Distance-Based Propagation for Efficient Knowledge Graph Reasoning

• URL: http://arxiv.org/abs/2311.01024v1
• Date: Thu, 2 Nov 2023 06:37:46 GMT
• Title: Distance-Based Propagation for Efficient Knowledge Graph Reasoning
• Authors: Harry Shomer, Yao Ma, Juanhui Li, Bo Wu, Charu C. Aggarwal, Jiliang Tang
• Abstract summary: Knowledge graph completion (KGC) aims to predict unseen edges in knowledge graphs (KGs) New class of methods have been proposed to tackle this problem by aggregating path information. New method, TAGNet, is able to efficiently propagate information.
• Score: 43.138409280069204
• License: http://creativecommons.org/licenses/by/4.0/
• 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. The code is available at https://github.com/HarryShomer/TAGNet.

Related papers

• TransNet: Transfer Knowledge for Few-shot Knowledge Graph Completion [69.6049217133483]
  We propose a transfer learning-based few-shot KG completion method (TransNet) By learning the relationships between different tasks, TransNet effectively transfers knowledge from similar tasks to improve the current task's performance.
  arXiv  Detail & Related papers  (2025-03-29T23:39:11Z)
• Adaptive Anchor Label Propagation for Transductive Few-Shot Learning [18.29463308334406]
  Few-shot learning addresses the issue of classifying images using limited labeled data. We propose a novel algorithm that adapts the feature embeddings of the labeled data by minimizing a differentiable loss function. Our algorithm outperforms the standard label propagation algorithm by as much as 7% and 2% in the 1-shot and 5-shot settings respectively.
  arXiv  Detail & Related papers  (2023-10-30T20:29:31Z)
• Efficient Heterogeneous Graph Learning via Random Projection [58.4138636866903]
  Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors. We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN)
  arXiv  Detail & Related papers  (2023-10-23T01:25:44Z)
• From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited [51.24526202984846]
  Graph-based semi-supervised learning (GSSL) has long been a hot research topic.<n> graph convolutional networks (GCNs) have become the predominant techniques for their promising performance.<n>We propose three simple but powerful graph convolution methods.
  arXiv  Detail & Related papers  (2023-09-24T10:10:21Z)
• Unsupervised Multiplex Graph Learning with Complementary and Consistent Information [20.340977728674698]
  Unsupervised multiplex graph learning (UMGL) has been shown to achieve significant effectiveness for different downstream tasks. Previous methods usually overlook the issues in practical applications, i.e., the out-of-sample issue and the noise issue. We propose an effective and efficient method to explore both complementary and consistent information.
  arXiv  Detail & Related papers  (2023-08-03T08:24:08Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Localized Contrastive Learning on Graphs [110.54606263711385]
  We introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL) In spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
  arXiv  Detail & Related papers  (2022-12-08T23:36:00Z)
• A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs [19.873384058276713]
  A*Net is a scalable path-based method for knowledge graph reasoning. Inspired by the A* algorithm for shortest iteration path problems, our A*Net learns a priority function to select important nodes and edges at each.
  arXiv  Detail & Related papers  (2022-06-07T01:01:36Z)
• DOTIN: Dropping Task-Irrelevant Nodes for GNNs [119.17997089267124]
  Recent graph learning approaches have introduced the pooling strategy to reduce the size of graphs for learning. We design a new approach called DOTIN (underlineDrunderlineopping underlineTask-underlineIrrelevant underlineNodes) to reduce the size of graphs. Our method speeds up GAT by about 50% on graph-level tasks including graph classification and graph edit distance.
  arXiv  Detail & Related papers  (2022-04-28T12:00:39Z)
• Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking [58.30147362745852]
  Data association across frames is at the core of Multiple Object Tracking (MOT) task. Existing methods mostly ignore the context information among tracklets and intra-frame detections. We propose a novel learnable graph matching method to address these issues.
  arXiv  Detail & Related papers  (2021-03-30T08:58:45Z)
• Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining [26.04006507181558]
  We propose a novel KG encoder -- Dual Attention Matching Network (Dual-AMN) The experimental results on widely used public datasets indicate that our method achieves both high accuracy and high efficiency.
  arXiv  Detail & Related papers  (2021-03-29T09:35:07Z)
• Knowledge Graph Embedding with Atrous Convolution and Residual Learning [4.582412257655891]
  We propose a simple but effective atrous convolution based knowledge graph embedding method. It effectively increases feature interactions by using atrous convolutions. It addresses the original information forgotten issue and vanishing/exploding gradient issue.
  arXiv  Detail & Related papers  (2020-10-23T00:57:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.