Metraipolis › archive › dc_43a32c88bf9f

Uncertainty in Representation Learning on Knowledge Graphs — arXiv:2610.06974

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06974
License (as archived)
CC0-1.0
Archived
2026-10-07T11:40:41.697Z
SHA-256 of the archived text
3efa84b9fc521c6eebdd5582b8154e14724a5a6fa01437d9db9cb26d981d13d8
Stable URL of this page
https://metraipolis.com/documento/dc_43a32c88bf9f

How to cite

Uncertainty in Representation Learning on Knowledge Graphs — arXiv:2610.06974 — arXiv (en), https://arxiv.org/abs/2610.06974 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43a32c88bf9f (Metraipolis archive dc_43a32c88bf9f, sha256 3efa84b9fc521c6eebdd5582b8154e14724a5a6fa01437d9db9cb26d981d13d8)
BibTeX
@misc{dc43a32c88bf9f,
  title = {Uncertainty in Representation Learning on Knowledge Graphs — arXiv:2610.06974},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06974},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43a32c88bf9f; sha256 3efa84b9fc521c6eebdd5582b8154e14724a5a6fa01437d9db9cb26d981d13d8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06974. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Knowledge graph embedding (KGE) methods represent entities and predicates in continuous vector spaces to infer missing knowledge. Despite strong benchmark performance, their predictions often lack principled reliability guarantees, limiting their use in high-stakes applications. Moreover, uncertainty arises throughout the KGE pipeline, from incomplete or probabilistic input knowledge to stochastic training and prediction. This thesis systematically investigates three sources of uncertainty in KGE: knowledge uncertainty, arising from incomplete, noisy, or probabilistic input knowledge; algorithmic uncertainty, induced by randomness in model training; and predictive uncertainty, concerning the reliability of model outputs. To address algorithmic uncertainty, the thesis demonstrates that models trained under identical settings can produce substantially different predictions and introduces a voting-based aggregation framework to mitigate this instability. To quantify predictive uncertainty, it adapts conformal prediction to KGE, constructing answer sets with distribution-free coverage guarantees and extending them to provide predicate-conditional reliability guarantees. To support reasoning under knowledge uncertainty, it develops statistically valid prediction intervals for confidence-scored triples and an embedding-based approach to approximate probabilistic reasoning over statistical ontologies with formal soundness guarantees. Together, these complementary, model-agnostic methods provide a practical and theoretically grounded approach to uncertainty in KGE, advancing beyond predictive accuracy toward reliable and uncertainty-aware knowledge graph reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06974 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:19:24.711Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).