Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
This work addresses the problem of inflexible model architectures for multimodal knowledge graph completion, which is incremental as it builds on existing transformer-based methods to improve applicability in real-world scenarios like information retrieval and recommendation systems.
The paper tackles the challenge of adapting multimodal knowledge graph completion models to diverse tasks and modalities by proposing a hybrid transformer with multi-level fusion, achieving state-of-the-art performance on four datasets for tasks like multimodal link prediction, relation extraction, and named entity recognition.
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.