mlsanityData to 7 Oct 2026

Modality-Aware Negative Sampling for Multi-modal Knowledge Graph Embedding

arXiv 2304.11618 ↗First posted 23 Apr 2023cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 23 Apr 2023.

Builds on

23 of 36 references.

References · 23

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  3. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  4. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  5. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  6. 2019K-BERT: Enabling Language Representation with Knowledge Graphcited by 303
  7. 2019MMKG: Multi-Modal Knowledge Graphscited by 104
  8. 2017Knowledge Graph Completion via Complex Tensor Factorizationcited by 80
  9. 2021ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphscited by 78
  10. 2016Image-embodied Knowledge Representation Learningcited by 68
  11. 2019Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoningcited by 63
  12. 2017KBGAN: Adversarial Learning for Knowledge Graph Embeddingscited by 62
11 more
  1. 2018NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embeddingcited by 42
  2. 2018Embedding Multimodal Relational Data for Knowledge Base Completioncited by 34
  3. 2018Incorporating GAN for Negative Sampling in Knowledge Representation Learningcited by 31
  4. 2020Structure Aware Negative Sampling in Knowledge Graphscited by 26
  5. 2022Knowledge Graph Completion with Pre-trained Multimodal Transformer and Twins Negative Samplingcited by 18
  6. 2022Tele-Knowledge Pre-training for Fault Analysiscited by 18
  7. 2021Efficient Non-Sampling Knowledge Graph Embeddingcited by 14
  8. 2021Billion-scale Pre-trained E-commerce Product Knowledge Graph Modelcited by 13
  9. 2022CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completioncited by 13
  10. 2022Entity Aware Negative Sampling with Auxiliary Loss of False Negative Prediction for Knowledge Graph Embeddingcited by 4
  11. 2023Analogical Inference Enhanced Knowledge Graph Embeddingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 1.

7 papers.

  1. 2024Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Surveycited by 50
  2. 2024Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learningcited by 13
  3. 2024Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completioncited by 10
  4. 2025Diffusion-based Hierarchical Negative Sampling for Multimodal Knowledge Graph Completioncited by 1
  5. 2025Complementarity-driven Representation Learning for Multi-modal Knowledge Graph Completioncited by 1
  6. 2025PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linkingcited by 0
  7. 2026Every Little Helps: Building Knowledge Graph Foundation Model with Fine-grained Transferable Multi-modal Tokenscited by 0