System improves trustworthiness of images in entity matching
Knowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignment
Computation and LanguageArtificial IntelligenceComputer Vision and Pattern Recognition
Summary
Matching data about the same thing from different sources is hard when images are not reliable or don’t fit well with text. The authors developed a method that checks how trustworthy images are and adjusts their representations to better match text descriptions. This approach helps combine images and words more effectively, making it easier to correctly identify the same entities across sources. Their tests showed that considering image reliability improves matching accuracy.
What this means in practice
- •For data integration teams: Improve the accuracy of matching entries from different databases by using reliable images combined with text descriptions.
- •For e-commerce platform developers: Enhance product matching across listings by filtering and refining image information for better alignment with product details.
Authors
Chenxiao Li, Yunhe Feng, Dongfang Liu, Dong Nie, Yan Huang, Heng Fan
Abstract
The visual modality, i.e., images, plays a key role in multi-modal entity alignment (MMEA). Existing approaches often directly fuse the image with other modalities to align different entities. Although simple, such strategies overlook the potential noise in the images and their semantic misalignment with corresponding entities, resulting in suboptimal fusion and degraded performance. Addressing this, we propose a novel Reliability-Aware framework for MMEA (RA-MMEA), which assesses visual reliability and adaptively improves unreliable visual representations for robust entity alignment. The core lies in two modules, including dependency-aware visual reliability prediction (DA-VRP) and stability-regularized visual embedding generation (SR-VEG). The former aims to estimate the reliability of an image by leveraging multi-modal dependency within the entity, while the latter focuses on producing alternative visual representation conditioned on semantics encoded in textual modalities for multi-modal fusion. Compared to current methods, RA-MMEA enables more reliable visual representations for modality fusion, thereby improving performance. In extensive experiments, RA-MMEA achieves state-of-the-art results, verifying the importance of reliable visual modality for entity alignment and the effectiveness of RA-MMEA. The code and results will be released.