2023年5月15日 · Current Multimodal Knowledge Graph Construction (MKGC) models struggle with the real-world dynamism of continuously emerging entities and relations, often succumbing to catastrophic forgetting-loss of previously acquired knowledge. This study introduces benchmarks aimed at fostering the development of the continual MKGC domain.

2024年10月7日 · 多模态知识图构建（mkgc）涉及使用多种模态（例如文本和图像）创建实体和关系的结构化表示。 然而，现有的 MKGC 模型在处理动态现实场景中添加新实体和关系时面临挑战。

2022年10月17日 · In this paper, we propose MoSE, a Modality Split representation learning and Ensemble inference framework for MKGC. Specifically, in the training phase, we learn modality-split relation embeddings for each modality instead of a single modality-shared one, which alleviates the modality interference.

如下图所示，本文提出的MKGformer模型具有统一的多模态KGC框架。 主要包括混合 Transformer 架构和特定任务范式。 具体来说，MKGformer分别采用 ViT 和 BERT 作为视觉Transformer和文本Transformer模型，并在最后 层Transformer中对实体的多模态表示进行建模。 文本端Bert输入格式如下所示，其中Mask为掩码的尾实体. 关系提取旨在将文本中提到的关系链接到知识图谱中的关系类型。 给定文本T和相应的图像I，旨在预测实体对 (e_h, e_t) 之间的关系，并将关系类型的分 …

2024年10月19日 · mkgc的目标是预测候选三元组对mkg正确的概率。该方法可应用于基于信号的轴承故障mkg进行故障诊断。现有的技术目前忽略了不同阶域的不同重要性。提出了一种基于rcgat模型的方法来解决这一问题。故障诊断流程图如图4所示。 图4 基于mkgc的故障诊断流程图

Code and dataset for IJCAI 2024 paper Continual Multimodal Knowledge Graph Construction. 1. Overview. Please note "we provide". This is the data set of lifelong benchmark provided by us.

2024年6月26日 · Multilingual Knowledge Graph Completion (mKGC) aim at solving queries like (h, r, ?) in different languages by reasoning a tail entity t thus improving multilingual knowledge graphs. Previous studies leverage multilingual pretrained language models (PLMs) and the generative paradigm to achieve mKGC.

In this work, we introduce a Unified Multi-Modal Knowledge Graph (MMKG) Representation Framework that incorporates tailored training objectives for Multi-modal Knowledge Graph Completion (MKGC) and Multi-modal Entity Alignment (MMEA). Our approach achieves SOTA performance across a comprehensive suite of ten datasets, including three for MKGC ...

To address the aforementioned challenges, we proposed a novel model named SCI-MKGC, which is a MKGC method based on spatial context enhancement and cross-modal interaction attention. In this paper, the spatial context enhancement module is proposed to enhance the central entity through aggregating neighborhood attributes.

2020年6月25日 · To tackle this challenging problem, this article proposes a new MKGC method to learn a consensus affinity graph directly. By using the self-expressiveness graph learning and an adaptive local structure learning term, the local manifold structure of the data in kernel space is preserved for learning multiple candidate affinity graphs from a ...