# Fast Linear Model for Knowledge Graph Embeddings

Source: [Fast Linear Model for Knowledge Graph Embeddings](<https://www.sota2.com/research/paper/68fa63bf1e209131cea00ae8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:49:10.785Z

Authors: Armand Joulin, Edouard Grave, Piotr Bojanowski, Maximilian Nickel, Tomas Mikolov

Published: 2017-10-30T11:46:23.000Z

## Abstract

This paper shows that a simple baseline based on a Bag-of-Words (BoW) representation learns surprisingly good knowledge graph embeddings. By casting knowledge base completion and question answering as supervised classification problems, we observe that modeling co-occurences of entities and relations leads to state-of-the-art performance with a training time of a few minutes using the open sourced library fastText.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1710.10881>)

[PDF](<https://arxiv.org/pdf/1710.10881.pdf>)