# Schema First! Learn Versatile Knowledge Graph Embeddings by Capturing Semantics with MASCHInE

arXiv: https://arxiv.org/abs/2306.03659 · HTML: https://mlsanity.com/paper/2306.03659/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 17 of 17)

- [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)
- [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)
- [Scaling Up Graph Neural Networks Via Graph Coarsening](https://mlsanity.com/paper/2106.05150/) (2021)
- [HARP: Hierarchical Representation Learning for Networks](https://mlsanity.com/paper/1706.07845/) (2017)
- [Type-Constrained Representation Learning in Knowledge Graphs](https://mlsanity.com/paper/1508.02593/) (2015)
- [Knowledge Graphs on the Web -- an Overview](https://mlsanity.com/paper/2003.00719/) (2020)
- [Rethinking Graph Convolutional Networks in Knowledge Graph Completion](https://mlsanity.com/paper/2202.05679/) (2022)
- [Type-augmented Relation Prediction in Knowledge Graphs](https://mlsanity.com/paper/2009.07938/) (2020)
- [Poisoning Knowledge Graph Embeddings via Relation Inference Patterns](https://mlsanity.com/paper/2111.06345/) (2021)
- [Sem@K: Is my knowledge graph embedding model semantic-aware?](https://mlsanity.com/paper/2301.05601/) (2023)
- [AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding](https://mlsanity.com/paper/2009.12030/) (2020)
- [Instance-based Learning for Knowledge Base Completion](https://mlsanity.com/paper/2211.06807/) (2022)
- [The DLCC Node Classification Benchmark for Analyzing Knowledge Graph Embeddings](https://mlsanity.com/paper/2207.06014/) (2022)
- [Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction](https://mlsanity.com/paper/2303.00286/) (2023)
- [Exploiting Global Semantic Similarities in Knowledge Graphs by Relational Prototype Entities](https://mlsanity.com/paper/2206.08021/) (2022)

## Built on by (most cited first, 3 of 3)

- [SnapE -- Training Snapshot Ensembles of Link Prediction Models](https://mlsanity.com/paper/2408.02707/) (2024)
- [PyGraft: Configurable Generation of Synthetic Schemas and Knowledge Graphs at Your Fingertips](https://mlsanity.com/paper/2309.03685/) (2023)
- [Do Similar Entities have Similar Embeddings?](https://mlsanity.com/paper/2312.10370/) (2023)

## Abstract (arXiv)

Knowledge graph embedding models (KGEMs) have gained considerable traction in recent years. These models learn a vector representation of knowledge graph entities and relations, a.k.a. knowledge graph embeddings (KGEs). Learning versatile KGEs is desirable as it makes them useful for a broad range of tasks. However, KGEMs are usually trained for a specific task, which makes their embeddings task-dependent. In parallel, the widespread assumption that KGEMs actually create a semantic representation of the underlying entities and relations (e.g., project similar entities closer than dissimilar ones) has been challenged. In this work, we design heuristics for generating protographs -- small, modified versions of a KG that leverage RDF/S information. The learnt protograph-based embeddings are meant to encapsulate the semantics of a KG, and can be leveraged in learning KGEs that, in turn, also better capture semantics. Extensive experiments on various evaluation benchmarks demonstrate the soundness of this approach, which we call Modular and Agnostic SCHema-based Integration of protograph Embeddings (MASCHInE). In particular, MASCHInE helps produce more versatile KGEs that yield substantially better performance for entity clustering and node classification tasks. For link prediction, using MASCHinE substantially increases the number of semantically valid predictions with equivalent rank-based performance.