Metraipolis › archive › dc_bbfeeed51741

Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding — arXiv:2608.24273

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.24273
License (as archived): CC0-1.0
Archived: 2026-10-18T07:00:34.087Z
SHA-256 of the archived text: 941caff884ebff4a6aa5da8d33d0cecc646be4f01da6aa34d8b9de76dff9e8f0
Stable URL of this page: https://metraipolis.com/documento/dc_bbfeeed51741

How to cite

Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding — arXiv:2608.24273 — arXiv (en), https://arxiv.org/abs/2608.24273 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bbfeeed51741 (Metraipolis archive dc_bbfeeed51741, sha256 941caff884ebff4a6aa5da8d33d0cecc646be4f01da6aa34d8b9de76dff9e8f0)

BibTeX

@misc{dcbbfeeed51741,
  title = {Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding — arXiv:2608.24273},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24273},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bbfeeed51741; sha256 941caff884ebff4a6aa5da8d33d0cecc646be4f01da6aa34d8b9de76dff9e8f0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24273. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Continual knowledge graph embedding updates entity and relation representations as a graph grows. Existing methods primarily address catastrophic forgetting, but entity admission also changes the candidate universe of every compatible query. A historical answer can therefore lose rank even when its score and its ordering among old entities are preserved. We formalize this effect as candidate-set interference and introduce Matched Excess-Outranker Regularization (MEOR), a host-level objective that compares smooth answer-relative newcomer pressure with score-blind, structurally matched old references. Its one-sided penalty acts only when newcomer competition exceeds the matched reference, preserving the host learner's signal for legitimate new entities. Across eight paired runs on ENTITY-ComplEx, MEOR improves historical current-universe mean reciprocal rank (MRR) by 0.0057 over replay and reduces candidate-set interference by 0.0055, with one-sided 95% lower bounds of 0.0052 and 0.0051, respectively. It satisfies the preservation criteria for old-universe ranking and newcomer acquisition and improves historical current-universe MRR over persistent calibration, matched maximum regularizer (MMR), and unmatched old regularizer (UOR). Direct ablations support each component of its reference construction and aggregation. Adding MEOR also improves historical ranking in all ten reported FBInc-S and FBInc-L host and backbone settings, with every paired 95% confidence interval excluding zero. These results establish candidate admission as a distinct source of continual rank loss and show that it can be controlled without replacing the underlying embedding architecture or continual learner.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-26 in cs.DB).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Databases (cs.DB); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.24273 — 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 2026-10-18T06:57:47.319Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).