Entity Alignment with Unlabeled Dangling Cases

• URL: http://arxiv.org/abs/2403.10978v1
• Date: Sat, 16 Mar 2024 17:21:58 GMT
• Title: Entity Alignment with Unlabeled Dangling Cases
• Authors: Hang Yin, Dong Ding, Liyao Xiang, Yuheng He, Yihan Wu, Xinbing Wang, Chenghu Zhou,
• Abstract summary: We propose a novel GNN-based dangling detection and entity alignment framework. While the two tasks share the same GNN, the detected dangling entities are removed in the alignment. Our framework is featured by a designed entity and relation attention mechanism for selective neighborhood aggregation in representation learning.
• Score: 49.86384156476041
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate the entity alignment problem with unlabeled dangling cases, meaning that there are entities in the source or target graph having no counterparts in the other, and those entities remain unlabeled. The problem arises when the source and target graphs are of different scales, and it is much cheaper to label the matchable pairs than the dangling entities. To solve the issue, we propose a novel GNN-based dangling detection and entity alignment framework. While the two tasks share the same GNN and are trained together, the detected dangling entities are removed in the alignment. Our framework is featured by a designed entity and relation attention mechanism for selective neighborhood aggregation in representation learning, as well as a positive-unlabeled learning loss for an unbiased estimation of dangling entities. Experimental results have shown that each component of our design contributes to the overall alignment performance which is comparable or superior to baselines, even if the baselines additionally have 30\% of the dangling entities labeled as training data.

Related papers

• SEG:Seeds-Enhanced Iterative Refinement Graph Neural Network for Entity Alignment [13.487673375206276]
  This paper presents a soft label propagation framework that integrates multi-source data and iterative seed enhancement. A bidirectional weighted joint loss function is implemented, which reduces the distance between positive samples and differentially processes negative samples. Our method outperforms existing semi-supervised approaches, as evidenced by superior results on multiple datasets.
  arXiv  Detail & Related papers  (2024-10-28T04:50:46Z)
• 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)
• Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding [29.81122170002021]
  We propose a scalable GNN-based entity alignment approach to reduce the structure and alignment loss from three perspectives. First, we propose a centrality-based subgraph generation algorithm to recall some landmark entities serving as the bridges between different subgraphs. Second, we introduce self-supervised entity reconstruction to recover entity representations from incomplete neighborhood subgraphs. Third, during the inference process, we merge the embeddings of subgraphs to make a single space for alignment search.
  arXiv  Detail & Related papers  (2022-08-23T07:09:59Z)
• 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)
• 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)
• Towards Entity Alignment in the Open World: An Unsupervised Approach [29.337157862514204]
  It is a pivotal step for integrating knowledge graphs (KGs) to increase knowledge coverage and quality. State-of-the-art solutions tend to rely on labeled data for model training. We offer an unsupervised framework that performs entity alignment in the open world.
  arXiv  Detail & Related papers  (2021-01-26T03:10:24Z)
• Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition [47.273602658066196]
  In many scenarios, named entity recognition models severely suffer from unlabeled entity problem. We propose a general approach, which can almost eliminate the misguidance brought by unlabeled entities. Our model is robust to unlabeled entity problem and surpasses prior baselines.
  arXiv  Detail & Related papers  (2020-12-10T02:53:59Z)
• Autoregressive Entity Retrieval [55.38027440347138]
  Entities are at the center of how we represent and aggregate knowledge. The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. We propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion.
  arXiv  Detail & Related papers  (2020-10-02T10:13:31Z)
• 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)

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.