A Zero-shot Learning Method Based on Large Language Models for Multi-modal Knowledge Graph Embedding
This addresses the challenge of handling unseen categories in open-domain scenarios for applications like natural language processing and image classification, representing an incremental improvement.
The paper tackled the problem of zero-shot learning for multi-modal knowledge graph embedding by proposing ZSLLM, a framework that uses large language models to transfer semantic information across modalities for unseen categories, achieving superior performance compared to state-of-the-art methods on multiple real-world datasets.
Zero-shot learning (ZL) is crucial for tasks involving unseen categories, such as natural language processing, image classification, and cross-lingual transfer.Current applications often fail to accurately infer and handle new relations orentities involving unseen categories, severely limiting their scalability and prac-ticality in open-domain scenarios. ZL learning faces the challenge of effectivelytransferring semantic information of unseen categories in multi-modal knowledgegraph (MMKG) embedding representation learning. In this paper, we proposeZSLLM, a framework for zero-shot embedding learning of MMKGs using largelanguage models (LLMs). We leverage textual modality information of unseencategories as prompts to fully utilize the reasoning capabilities of LLMs, enablingsemantic information transfer across different modalities for unseen categories.Through model-based learning, the embedding representation of unseen cate-gories in MMKG is enhanced. Extensive experiments conducted on multiplereal-world datasets demonstrate the superiority of our approach compared tostate-of-the-art methods.