Distance-Based Propagation for Efficient Knowledge Graph Reasoning
Harry Shomer, Yao Ma, Juanhui Li, Bo Wu, Charu C. Aggarwal, Jiliang Tang
Abstract
Knowledge graph completion (KGC) aims to predict unseen edges in knowledge graphs (KGs), resulting in the discovery of new facts. A new class of methods have been proposed to tackle this problem by aggregating path information. These methods have shown tremendous ability in the task of KGC. However they are plagued by efficiency issues. Though there are a few recent attempts to address this through learnable path pruning, they often sacrifice the performance to gain efficiency. In this work, we identify two intrinsic limitations of these methods that affect the efficiency and representation quality. To address the limitations, we introduce a new method, TAGNet, which is able to efficiently propagate information. This is achieved by only aggregating paths in a fixed window for each source-target pair. We demonstrate that the complexity of TAGNet is independent of the number of layers. Extensive experiments demonstrate that TAGNet can cut down on the number of propagated messages by as much as 90% while achieving competitive performance on multiple KG datasets 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction cites Inductive Relation Prediction by Subgraph Reasoning
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction cites Composition-based Multi-Relational Graph Convolutional Networks
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction cites Principal Neighbourhood Aggregation for Graph Nets
- Knowledge Graph Reasoning with Relational Digraph cites Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
- Knowledge Graph Reasoning with Relational Digraph cites Inductive Relation Prediction by Subgraph Reasoning
- Knowledge Graph Reasoning with Relational Digraph cites Composition-based Multi-Relational Graph Convolutional Networks
Builds on8
- Composition-based Multi-Relational Graph Convolutional NetworksShikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. TalukdarICLR 2020 · 1,105 citations
- Principal Neighbourhood Aggregation for Graph NetsGabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò et al.NeurIPS 2020 · 914 citations
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link PredictionZhaocheng Zhu, Zuobai Zhang, Louis-Pascal A. C. Xhonneux, Jian TangNeurIPS 2021 · 546 citations
- Inductive Relation Prediction by Subgraph ReasoningKomal K. Teru, Etienne G. Denis, William L. HamiltonICML 2020 · 493 citations
- Knowledge Graph Reasoning with Relational DigraphYongqi Zhang, Quanming YaoWWW 2022 · 193 citations
Related papers
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph CompletionLing Ding, Lei Huang, Zhizhi Yu, Di Jin et al.AAAI 2025 · 8 citations
- GreenKGC: A Lightweight Knowledge Graph Completion MethodYuncheng Wang, Xiou Ge, Bin Wang, C.-C. Jay KuoACL 2023 · 18 citations
- A Unified Joint Approach with Topological Context Learning and Rule Augmentation for Knowledge Graph CompletionJingtao Guo, Chunxia Zhang, Lingxi Li, Xiaojun Xue et al.ACL Findings 2024 · 9 citations
- Mixed Geometry Message and Trainable Convolutional Attention Network for Knowledge Graph CompletionBin Shang, Yinliang Zhao, Jun Liu, Di WangAAAI 2024 · 18 citations
- Logical Reasoning with Relation Network for Inductive Knowledge Graph CompletionQinggang Zhang, Keyu Duan, Junnan Dong, Pai Zheng et al.KDD 2024 · 8 citations
