Supervised contrastive learning for product matching

PDF
3487553.3524254.pdf - Veröffentlichte Version
Download (507kB)

DOI:	https://doi.org/10.1145/3487553.3524254
URL:	https://dl.acm.org/doi/abs/10.1145/3487553.3524254
URN:	urn:nbn:de:bsz:180-madoc-626614
Dokumenttyp:	Konferenzveröffentlichung
Erscheinungsjahr:	2022
Buchtitel:	Companion Proceedings of the Web Conference 2022
Seitenbereich:	248-251
Veranstaltungstitel:	WWW '22
Veranstaltungsort:	Lyon, France, Online
Veranstaltungsdatum:	25.-29.04.2022
Herausgeber:	Laforest, Frédérique ; Troncy, Raphaël
Ort der Veröffentlichung:	New York, NY
Verlag:	ACM
ISBN:	978-1-4503-9130-6
Verwandte URLs:	https://dl.acm.org/action/showFmPdf?doi=...
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Information Systems V: Web-based Systems (Bizer 2012-)
Bereits vorhandene Lizenz:	Creative Commons Namensnennung 4.0 International (CC BY 4.0)
Fachgebiet:	004 Informatik
Fachklassifikation:	CCS: Information systems → Entity resolution; Data extraction and integration,
Freie Schlagwörter (Englisch):	e-commerce , product matching , entity matching , contrastive learning , transformers
Abstract:	Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in e-commerce using product offers from different e-shops. More specifically, we employ a supervised contrastive learning technique to pre-train a Transformer encoder which is afterward fine-tuned for the matching task using pair-wise training data. We further propose a source-aware sampling strategy that enables contrastive learning to be applied for use cases in which the training data does not contain product identifiers. We show that applying supervised contrastive pre-training in combination with source-aware sampling significantly improves the state-of-the-art performance on several widely used benchmarks: For Abt-Buy, we reach an F1-score of 94.29 (+3.24 compared to the previous state-of-the-art), for Amazon-Google 79.28 (+ 3.7). For WDC Computers datasets, we reach improvements between +0.8 and +8.84 in F1-score depending on the training set size. Further experiments with data augmentation and self-supervised contrastive pre-training show that the former can be helpful for smaller training sets while the latter leads to a significant decline in performance due to inherent label noise. We thus conclude that contrastive pre-training has a high potential for product matching use cases in which explicit supervision is available.