Lune

EMNLP Findings2023

Towards Enhancing Relational Rules for Knowledge Graph Link Prediction

Shuhan Wu, Huaiyu Wan, Wei Chen, Yuting Wu, Junfeng Shen, Youfang Lin

摘要

Graph neural networks (GNNs) have shown promising performance for knowledge graph reasoning. A recent variant of GNN called progressive relational graph neural network (PRGNN), utilizes relational rules to infer missing knowledge in relational digraphs and achieves notable results. However, during reasoning with PRGNN, two important properties are often overlooked: (1) the sequentiality of relation composition, where the order of combining different relations affects the semantics of the relational rules, and (2) the lagged entity information propagation, where the transmission speed of required information lags behind the appearance speed of new entities. Ignoring these properties leads to incorrect relational rule learning and decreased reasoning accuracy. To address these issues, we propose a novel knowledge graph reasoning approach, the Relational rUle eNhanced Graph Neural Network (RUN-GNN). Specifically, RUN-GNN employs a query related fusion gate unit to model the sequentiality of relation composition and utilizes a buffering update mechanism to alleviate the negative effect of lagged entity information propagation, resulting in higher-quality relational rule learning. Experimental results on multiple datasets demonstrate the superiority of RUN-GNN is superior on both transductive and inductive link prediction tasks.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

已有 4 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。

可以从这些问题问起

Lune 可以查阅

全文 · 引用它的顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning 引用了 Spatial-Temporal Knowledge Distillation for Takeaway Recommendation
  • TIGER: Training Inductive Graph Neural Network for Large-scale Knowledge Graph Reasoning 引用了 Inductive Relation Prediction by Subgraph Reasoning
  • TIGER: Training Inductive Graph Neural Network for Large-scale Knowledge Graph Reasoning 引用了 Composition-based Multi-Relational Graph Convolutional Networks
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

引用它的顶会 Paper4

  1. A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph ReasoningZhiyu Zhang, Wei Chen, Youfang Lin, Huaiyu WanACL 2025 · 4 次引用
  2. CognTKE: A Cognitive Temporal Knowledge Extrapolation FrameworkWei Chen, Yuting Wu, Shuhan Wu, Zhiyu Zhang 等AAAI 2025 · 3 次引用
  3. TIGER: Training Inductive Graph Neural Network for Large-scale Knowledge Graph ReasoningKai Wang, Yuwei Xu, Siqiang LuoVLDB 2024 · 3 次引用
  4. Spatial-Temporal Knowledge Distillation for Takeaway RecommendationShuyuan Zhao, Wei Chen, Boyan Shi, Liyong Zhou 等AAAI 2025 · 2 次引用

它引用的 Paper18

  1. Composition-based Multi-Relational Graph Convolutional NetworksShikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. TalukdarICLR 2020 · 1,105 次引用
  2. Inductive Relation Prediction by Subgraph ReasoningKomal K. Teru, Etienne G. Denis, William L. HamiltonICML 2020 · 493 次引用
  3. Learning Hierarchy-Aware Knowledge Graph Embeddings for Link PredictionZhanqiu Zhang, Jianyu Cai, Yongdong Zhang, Jie WangAAAI 2020 · 481 次引用
  4. Structure-Augmented Text Representation Learning for Efficient Knowledge Graph CompletionBo Wang, Tao Shen, Guodong Long, Tianyi Zhou 等WWW 2021 · 322 次引用
  5. RNNLogic: Learning Logic Rules for Reasoning on Knowledge GraphsMeng Qu, Jun-Kun Chen, Louis-Pascal A. C. Xhonneux, Yoshua Bengio 等ICLR 2021 · 230 次引用

相关 Paper

  1. Knowledge Graph Reasoning with Relational DigraphYongqi Zhang, Quanming YaoWWW 2022 · 193 次引用
  2. Temporal Knowledge Graph Reasoning Based on Evolutional Representation LearningZixuan Li, Xiaolong Jin, Wei Li, Saiping Guan 等SIGIR 2021 · 345 次引用
  3. Learning Long- and Short-term Representations for Temporal Knowledge Graph ReasoningMengqi Zhang, Yuwei Xia, Qiang Liu, Shu Wu 等WWW 2023 · 83 次引用
  4. Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor AggregationHan Yu, Xiaojuan Zhao, Aiping Li, Kai Chen 等AAAI 2026
  5. AdaRPT: An Adaptive Rule Pattern Transfer Model for Fully Inductive Knowledge Graph ReasoningZhiwen Xie, Zhuo Zhao, Jinjin Ma, Guangyou Zhou 等SIGIR 2025 · 3 次引用
黄昏的海面,两侧是细线勾勒的悬崖