Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

Abstract

Multimodal Knowledge Graphs (MKGs), which organize visual-text factual knowledge, have recently been successfully applied to tasks such as information retrieval, question answering, and recommendation system. Since most MKGs are far from complete, extensive knowledge graph completion studies have been proposed focusing on the multimodal entity, relation extraction and link prediction. However, different tasks and modalities require changes to the model architecture, and not all images/objects are relevant to text input, which hinders the applicability to diverse real-world scenarios. In this paper, we propose a hybrid transformer with multi-level fusion to address those issues. Specifically, we leverage a hybrid transformer architecture with unified input-output for diverse multimodal knowledge graph completion tasks. Moreover, we propose multi-level fusion, which integrates visual and text representation via coarse-grained prefix-guided interaction and fine-grained correlation-aware fusion modules. We conduct extensive experiments to validate that our MKGformer can obtain SOTA performance on four datasets of multimodal link prediction, multimodal RE, and multimodal NER. Code is available in https://github.com/zjunlp/MKGformer.

arXiv commentAccepted by SIGIR 2022. Fix a severe bug

References in corpus (12)

• Efficient Estimation of Word Representations in Vector Space
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
• Microsoft COCO Captions: Data Collection and Evaluation Server
• VisualBERT: A Simple and Performant Baseline for Vision and Language
• Complex Embeddings for Simple Link Prediction
• VL-BERT: Pre-training of Generic Visual-Linguistic Representations
• KG-BERT: BERT for Knowledge Graph Completion
• KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
• Towards a Unified View of Parameter-Efficient Transfer Learning
• Knowledge Neurons in Pretrained Transformers
• MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion

Cited by in corpus (6)

• Multi-Modal Knowledge Graph Construction and Application: A Survey
• Enhancing Multimodal Entity and Relation Extraction with Variational Information Bottleneck
• Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph
• MORE: A Multimodal Object-Entity Relation Extraction Dataset with a Benchmark Evaluation
• Towards Multimodal Graph Large Language Model
• Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning