analiza aiqbench
This research introduces LitEm, a neural regression framework designed to integrate numerical attributes into transductive knowledge graph embedding models, addressing a significant gap in current representation learning. By employing a co-training strategy, the method simultaneously enhances link prediction accuracy and enables models to effectively encode literal-aware information without relying solely on parameter bloat. The findings demonstrate that explicitly modeling diverse attribute types improves overall model robustness across standard benchmarks like FB15K-237 and YAGO15K.
Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs
arXiv:2608.26729v1 Announce Type: new Abstract: In recent years, transductive knowledge graph embedding models have been applied to tasks such as link prediction and query answering. Although knowledge graphs often contain rich numerical attributes, most embedding models neglect them, limiting their ability to represent real-world knowledge graphs with diverse information. In this work, we propose a neural regression model (LitEm) that enables transductive knowledge graph embedding models to predict numerical attributes within knowledge graphs. Experimental results demonstrate that LitEm achieves the best or second-best results on most attributes across FB15K-237, YAGO15K, DB15K, and Mutagenesis. Furthermore, we propose a co-training framework that jointly trains state-of-the-art transductive knowledge graph embedding models with LitEm, which improves link prediction performance mainly for bilinear models and simultaneously enables them to predict numerical attributes. In addition, the literal-awareness evaluation demonstrates that co-training helps models to encode and exploit attribute information in a "literal-aware'' manner, suggesting that the observed gains are not merely due to additional parameters. We publicly release our implementation at https://github.com/dice-group/dice-embeddings.
Abstract:In recent years, transductive knowledge graph embedding models have been applied to tasks such as link prediction and query answering. Although knowledge graphs often contain rich numerical attributes, most embedding models neglect them, limiting their ability to represent real-world knowledge graphs with diverse information. In this work, we propose a neural regression model (LitEm) that enables transductive knowledge graph embedding models to predict numerical attributes within knowledge graphs. Experimental results demonstrate that LitEm achieves the best or second-best results on most attributes across FB15K-237, YAGO15K, DB15K, and Mutagenesis. Furthermore, we propose a co-training framework that jointly trains state-of-the-art transductive knowledge graph embedding models with LitEm, which improves link prediction performance mainly for bilinear models and simultaneously enables them to predict numerical attributes. In addition, the literal-awareness evaluation demonstrates that co-training helps models to encode and exploit attribute information in a "literal-aware'' manner, suggesting that the observed gains are not merely due to additional parameters. We publicly release our implementation at this https URL.
Machine Learning (cs.LG)
arXiv:2608.26729 [cs.LG]
(or arXiv:2608.26729v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.26729 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 257 cuvinte
Subiecte conexe
Application of machine learning to monster level prediction in tabletop RPG game design
arXiv · 3 aug. 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · 8 oct. 2026
Model Weight Profiles: Where Do the Parameters Go?
AMD · 25 sept. 2026
Hierarchy-Aware Semantic Losses for Knowledge Graph Link Prediction
arXiv · 25 aug. 2026