Generating Explanations to Understand and Repair Embedding-based Entity Alignment
- URL: http://arxiv.org/abs/2312.04877v3
- Date: Thu, 21 Mar 2024 07:22:54 GMT
- Title: Generating Explanations to Understand and Repair Embedding-based Entity Alignment
- Authors: Xiaobin Tian, Zequn Sun, Wei Hu,
- Abstract summary: We present the first framework that can generate explanations for understanding and repairing embedding-based EA results.
Given an EA pair produced by an embedding model, we first compare its neighbor entities and relations to build a matching subgraph as a local explanation.
We then construct an alignment dependency graph to understand the pair from an abstract perspective.
- Score: 15.608451451547067
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Entity alignment (EA) seeks identical entities in different knowledge graphs, which is a long-standing task in the database research. Recent work leverages deep learning to embed entities in vector space and align them via nearest neighbor search. Although embedding-based EA has gained marked success in recent years, it lacks explanations for alignment decisions. In this paper, we present the first framework that can generate explanations for understanding and repairing embedding-based EA results. Given an EA pair produced by an embedding model, we first compare its neighbor entities and relations to build a matching subgraph as a local explanation. We then construct an alignment dependency graph to understand the pair from an abstract perspective. Finally, we repair the pair by resolving three types of alignment conflicts based on dependency graphs. Experiments on a variety of EA datasets demonstrate the effectiveness, generalization, and robustness of our framework in explaining and repairing embedding-based EA results.
Related papers
- Entity Alignment with Unlabeled Dangling Cases [49.86384156476041]
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.
arXiv Detail & Related papers (2024-03-16T17:21:58Z) - ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment [15.527373618633847]
We propose the Align-Subgraph Entity Alignment (ASGEA) framework to exploit logic rules from Align-Subgraphs.
We also design an interpretable Path-based Graph Neural Network, ASGNN, to effectively identify and integrate the logic rules across KGs.
Our experimental results demonstrate the superior performance of ASGEA over the existing embedding-based methods in both EA and Multi-Modal EA (MMEA) tasks.
arXiv Detail & Related papers (2024-02-16T17:03:05Z) - What Makes Entities Similar? A Similarity Flooding Perspective for
Multi-sourced Knowledge Graph Embeddings [20.100378168629195]
We provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models.
We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities.
arXiv Detail & Related papers (2023-06-05T06:50:09Z) - Learnable Pillar-based Re-ranking for Image-Text Retrieval [119.9979224297237]
Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities.
Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks.
We propose a novel learnable pillar-based re-ranking paradigm for image-text retrieval.
arXiv Detail & Related papers (2023-04-25T04:33:27Z) - 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) - Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner [56.08919422452905]
We propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR)
Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises.
We outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.
arXiv Detail & Related papers (2022-05-18T21:52:11Z) - Entity Alignment For Knowledge Graphs: Progress, Challenges, and
Empirical Studies [4.221619479687067]
Entity alignment (EA) identifies entities across databases that refer to the same entity.
EA methods map entities to a low-dimension space and align them based on their similarities.
This paper presents a comprehensive analysis of various existing EA methods, elaborating their applications and limitations.
arXiv Detail & Related papers (2022-05-18T07:59:03Z) - ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs [73.86041481470261]
Cone Embeddings (ConE) is the first geometry-based query embedding model that can handle conjunction, disjunction, and negation.
ConE significantly outperforms existing state-of-the-art methods on benchmark datasets.
arXiv Detail & Related papers (2021-10-26T14:04:02Z) - Exploring and Evaluating Attributes, Values, and Structures for Entity
Alignment [100.19568734815732]
Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs.
attribute triples can also provide crucial alignment signal but have not been well explored yet.
We propose to utilize an attributed value encoder and partition the KG into subgraphs to model the various types of attribute triples efficiently.
arXiv Detail & Related papers (2020-10-07T08:03:58Z) - HittER: Hierarchical Transformers for Knowledge Graph Embeddings [85.93509934018499]
We propose Hitt to learn representations of entities and relations in a complex knowledge graph.
Experimental results show that Hitt achieves new state-of-the-art results on multiple link prediction.
We additionally propose a simple approach to integrate Hitt into BERT and demonstrate its effectiveness on two Freebase factoid answering datasets.
arXiv Detail & Related papers (2020-08-28T18:58:15Z)
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.