Metraipolis › archive › dc_5486550f82f4

ImbalancE: Inference-Time Latent Search Against Degree Imbalance in Link Prediction — arXiv:2609.36996

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36996
License (as archived)
CC0-1.0
Archived
2026-10-07T16:23:21.874Z
SHA-256 of the archived text
7901e54ff1e5e4ee5c4a26c289bdb0841b03a875aa0ed03b9055f733520d9abc
Stable URL of this page
https://metraipolis.com/documento/dc_5486550f82f4

How to cite

ImbalancE: Inference-Time Latent Search Against Degree Imbalance in Link Prediction — arXiv:2609.36996 — arXiv (en), https://arxiv.org/abs/2609.36996 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5486550f82f4 (Metraipolis archive dc_5486550f82f4, sha256 7901e54ff1e5e4ee5c4a26c289bdb0841b03a875aa0ed03b9055f733520d9abc)
BibTeX
@misc{dc5486550f82f4,
  title = {ImbalancE: Inference-Time Latent Search Against Degree Imbalance in Link Prediction — arXiv:2609.36996},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36996},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5486550f82f4; sha256 7901e54ff1e5e4ee5c4a26c289bdb0841b03a875aa0ed03b9055f733520d9abc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36996. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Knowledge Graph Embedding models have been extensively used to learn representations of entities and relations in Knowledge Graphs for predicting missing links. However, the quality of the learned representations varies a lot across different areas of the graph. If previous research has loosely linked the problem to relation types or degree bias, we show that it is more widespread and it correlates with the degree imbalance of the entities in test triples. In particular, the prediction of a target entity that has a degree much smaller than the degree of the anchor entity is extremely problematic. This is critical in recommender systems and other use cases, where these triples represent important corner cases. To address this issue, we propose an inference-time latent search optimization method capable of significantly improving model predictions on the most imbalanced triples. Built on top of a pre-trained model, it explores the embedding space at evaluation time, blending known and out-of-band information to mitigate the degree imbalance bias. We show the value of our approach on imbalanced triples from common benchmark datasets, where we outperform conventional methods, opening the door to the successful adoption of Knowledge Graph Embedding models on these critical corner cases.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.36996 — 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 2026-10-07T15:54:53.575Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).