π
π
The Cartographer
Do Similar Entities have Similar Embeddings?
December 16, 2023 Β· Entered Twilight Β· π Extended Semantic Web Conference
Repo contents: .gitignore, README.md, embeddings, fast_jaccard.py, get_datasets_statistics.py, get_rel_freq_per_class.py, preprocessed_datasets, requirements.txt, run_expe_1_2.py, run_expe_3.py, utils.py
Authors
Nicolas Hubert, Heiko Paulheim, Armelle Brun, Davy Monticolo
arXiv ID
2312.10370
Category
cs.AI: Artificial Intelligence
Cross-listed
cs.IR,
cs.LG
Citations
10
Venue
Extended Semantic Web Conference
Repository
https://github.com/nicolas-hbt/similar-embeddings/
β 4
Last Checked
3 months ago
Abstract
Knowledge graph embedding models (KGEMs) developed for link prediction learn vector representations for entities in a knowledge graph, known as embeddings. A common tacit assumption is the KGE entity similarity assumption, which states that these KGEMs retain the graph's structure within their embedding space, \textit{i.e.}, position similar entities within the graph close to one another. This desirable property make KGEMs widely used in downstream tasks such as recommender systems or drug repurposing. Yet, the relation of entity similarity and similarity in the embedding space has rarely been formally evaluated. Typically, KGEMs are assessed based on their sole link prediction capabilities, using ranked-based metrics such as Hits@K or Mean Rank. This paper challenges the prevailing assumption that entity similarity in the graph is inherently mirrored in the embedding space. Therefore, we conduct extensive experiments to measure the capability of KGEMs to cluster similar entities together, and investigate the nature of the underlying factors. Moreover, we study if different KGEMs expose a different notion of similarity. Datasets, pre-trained embeddings and code are available at: https://github.com/nicolas-hbt/similar-embeddings/.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Artificial Intelligence
R.I.P.
π»
Ghosted
Explanation in Artificial Intelligence: Insights from the Social Sciences
R.I.P.
π»
Ghosted
Federated Machine Learning: Concept and Applications
R.I.P.
π»
Ghosted
Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR
R.I.P.
π»
Ghosted
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
R.I.P.
π»
Ghosted