Spatial-Temporal Attention Network for Temporal Knowledge Graph Completion

Zhang, Jiasheng; Liang, Shuang; Deng, Zhiyi; Shao, Jie

doi:10.1007/978-3-030-73194-6_15

Cited by 11 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Static knowledge graph methods include TransE [27], DisMult [42], Com-plEx [5], SimplE [43]. TKG methods are divided into geometric methods (TTransE [1], HyTE [2], TeRo [31], ChronoR [7], BoxTE [8], TLT-KGE [9], RotateQVS [10], HTTR [11], PTKE [12], TGeomE [44]); tensor decomposition methods (TNTComplEx [6], TuckERTNT [33], QDN [13], TBDRI [14]); deep learning and embedding-based methods (TeMP-SA [3], DE-Simple [4], TeLM [45], TASTER [15], TeAST [16], RoAN [17], BiQ-Cap [18]); and graph neural network based-reasoning methods (TARGCN [19], T-GAP [20], TAL-TKGC [21]).…”

Section: Baseline Modelsmentioning

confidence: 99%

“…To address this issue, various temporal knowledge graph embedding (KGE) models are proposed to encode entities and relations in a low-dimensional space using translation-based functions [1,2], a deep neural networkbased method [3,4], and a tensor decomposition method [5,6]. As these methodologies have progressed, numerous strategies for TKG completion have been proposed, including geometric methods (ChronoR [7], BoxTE [8], TLT-KGE [9], RotateQVS [10], HTTR [11], PTKE [12]); tensor decomposition methods (QDN [13], TBDRI [14]); deep learning and embedding-based methods (TASTER [15], TeAST [16], RoAN [17], BiQCap [18]); and graph neural network-based reasoning methods (TARGCN [19], T-GAP [20], TAL-TKGC [21]). Interpolation is a statistical method that utilizes the relevant known values to estimate an unknown value or set [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-View Temporal Knowledge Graph Reasoning Framework with Interpretable Logic Rules and Feature Fusion

Xu,

Bao,

et al. 2024

Electronics

View full text Add to dashboard Cite

A temporal knowledge graph represents temporal information between entities in a multi-relational graph. Its reasoning aims to infer and predict potential links among entities. Predicting time-aware entities is a challenging task due to significant differences in entity appearances over time, such as different timestamps and frequencies. Current embedding-based similarity-matching methods have been introduced for predicting temporal facts. However, they lack deterministic logical explainability and cannot model the dynamic evolution of entities over time. To address these challenges, we propose a novel framework for temporal knowledge graph reasoning based on multi-view feature fusion (MVFF). First, MVFF extracts logical rules and uses the Gumbel-Softmax trick to sample high-quality rules. Second, it integrates logical rules, temporal quadruples, and factual triples to capture semantic features, temporal information, and structural information to solve link prediction tasks. Through experiments on four benchmark datasets, we show that MVFF outperforms state-of-the-art methods, providing not only better performance but also interpretable results.

show abstract

Section: Baseline Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Multi-View Temporal Knowledge Graph Reasoning Framework with Interpretable Logic Rules and Feature Fusion

Xu,

Bao,

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…KG is a hot research area, and several public and commercial solutions have recently leveraged its semantic power fantastically. For instance, KG completion and reasoning via link prediction, neighborhood prediction, and community detection have been explored [6], [16], [17]. To provide a snapshot of the current state of the art, we highlight relevant work in this section, focusing on KG completion, modeling, explainability, and representation.…”

Section: ) Knowledge Graph Reasoning and Representationmentioning

confidence: 99%

“…Reference [5] proposed a deep learning model for symbolic representation and explainability, validated for cultural heritage use cases. A survey by [16] discussed present and future perspectives for symbolic KG reasoning, including related technologies.…”

Section: ) Knowledge Graph Representation and Reasoning (Symbolic)mentioning

confidence: 99%

See 1 more Smart Citation

A Network Analysis-Driven Framework for Factual Explainability of Knowledge Graphs

Munir,

Malick,

Ferretti

2024

IEEE Access

View full text Add to dashboard Cite

Knowledge Graphs are widely used to represent knowledge structures in complex domains. In most real-world scenarios, these knowledge structures are dynamic. As a result, measures must be developed to assess the robustness and usability of Knowledge Graphs in temporal settings. Additionally, the explainability of inherent knowledge constituents is crucial for the desired attention of Knowledge Graphs, particularly in temporal settings. In this paper, we developed a framework to understand the robustness of factual explainability of Knowledge Graphs. The method is further verified by using meso-level attributes of the knowledge graph. The complex network analysis along with the community structures are co-evaluated through homophilic and heterophilic properties within the graph to validate the robustness of the factual interpretations. The analysis reveals that symbolic representation could be used as a reasonable metric for extracting link-based communities.INDEX TERMS Knowledge graph analysis, complex network analysis, homophily and heterophily analysis, factual reasoning and explainability, interpretability.

show abstract

On Glocal Explainability of Graph Neural Networks

Chen

Cao

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Spatial-Temporal Attention Network for Temporal Knowledge Graph Completion

Cited by 11 publications

References 21 publications

A Multi-View Temporal Knowledge Graph Reasoning Framework with Interpretable Logic Rules and Feature Fusion

A Multi-View Temporal Knowledge Graph Reasoning Framework with Interpretable Logic Rules and Feature Fusion

A Network Analysis-Driven Framework for Factual Explainability of Knowledge Graphs

On Glocal Explainability of Graph Neural Networks

Contact Info

Product

Resources

About