TL;DR
This paper introduces DivEA, a framework for dividing large-scale entity alignment tasks into high-quality subtasks, improving efficiency and effectiveness by leveraging a novel counterpart discovery method and evidence passing mechanism.
Contribution
DivEA presents a new task division framework that maintains high coverage of potential mappings and balances subtask sizes, enhancing large-scale entity alignment performance.
Findings
DivEA outperforms state-of-the-art methods in large-scale EA tasks.
The framework effectively balances subtask sizes with high mapping coverage.
Experimental results demonstrate improved alignment accuracy.
Abstract
Entity Alignment (EA) aims to match equivalent entities that refer to the same real-world objects and is a key step for Knowledge Graph (KG) fusion. Most neural EA models cannot be applied to large-scale real-life KGs due to their excessive consumption of GPU memory and time. One promising solution is to divide a large EA task into several subtasks such that each subtask only needs to match two small subgraphs of the original KGs. However, it is challenging to divide the EA task without losing effectiveness. Existing methods display low coverage of potential mappings, insufficient evidence in context graphs, and largely differing subtask sizes. In this work, we design the DivEA framework for large-scale EA with high-quality task division. To include in the EA subtasks a high proportion of the potential mappings originally present in the large EA task, we devise a counterpart discovery…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
