activity
20192026
most citedHybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

226 citations · 1.2k across the 215 of their papers we have counts for

collaborators
Showing 2022 · cs.AIShow all

10 papers · 2 filters

cs.AI2022★ 5 cited

MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid

Zhuo Chen, Jiaoyan Chen, Wen Zhang +8

Multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs (KGs) whose entities are associated with relevant images. However, current…

cs.AI2022★ 1 cited

Tele-Knowledge Pre-training for Fault Analysis

Zhuo Chen, Wen Zhang, Yufeng Huang +14

In this work, we share our experience on tele-knowledge pre-training for fault analysis, a crucial task in telecommunication applications that requires a wide range of knowledge no…

cs.AI2022★ 7 cited

Relational Message Passing for Fully Inductive Knowledge Graph Completion

Yuxia Geng, Jiaoyan Chen, Jeff Z. Pan +4

In knowledge graph completion (KGC), predicting triples involving emerging entities and/or relations, which are unseen when the KG embeddings are learned, has become a critical cha…

cs.AI2022★ 6 cited

Neural-Symbolic Entangled Framework for Complex Query Answering

Zezhong Xu, Wen Zhang, Peng Ye +2

Answering complex queries over knowledge graphs (KG) is an important yet challenging task because of the KG incompleteness issue and cascading errors during reasoning. Recent query…

cs.AI2022★ 6 cited

Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph

Shumin Deng, Chengming Wang, Zhoubo Li +11

Business Knowledge Graphs (KGs) are important to many enterprises today, providing factual knowledge and structured data that steer many products and make them more intelligent. De…

cs.AI2022

Disentangled Ontology Embedding for Zero-shot Learning

Yuxia Geng, Jiaoyan Chen, Wen Zhang +6

Knowledge Graph (KG) and its variant of ontology have been widely used for knowledge representation, and have shown to be quite effective in augmenting Zero-shot Learning (ZSL). Ho…