Dangling-Aware Entity Alignment with Mixed High-Order Proximities

• URL: http://arxiv.org/abs/2205.02406v1
• Date: Thu, 5 May 2022 02:39:55 GMT
• Title: Dangling-Aware Entity Alignment with Mixed High-Order Proximities
• Authors: Juncheng Liu, Zequn Sun, Bryan Hooi, Yiwei Wang, Dayiheng Liu, Baosong Yang, Xiaokui Xiao, Muhao Chen
• Abstract summary: 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.
• Score: 65.53948800594802
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study dangling-aware entity alignment in knowledge graphs (KGs), which is an underexplored but important problem. As different KGs are naturally constructed by different sets of entities, a KG commonly contains some dangling entities that cannot find counterparts in other KGs. Therefore, dangling-aware entity alignment is more realistic than the conventional entity alignment where prior studies simply ignore dangling entities. We propose a framework using mixed high-order proximities on dangling-aware entity alignment. Our framework utilizes both the local high-order proximity in a nearest neighbor subgraph and the global high-order proximity in an embedding space for both dangling detection and entity alignment. Extensive experiments with two evaluation settings shows that our framework more precisely detects dangling entities, and better aligns matchable entities. Further investigations demonstrate that our framework can mitigate the hubness problem on dangling-aware entity alignment.

Related papers

• Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases [49.86384156476041]
  We propose the framework textitLambda for dangling detection and entity alignment. Lambda features a GNN-based encoder called KEESA with spectral contrastive learning for EA and a positive-unlabeled learning algorithm for dangling detection called iPULE.
  arXiv  Detail & Related papers  (2024-03-16T17:21:58Z)
• 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)
• EventEA: Benchmarking Entity Alignment for Event-centric Knowledge Graphs [17.27027602556303]
  We show that the progress made in the past was due to biased and unchallenging evaluation. We construct a new dataset with heterogeneous relations and attributes based on event-centric KGs. As a new approach to this difficult problem, we propose a time-aware literal encoder for entity alignment.
  arXiv  Detail & Related papers  (2022-11-05T05:34:21Z)
• Facing Changes: Continual Entity Alignment for Growing Knowledge Graphs [22.88552158340435]
  We propose and dive into a realistic yet unexplored setting, referred to as continual entity alignment. It reconstructs an entity's representation based on entity adjacency, enabling it to generate embeddings for new entities quickly. It selects and replays partial pre-aligned entity pairs to train only parts of KGs while extracting trustworthy alignment for knowledge augmentation.
  arXiv  Detail & Related papers  (2022-07-23T06:52:44Z)
• Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment [69.41986652911143]
  We propose a novel self-supervised adaptive graph alignment (SS-AGA) method to predict missing facts in a knowledge graph (KG) SS-AGA fuses all KGs as a whole graph by regarding alignment as a new edge type. Experiments on the public multilingual DBPedia KG and newly-created industrial multilingual E-commerce KG empirically demonstrate the effectiveness of SS-AGA.
  arXiv  Detail & Related papers  (2022-03-28T18:00:51Z)
• Semi-constraint Optimal Transport for Entity Alignment with Dangling Cases [6.755145435406154]
  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.
  arXiv  Detail & Related papers  (2022-03-11T04:20:18Z)
• Knowing the No-match: Entity Alignment with Dangling Cases [22.909706377522614]
  This paper studies a new problem setting of entity alignment for knowledge graphs (KGs) Since KGs possess different sets of entities, there could be entities that cannot find alignment across them, leading to the problem of dangling entities. We construct a new dataset and design a multi-task learning framework for both entity alignment and dangling entity detection.
  arXiv  Detail & Related papers  (2021-06-04T04:28:36Z)
• 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)
• Neighborhood Matching Network for Entity Alignment [71.24217694278616]
  Neighborhood Matching Network (NMN) is a novel entity alignment framework. NMN estimates the similarities between entities to capture both the topological structure and the neighborhood difference. It first uses a novel graph sampling method to distill a discriminative neighborhood for each entity. It then adopts a cross-graph neighborhood matching module to jointly encode the neighborhood difference for a given entity pair.
  arXiv  Detail & Related papers  (2020-05-12T08:26:15Z)
• 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.