Search Results for author:
Found 8 papers, 4 papers with code
基于知识监督的标签降噪实体对齐(Refined De-noising for Labeled Entity Alignment from Auxiliary Evidence Knowledge)
“大多数现有的实体对齐解决方案都依赖于干净的标记数据来训练模型, 很少关注种子噪声。为了解决实体对齐中的噪声问题, 本文提出了一个标签降噪框架, 在实体对齐中注入辅助知识和附带监督, 以纠正标记和引导过程中的种子错误。特别是, 考虑到以前基于邻域嵌入方法的弱点, 本文应用了一种新的对偶关系注意力匹配编码器来加速知识图谱的结构学习, 同时使用辅助知识来弥补结构表征的不足。然后, 通过对抗训练来执行弱监督标签降噪。对于误差累积的问题, 本文进一步使用对齐精化模块来提高模型的性能。实验结果表明, 所提的框架能够轻松应对含噪声环境下的实体对齐问题, 在多个真实数据集上的对齐准确性和噪声辨别能力始终优于其他基线方法。”
Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge Graphs
Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs).
Ranked #2 on
Entity Alignment
on DICEWS-1K
Incorporating Structured Sentences with Time-enhanced BERT for Fully-inductive Temporal Relation Prediction
In the inductive setting where test TKGs contain emerging entities, the latest methods are based on symbolic rules or pre-trained language models (PLMs).
Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
Firstly, we address the oversimplified heterogeneity settings of current datasets and propose two new HHKG datasets that closely mimic practical EA scenarios.
Meta-Learning Based Knowledge Extrapolation for Temporal Knowledge Graph
Different from KGs and TKGs in the transductive setting, constantly emerging entities and relations in incomplete TKGs create demand to predict missing facts with unseen components, which is the extrapolation setting.
TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph
In addition, our framework extends vector logic on timestamp set to cope with three extra temporal operators (After, Before and Between).
Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs
Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs).
Time-aware Relational Graph Attention Network for Temporal Knowledge Graph Embeddings
Embedding-based representation learning approaches for knowledge graphs (KGs) have been mostly designed for static data.
