Pseudo-Label Calibration Semi-supervised Multi-Modal Entity Alignment

arXiv:2403.01203v1 Announce Type: new
Abstract: Multi-modal entity alignment (MMEA) aims to identify equivalent entities between two multi-modal knowledge graphs for integration. Unfortunately, prior arts have attempted to improve the interaction and fusion of multi-modal information, which have overlooked the influence of modal-specific noise and the usage of labeled and unlabeled data in semi-supervised settings. In this work, we introduce a Pseudo-label Calibration Multi-modal Entity Alignment (PCMEA) in a semi-supervised way. Specifically, in order to generate holistic entity representations, we first …

abstract alignment arts arxiv cs.cl cs.db cs.lg data fusion graphs identify influence information integration knowledge knowledge graphs modal multi-modal noise prior semi-supervised type usage