Repository logo

Visual Pivoting for (Unsupervised) Entity Alignment

Accepted version


Conference Object

Change log


Chen, M 
Roth, D 


This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs). Images are natural components of many existing KGs. By combining visual knowledge with other auxiliary information, we show that the proposed new approach, EVA, creates a holistic entity representation that provides strong signals for cross-graph entity alignment. Besides, previous entity alignment methods require human labelled seed alignment, restricting availability. EVA provides a completely unsupervised solution by leveraging the visual similarity of entities to create an initial seed dictionary (visual pivots). Experiments on benchmark data sets DBP15k and DWY15k show that EVA offers state-of-the-art performance on both monolingual and cross-lingual entity alignment tasks. Furthermore, we discover that images are particularly useful to align long-tail KG entities, which inherently lack the structural contexts necessary for capturing the correspondences.



cs.CL, cs.CL, cs.AI

Journal Title

35th AAAI Conference on Artificial Intelligence, AAAI 2021

Conference Name

The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)

Journal ISSN


Volume Title



Publisher DOI

Publisher URL

Fangyu Liu is supported by Grace & Thomas C.H. Chan Cambridge Scholarship. This research is supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA Contract No. 2019- 19051600006 under the BETTER Program, and by Contracts HR0011-18-2-0052 and FA8750-19-2-1004 with the US Defence Advanced Research Projects Agency (DARPA).