Modality-Aware Negative Sampling for Multi-modal Knowledge Graph Embedding (2023-04-23T00:00:00.000000Z)

TL;DR

Modality-Aware Negative Sampling (MANS) for multi-modal knowledge graph embedding (MMKGE) is proposed to address the mentioned problems and empirical results demonstrate that MANS outperforms existing NS methods.

Abstract

Negative sampling (NS) is widely used in knowledge graph embedding (KGE), which aims to generate negative triples to make a positive-negative contrast during training. However, existing NS methods are unsuitable when multi-modal information is considered in KGE models. They are also inefficient due to their complex design. In this paper, we propose Modality-Aware Negative Sampling (MANS) for multi-modal knowledge graph embedding (MMKGE) to address the mentioned problems. MANS could align structural and visual embeddings for entities in KGs and learn meaningful embeddings to perform better in multi-modal KGE while keeping lightweight and efficient. Empirical results on two benchmarks demonstrate that MANS outperforms existing NS methods. Meanwhile, we make further explorations about MANS to confirm its effectiveness.

Authors

Mingyang Chen

4 papers

Yichi Zhang

3 papers

Wen Zhang

9 papers

TL;DR

Abstract

Authors

References36 items

Analogical Inference Enhanced Knowledge Graph Embedding

Tele-Knowledge Pre-training for Fault Analysis

Entity Aware Negative Sampling with Auxiliary Loss of False Negative Prediction for Knowledge Graph Embedding

Knowledge Graph Completion with Pre-trained Multimodal Transformer and Twins Negative Sampling

CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Is Visual Context Really Helpful for Knowledge Graph? A Representation Learning Perspective

Efficient Non-Sampling Knowledge Graph Embedding

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

Billion-scale Pre-trained E-commerce Product Knowledge Graph Model

Structure Aware Negative Sampling in Knowledge Graphs

K-BERT: Enabling Language Representation with Knowledge Graph

Multimodal Data Enhanced Representation Learning for Knowledge Graphs

Adaptive Convolution for Multi-Relational Learning

Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning

MMKG: Multi-Modal Knowledge Graphs

NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding

RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Embedding Multimodal Relational Data for Knowledge Base Completion

Incorporating GAN for Negative Sampling in Knowledge Representation Learning

A Multimodal Translation-Based Approach for Knowledge Graph Representation Learning

Knowledge Graph Embedding: A Survey of Approaches and Applications

KBGAN: Adversarial Learning for Knowledge Graph Embeddings

Convolutional 2D Knowledge Graph Embeddings

Knowledge Graph Completion via Complex Tensor Factorization

Image-embodied Knowledge Representation Learning

Embedding Entities and Relations for Learning and Inference in Knowledge Bases

GloVe: Global Vectors for Word Representation

Very Deep Convolutional Networks for Large-Scale Image Recognition

Knowledge Graph Embedding by Translating on Hyperplanes

Translating Embeddings for Modeling Multi-relational Data

Understanding the difficulty of training deep feedforward neural networks

Freebase: a collaboratively created graph database for structuring human knowledge

DBpedia: A Nucleus for a Web of Open Data

GENERATIVE ADVERSARIAL NETS

license agreement with IEEE. Restrictions apply

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names