Learning multi-graph structure for Temporal Knowledge Graph reasoning [PDF]
Expert Systems With ApplicationsTemporal Knowledge Graph (TKG) reasoning that forecasts future events based on historical snapshots distributed over timestamps is denoted as extrapolation and has gained significant attention. Owing to its extreme versatility and variation in spatial and temporal correlations, TKG reasoning presents a challenging task, demanding efficient capture of ...
Hui Bei, Ling Tian, Chong Mu
exaly +4 more sources
A contrastive learning framework with dual gates and noise awareness for temporal knowledge graph reasoning [PDF]
Scientific ReportsTemporal knowledge graph reasoning(TKGR) has attracted widespread attention due to its ability to handle dynamic temporal features. However, existing methods face three major challenges: (1) the difficulty of capturing long-distance dependencies in ...
Siling Feng +3 more
doaj +3 more sources
A temporal knowledge graph reasoning model based on recurrent encoding and contrastive learning [PDF]
PeerJ Computer ScienceTemporal knowledge graphs (TKGs) are critical tools for capturing the dynamic nature of facts that evolve over time, making them highly valuable in a broad spectrum of intelligent applications.
Weitong Liu +4 more
doaj +3 more sources
TempReasoner: neural temporal graph networks for event timeline construction [PDF]
Scientific ReportsConstructing event timelines from unstructured temporal data is a fundamental challenge for knowledge extraction and reasoning systems. Existing temporal reasoning methods face challenges in jointly modelling fine-grained temporal dependencies, sparse ...
Mohammed Aldawsari
doaj +2 more sources
Temporal inductive path neural network for temporal knowledge graph reasoning
Artificial IntelligenceAccepted to Artificial ...
Meng Xiao +2 more
exaly +3 more sources
Extrapolation Reasoning on Temporal Knowledge Graphs via Temporal Dependencies Learning
CAAI Transactions on Intelligence TechnologyExtrapolation on Temporal Knowledge Graphs (TKGs) aims to predict future knowledge from a set of historical Knowledge Graphs in chronological order. The temporally adjacent facts in TKGs naturally form event sequences, called event evolution patterns ...
Ye Wang +5 more
doaj +2 more sources
CALENDAR+: in-context contrastive learning for temporal knowledge graph reasoning
Complex & Intelligent SystemsTemporal Knowledge Graph (TKG) reasoning aims to infer future events from historical facts. Recent advances in large language models (LLMs) have shown that in-context learning can effectively enhance temporal reasoning.
Xingyi Li +4 more
doaj +2 more sources
MSEN: A Multi-Scale Evolutionary Network for Modeling the Evolution of Temporal Knowledge Graphs
Future Internet, 2023 Temporal knowledge graphs play an increasingly prominent role in scenarios such as social networks, finance, and smart cities. As such, research on temporal knowledge graphs continues to deepen.
Yong Yu +5 more
doaj +1 more source
Temporal knowledge graph reasoning triggered by memories
Applied Intelligence, 2023 Inferring missing facts in temporal knowledge graphs is a critical task and has been widely explored. Extrapolation in temporal reasoning tasks is more challenging and gradually attracts the attention of researchers since no direct history facts for prediction.
Mengnan Zhao 0001 +3 more
openaire +2 more sources
Recurrent Event Networks Based on Subgraph and Attention Enhancement
IEEE Access, 2023 Temporal knowledge graph (TKG) reasoning, as an essential research direction in natural language processing, focuses on capturing the dynamic changes in entities and relationships over time.
Hongxi Liu, Jiana Meng, Shichang Sun
doaj +1 more source