# DeepGraphLearning/KnowledgeGraphEmbedding

Repository: https://github.com/DeepGraphLearning/KnowledgeGraphEmbedding
Canonical: https://ross.abutalabs.com/products/knowledgegraphembedding
Language: Python
License: MIT
License Family: permissive
Last push: 2023-12-15T23:43:27+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": 2779, "days_push": 992, "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 1381, forks 272 (observed 2026-08-28T04:04:33.957032+00:00)

## What it is
A PyTorch toolkit implementing the RotatE knowledge graph embedding model along with TransE, ComplEx, DistMult, and pRotatE. It trains and evaluates KGE models on standard benchmarks like FB15k-237 and WN18RR with self-adversarial negative sampling.

## Use cases
- train knowledge graph embeddings with pytorch
- reproduce RotatE ICLR 2019 paper results
- run link prediction on FB15k-237 and WN18RR
- compare TransE ComplEx DistMult RotatE models
- evaluate knowledge graph completion with MRR and Hits@k
- learn how self-adversarial negative sampling works

## When to choose
- you need state-of-the-art KGE baselines on standard benchmarks
- you want to reproduce or extend the RotatE paper
- you need fast single-GPU training of knowledge graph embeddings

## When to avoid
- you need production serving or an embedding API
- you want multi-GPU or very large-scale training (use GraphVite instead)
- you need actively maintained code with recent dependency updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, rag
- domain: machine-learning, deep-learning, artificial-intelligence, databases
- platform: python, cross-platform
- tags: knowledge-graph-embedding, pytorch, rotate, transe, complex, distmult, link-prediction, negative-sampling, research-code, gpu, linux

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:33.957032+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 2026-08-30T04:40:09.035153+00:00, confidence not recorded.
  - readme: https://github.com/DeepGraphLearning/KnowledgeGraphEmbedding (fetched 2026-08-28T04:04:33.957032+00:00, sha 283920fe8c41)
- Data as of 2026-08-30T08:39:29.467469+00:00.