# thunlp/KB2E

Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE

Repository: https://github.com/thunlp/KB2E
Canonical: https://ross.abutalabs.com/products/kb2e
Language: C++
License: MIT
License Family: permissive
Topics: knowledge-embedding
Last push: 2022-11-03T06:53:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3761, "days_push": 1399, "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 1420, forks 445 (observed 2026-08-28T04:04:40.556035+00:00)

## What it is
KB2E is a C++ library implementing knowledge graph embedding models including TransE, TransH, TransR, and PTransE from Tsinghua University's THU-OpenSK project. The project is no longer maintained and users are directed to its successor, OpenKE.

## Use cases
- train knowledge graph embeddings with transe
- compute transh embeddings for a knowledge base
- learn entity and relation vectors with transr
- run ptrans on a knowledge graph
- research knowledge graph representation learning

## When to choose
- you need the original C++ implementations of TransE/TransH/TransR/PTransE for research reproduction

## When to avoid
- you want an actively maintained knowledge embedding toolkit - use OpenKE instead
- you need Python or GPU-based training

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning
- domain: machine-learning, artificial-intelligence, databases
- platform: cpp, cross-platform
- tags: knowledge-graph, knowledge-graph-embeddings, transe, transh, transr, ptrans, research, embedding, linux

## Member repositories
- thunlp/KB2E (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:40.556035+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 2026-08-30T04:37:50.106631+00:00, confidence not recorded.
  - readme: https://github.com/thunlp/KB2E (fetched 2026-08-28T04:04:40.556035+00:00, sha d56133be0068)
- Data as of 2026-08-30T08:39:29.467469+00:00.