Semi-constraint Optimal Transport for Entity Alignment with Dangling Cases

• URL: http://arxiv.org/abs/2203.05744v1
• Date: Fri, 11 Mar 2022 04:20:18 GMT
• Title: Semi-constraint Optimal Transport for Entity Alignment with Dangling Cases
• Authors: Shengxuan Luo, Pengyu Cheng, Sheng Yu
• Abstract summary: We propose an unsupervised method called Semi-constraint Optimal Transport for Entity Alignment in Dangling cases (SoTead) Our main idea is to model the entity alignment between two KGs as an optimal transport problem from one KG's entities to the others. In the experimental part, we first show the superiority of SoTead on a commonly-used entity alignment dataset.
• Score: 6.755145435406154
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Entity alignment (EA) merges knowledge graphs (KGs) by identifying the equivalent entities in different graphs, which can effectively enrich knowledge representations of KGs. However, in practice, different KGs often include dangling entities whose counterparts cannot be found in the other graph, which limits the performance of EA methods. To improve EA with dangling entities, we propose an unsupervised method called Semi-constraint Optimal Transport for Entity Alignment in Dangling cases (SoTead). Our main idea is to model the entity alignment between two KGs as an optimal transport problem from one KG's entities to the others. First, we set pseudo entity pairs between KGs based on pretrained word embeddings. Then, we conduct contrastive metric learning to obtain the transport cost between each entity pair. Finally, we introduce a virtual entity for each KG to "align" the dangling entities from the other KGs, which relaxes the optimization constraints and leads to a semi-constraint optimal transport. In the experimental part, we first show the superiority of SoTead on a commonly-used entity alignment dataset. Besides, to analyze the ability for dangling entity detection with other baselines, we construct a medical cross-lingual knowledge graph dataset, MedED, where our SoTead also reaches state-of-the-art performance.

Related papers

• Aligning Multiple Knowledge Graphs in a Single Pass [16.396492040719657]
  We propose an effective framework named MultiEA to solve the problem of aligning multiple knowledge graphs. In particular, we propose an innovative inference enhancement technique to improve the alignment performance. The results show that our MultiEA can effectively and efficiently align multiple KGs in a single pass.
  arXiv  Detail & Related papers  (2024-08-01T15:58:05Z)
• Entity Disambiguation via Fusion Entity Decoding [68.77265315142296]
  We propose an encoder-decoder model to disambiguate entities with more detailed entity descriptions. We observe +1.5% improvements in end-to-end entity linking in the GERBIL benchmark compared with EntQA.
  arXiv  Detail & Related papers  (2024-04-02T04:27:54Z)
• Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment [31.70064035432789]
  We propose a Large Language Model-enhanced Entity Alignment framework (LLMEA) LLMEA identifies candidate alignments for a given entity by considering both embedding similarities between entities across Knowledge Graphs and edit distances to a virtual equivalent entity. Experiments conducted on three public datasets reveal that LLMEA surpasses leading baseline models.
  arXiv  Detail & Related papers  (2024-01-30T12:41:04Z)
• A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignment [22.526341223786375]
  In this paper, we introduce FGWEA, an unsupervised entity alignment framework that leverages the Fused Gromov-Wasserstein (FGW) distance. We show that FGWEA surpasses 21 competitive baselines, including cutting-edge supervised entity alignment methods.
  arXiv  Detail & Related papers  (2023-05-11T05:17:54Z)
• Exploiting Global Semantic Similarities in Knowledge Graphs by Relational Prototype Entities [55.952077365016066]
  An empirical observation is that the head and tail entities connected by the same relation often share similar semantic attributes. We propose a novel approach, which introduces a set of virtual nodes called textittextbfrelational prototype entities. By enforcing the entities' embeddings close to their associated prototypes' embeddings, our approach can effectively encourage the global semantic similarities of entities.
  arXiv  Detail & Related papers  (2022-06-16T09:25:33Z)
• Dangling-Aware Entity Alignment with Mixed High-Order Proximities [65.53948800594802]
  dangling-aware entity alignment is an underexplored but important problem in knowledge graphs. We propose a framework using mixed high-order proximities on dangling-aware entity alignment. Our framework more precisely detects dangling entities, and better aligns matchable entities.
  arXiv  Detail & Related papers  (2022-05-05T02:39:55Z)
• ActiveEA: Active Learning for Neural Entity Alignment [31.212894129845093]
  Entity alignment (EA) aims to match equivalent entities across different Knowledge Graphs (KGs) Current mainstream methods -- neural EA models -- rely on training with seed alignment, i.e., a set of pre-aligned entity pairs. We devise a novel Active Learning (AL) framework for neural EA, aiming to create highly informative seed alignment.
  arXiv  Detail & Related papers  (2021-10-13T03:38:04Z)
• Visual Pivoting for (Unsupervised) Entity Alignment [93.82387952905756]
  This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs) We show that the proposed new approach, EVA, creates a holistic entity representation that provides strong signals for cross-graph entity alignment.
  arXiv  Detail & Related papers  (2020-09-28T20:09:40Z)
• Inductive Learning on Commonsense Knowledge Graph Completion [89.72388313527296]
  Commonsense knowledge graph (CKG) is a special type of knowledge graph (CKG) where entities are composed of free-form text. We propose to study the inductive learning setting for CKG completion where unseen entities may present at test time. InductivE significantly outperforms state-of-the-art baselines in both standard and inductive settings on ATOMIC and ConceptNet benchmarks.
  arXiv  Detail & Related papers  (2020-09-19T16:10:26Z)
• Cross-lingual Entity Alignment with Incidental Supervision [76.66793175159192]
  We propose an incidentally supervised model, JEANS, which jointly represents multilingual KGs and text corpora in a shared embedding scheme. Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision.
  arXiv  Detail & Related papers  (2020-05-01T01:53:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.