# tangjianpku/LINE

LINE: Large-scale information network embedding

Repository: https://github.com/tangjianpku/LINE
Canonical: https://ross.abutalabs.com/products/line
Language: C++
License Family: other
Last push: 2024-07-16T05:03:25+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": 4198, "days_push": 778, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1053, forks 408 (observed 2026-08-28T04:03:23.618895+00:00)

## What it is
LINE is a C++ toolkit for embedding very large-scale information networks into low-dimensional vectors, supporting directed, undirected, binary, and weighted edges. It can embed networks with millions of vertices and billions of edges on a single machine within hours.

## Use cases
- embed large-scale information networks into vectors
- learn node embeddings for a social network graph
- generate graph embeddings for link prediction
- embed a weighted directed graph with millions of nodes
- train network representations for node classification

## When to choose
- you need to embed a very large network (billions of edges) on a single machine
- you want the classic LINE first-order/second-order proximity model
- you work with C++ and want a fast, lightweight graph embedding tool

## When to avoid
- you want actively maintained software - the repo is explicitly unmaintained
- you need modern graph embedding methods - use the authors' GraphVite instead
- you prefer Python-based tooling or GPU acceleration

## Facets
- artifact type: cli-tool
- maturity: abandoned
- function: machine-learning, cli
- domain: machine-learning, graph-processing
- platform: windows, cpp
- tags: graph-embedding, network-embedding, node2vec, unsupervised-learning, algorithms, linux

## Member repositories
- tangjianpku/LINE (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.618895+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 2026-08-30T06:59:39.205750+00:00, confidence not recorded.
  - readme: https://github.com/tangjianpku/LINE (fetched 2026-08-28T04:03:23.618895+00:00, sha d86fb580a2e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.