LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation

Published in

Conference on Empirical Methods in Natural Lang...(2022)

External Links:

Generate Graph DownloadPDF

TL;DR

It is argued that existing complex EA methods inevitably inherit the inborn defects from their neural network lineage: poor interpretability and weak scalability and a neural-free EA framework is proposed — LightEA, consisting of three efficient components: Random Orthogonal Label Generation, Three-view Label Propagation, and Sparse Sinkhorn Operation.

Abstract

Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step to bridging and integrating multi-source KGs. In this paper, we argue that existing complex EA methods inevitably inherit the inborn defects from their neural network lineage: poor interpretability and weak scalability. Inspired by recent studies, we reinvent the classical Label Propagation algorithm to effectively run on KGs and propose a neural-free EA framework — LightEA, consisting of three efficient components: (i) Random Orthogonal Label Generation, (ii) Three-view Label Propagation, and (iii) Sparse Sinkhorn Operation.According to the extensive experiments on public datasets, LightEA has impressive scalability, robustness, and interpretability. With a mere tenth of time consumption, LightEA achieves comparable results to state-of-the-art methods across all datasets and even surpasses them on many. Besides, due to the computational process of LightEA being entirely linear, we could trace the propagation process at each step and clearly explain how the entities are aligned.

Authors

Wenting Wang

3 papers

Xin Mao

3 papers

Man Lan

3 papers

References41 items

ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities

From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment

LargeEA: Aligning Entities for Large-scale Knowledge Graphs

Make It Easy: An Effective End-to-End Entity Alignment Framework

Boosting the Speed of Entity Alignment 10 ×: Dual Attention Matching Network with Normalized Hard Sample Mining

LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation

Published in

Conference on Empirical Methods in Natural Lang...(2022)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Wenting Wang

3 papers

Xin Mao

3 papers

Man Lan

3 papers

References41 items

TL;DR

Abstract

Authors

References41 items

ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities

From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment

LargeEA: Aligning Entities for Large-scale Knowledge Graphs

Make It Easy: An Effective End-to-End Entity Alignment Framework

Boosting the Speed of Entity Alignment 10 ×: Dual Attention Matching Network with Normalized Hard Sample Mining

TL;DR

Abstract

Authors

References41 items

ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities

From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment

LargeEA: Aligning Entities for Large-scale Knowledge Graphs

Make It Easy: An Effective End-to-End Entity Alignment Framework

Boosting the Speed of Entity Alignment 10 ×: Dual Attention Matching Network with Normalized Hard Sample Mining

Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

Knowledge Association with Hyperbolic Knowledge Graph Embeddings

GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems

Relational Reflection Entity Alignment

An Experimental Study of State-of-the-Art Entity Alignment Approaches

Neighborhood Matching Network for Entity Alignment

A benchmarking study of embedding-based entity alignment for knowledge graphs

Unifying Graph Convolutional Neural Networks and Label Propagation

Retrieval

Deep Graph Matching Consensus

Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment

MRAEA: An Efficient and Robust Entity Alignment Approach for Cross-lingual Knowledge Graph

TransEdge: Translating Relation-Contextualized Embeddings for Knowledge Graphs

Aligning Cross-Lingual Entities with Multi-Aspect Information

Multi-Channel Graph Neural Network for Entity Alignment

Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs

Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

An Efficient Parallel Keyword Search Engine on Knowledge Graphs

Bootstrapping Entity Alignment with Knowledge Graph Embedding

Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

Additive Margin Softmax for Face Verification

Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding

Billion-Scale Similarity Search with GPUs

Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment

Translating Embeddings for Modeling Multi-relational Data

Sinkhorn Distances: Lightspeed Computation of Optimal Transport

YAGO: A Core of Semantic Knowledge Unifying WordNet and Wikipedia

Dimensionality Reduction by Learning an Invariant Mapping

Learning from labeled and unlabeled data with label propagation

An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism

Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks

Product Quantization for Nearest Neighbor Search

An Elementary Introduction to Modern Convex Geometry

On the quadratic assignment problem

Field of Study

Venue Information

Name

Type

URL

Alternate Names