EUVIMEDEUVIMED entdecken
Crossref

BEACON: Budget-Aware Entity Matching Across Domains

Nicholas Pulsone, Roee Shraga, Gregory Goren

Proceedings of the ACM on Management of Data · 18.05.2026 · 4 (3) · 1-26

DOI: 10.1145/3802021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 18.05.2026. Verfasst von Nicholas Pulsone und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Entity Matching (EM)--the task of determining whether two data records refer to the same real-world entity--is a core task in data integration. Recent advances in deep learning have set a new standard for EM, particularly through fine-tuning Pretrained Language Models (PLMs) and, more recently, Large Language Models (LLMs). However, fine-tuning typically requires large amounts of labeled data, which are expensive and time-consuming to obtain. In the context of e-commerce matching, labeling scarcity varies widely across domains, raising the question of how to intelligently train accurate domain-specific EM models with limited labeled data. In this work we assume users have only a limited amount of labels for a specific target domain but have access to labeled data from other domains. We introduce BEACON, a distribution-aware, budget-aware framework for low-resource EM across domains. BEACON leverages the insight that embedding representations of pairwise candidate matches can guide the effective selection of out-of-domain samples under limited in-domain supervision. We conduct extensive experiments across multiple domain-partitioned datasets derived from established EM benchmarks, demonstrating that BEACON consistently outperforms state-of-the-art methods under different training budgets.

Förderung

  • National Science Foundation

Zitieren

APA

Pulsone, N., Shraga, R., & Goren, G. (2026). BEACON: Budget-Aware Entity Matching Across Domains. Proceedings of the ACM on Management of Data, 4(3), 1-26. https://doi.org/10.1145/3802021

Vancouver

Pulsone N, Shraga R, Goren G. BEACON: Budget-Aware Entity Matching Across Domains. Proceedings of the ACM on Management of Data. 2026;4(3):1-26. doi:10.1145/3802021

BibTeX
@article{Pulsone2026,
  author = {Pulsone, Nicholas and Shraga, Roee and Goren, Gregory},
  title = {BEACON: Budget-Aware Entity Matching Across Domains},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2026},
  volume = {4},
  number = {3},
  pages = {1--26},
  doi = {10.1145/3802021}
}
Kostenlos starten →