

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, data-visualization, gpu-computing, benchmarking
- domain: machine-learning, deep-learning, data-visualization
- platform: cpp, python
- tags: graph-embedding, network-embedding, knowledge-graph-embedding, node2vec, deepwalk, representation-learning, algorithms, linux, gpu, cuda

## Member repositories
- DeepGraphLearning/graphvite (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:11.580120+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:03:29.740890+00:00, confidence not recorded.
  - readme: https://github.com/DeepGraphLearning/graphvite (fetched 2026-08-28T04:04:11.580120+00:00, sha 9e0a7346f777)
- Data as of 2026-08-30T08:39:29.467469+00:00.