TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916632955191296 |
|---|---|
| author | Zhang, Yucheng Bevilacqua, Beatrice Galkin, Mikhail Ribeiro, Bruno |
| author_facet | Zhang, Yucheng Bevilacqua, Beatrice Galkin, Mikhail Ribeiro, Bruno |
| contents | Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an important capability towards the goal of having foundation models for knowledge graphs. In this work, we introduce a more expressive and capable fully inductive model, dubbed TRIX, which not only yields strictly more expressive triplet embeddings (head entity, relation, tail entity) compared to state-of-the-art methods, but also introduces a new capability: directly handling both entity and relation prediction tasks in inductive settings. Empirically, we show that TRIX outperforms the state-of-the-art fully inductive models in zero-shot entity and relation predictions in new domains, and outperforms large-context LLMs in out-of-domain predictions. The source code is available at https://github.com/yuchengz99/TRIX. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19512 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs Zhang, Yucheng Bevilacqua, Beatrice Galkin, Mikhail Ribeiro, Bruno Machine Learning Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an important capability towards the goal of having foundation models for knowledge graphs. In this work, we introduce a more expressive and capable fully inductive model, dubbed TRIX, which not only yields strictly more expressive triplet embeddings (head entity, relation, tail entity) compared to state-of-the-art methods, but also introduces a new capability: directly handling both entity and relation prediction tasks in inductive settings. Empirically, we show that TRIX outperforms the state-of-the-art fully inductive models in zero-shot entity and relation predictions in new domains, and outperforms large-context LLMs in out-of-domain predictions. The source code is available at https://github.com/yuchengz99/TRIX. |
| title | TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.19512 |