# Augmenting Knowledge Graphs for Better Link Prediction

arXiv: https://arxiv.org/abs/2203.13965 · HTML: https://mlsanity.com/paper/2203.13965/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 26 Mar 2022.

## Builds on (most cited first, 14 of 14)

- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [PyTorch-BigGraph: A Large-scale Graph Embedding System](https://mlsanity.com/paper/1903.12287/) (2019)
- [Tensor Decompositions for temporal knowledge base completion](https://mlsanity.com/paper/2004.04926/) (2020)
- [MMKG: Multi-Modal Knowledge Graphs](https://mlsanity.com/paper/1903.05485/) (2019)
- [A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly?](https://mlsanity.com/paper/1910.12507/) (2019)
- [Incorporating Literals into Knowledge Graph Embeddings](https://mlsanity.com/paper/1802.00934/) (2018)
- [KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features](https://mlsanity.com/paper/1709.04676/) (2017)
- [SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions](https://mlsanity.com/paper/1604.04835/) (2016)
- [Multi-task Neural Network for Non-discrete Attribute Prediction in Knowledge Graphs](https://mlsanity.com/paper/1708.04828/) (2017)
- [Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation](https://mlsanity.com/paper/2011.05301/) (2020)

## Built on by (most cited first, 7 of 7)

- [NativE: Multi-modal Knowledge Graph Completion in the Wild](https://mlsanity.com/paper/2406.17605/) (2024)
- [Universal Preprocessing Operators for Embedding Knowledge Graphs with Literals](https://mlsanity.com/paper/2309.03023/) (2023)
- [Literal-Aware Knowledge Graph Embedding for Welding Quality Monitoring: A Bosch Case](https://mlsanity.com/paper/2308.01105/) (2023)
- [Numerical Literals in Link Prediction: A Critical Examination of Models and Datasets](https://mlsanity.com/paper/2407.18241/) (2024)
- [ReaLitE: Enrichment of Relation Embeddings in Knowledge Graphs using Numeric Literals](https://mlsanity.com/paper/2504.00852/) (2025)
- [CHAINSFORMER: Numerical Reasoning on Knowledge Graphs from a Chain Perspective](https://mlsanity.com/paper/2504.14282/) (2025)
- [Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs](https://mlsanity.com/paper/2608.26729/) (2026)

## Abstract (arXiv)

Embedding methods have demonstrated robust performance on the task of link prediction in knowledge graphs, by mostly encoding entity relationships. Recent methods propose to enhance the loss function with a literal-aware term. In this paper, we propose KGA: a knowledge graph augmentation method that incorporates literals in an embedding model without modifying its loss function. KGA discretizes quantity and year values into bins, and chains these bins both horizontally, modeling neighboring values, and vertically, modeling multiple levels of granularity. KGA is scalable and can be used as a pre-processing step for any existing knowledge graph embedding model. Experiments on legacy benchmarks and a new large benchmark, DWD, show that augmenting the knowledge graph with quantities and years is beneficial for predicting both entities and numbers, as KGA outperforms the vanilla models and other relevant baselines. Our ablation studies confirm that both quantities and years contribute to KGA's performance, and that its performance depends on the discretization and binning settings. We make the code, models, and the DWD benchmark publicly available to facilitate reproducibility and future research.