mlsanityData to 7 Oct 2026

Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks

arXiv 1905.08865 ↗First posted 21 May 2019cs.LG cs.IR stat.MLcited by 43

Not on the map. Why?

Abstract (arXiv)

How can we estimate the importance of nodes in a knowledge graph (KG)? A KG is a multi-relational graph that has proven valuable for many tasks including question answering and semantic search. In this paper, we present GENI, a method for tackling the problem of estimating node importance in KGs, which enables several downstream applications such as item recommendation and resource allocation. While a number of approaches have been developed to address this problem for general graphs, they do not fully utilize information available in KGs, or lack flexibility needed to model complex relationship between entities and their importance. To address these limitations, we explore supervised machine learning algorithms. In particular, building upon recent advancement of graph neural networks (GNNs), we develop GENI, a GNN-based method designed to deal with distinctive challenges involved with predicting node importance in KGs. Our method performs an aggregation of importance scores instead of aggregating node embeddings via predicate-aware attention mechanism and flexible centrality adjustment. In our evaluation of GENI and existing methods on predicting node importance in real-world KGs with different characteristics, GENI achieves 5-17% higher NDCG@100 than the state of the art.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 9; 2023: 9; 2024: 8; 2025: 6; 2026: 3.

43 papers.

Sort:

By area:

  1. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  2. 2021On Provable Benefits of Depth in Training Graph Convolutional Networkscited by 58
  3. 2021Incorporating Domain Knowledge into Deep Neural Networkscited by 56
  4. 2022Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Predictioncited by 39
  5. 2022MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initializationcited by 31
  6. 2022MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural Networkscited by 19
  7. 2021Engineering Knowledge Graph from Patent Databasecited by 18
  8. 2024Anomaly Detection in Dynamic Graphs: A Comprehensive Surveycited by 18
  9. 2024OAG-Bench: A Human-Curated Benchmark for Academic Graph Miningcited by 14
  10. 2022Supervised Graph Contrastive Learning for Few-shot Node Classificationcited by 9
  11. 2022GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimationcited by 9
  12. 2024Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networkscited by 9
31 more
  1. 2021Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classificationcited by 8
  2. 2023Collaborative Graph Neural Networks for Attributed Network Embeddingcited by 8
  3. 2023Modeling Dynamic Heterogeneous Graph and Node Importance for Future Citation Predictioncited by 7
  4. 2023NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streamscited by 6
  5. 2024CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influencecited by 6
  6. 2021Graph neural network-based fault diagnosis: a reviewcited by 5
  7. 2024Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphscited by 5
  8. 2024Training-free Graph Neural Networks and the Power of Labels as Featurescited by 5
  9. 2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
  10. 2023Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgenesscited by 4
  11. 2025Semi-supervised Node Importance Estimation with Informative Distribution Modeling for Uncertainty Regularizationcited by 4
  12. 2022Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Networkcited by 2
  13. 2022Comprehensive Analysis of Over-smoothing in Graph Neural Networks from Markov Chains Perspectivecited by 2
  14. 2023Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphscited by 2
  15. 2024Node Importance Estimation Leveraging LLMs for Semantic Augmentation in Knowledge Graphscited by 2
  16. 2022Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothingcited by 1
  17. 2023Classification of vertices on social networks by multiple approachescited by 1
  18. 2023MGL2Rank: Learning to Rank the Importance of Nodes in Road Networks Based on Multi-Graph Fusioncited by 1
  19. 2025NodeReg: Mitigating the Imbalance and Distribution Shift Effects in Semi-Supervised Node Classification via Norm Consistencycited by 1
  20. 2025Critical Nodes Identification in Complex Networks: A Surveycited by 1
  21. 2025PINE: Pipeline for Important Node Exploration in Attributed Networkscited by 1
  22. 2021Knowledge-Guided Dynamic Systems Modeling: A Case Study on Modeling River Water Qualitycited by 0
  23. 2021A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networkscited by 0
  24. 2021Incorporation of Deep Neural Network & Reinforcement Learning with Domain Knowledgecited by 0
  25. 2023Edge Ranking of Graphs in Transportation Networks using a Graph Neural Network (GNN)cited by 0
  26. 2023Differentially Private Graph Neural Network with Importance-Grained Noise Adaptioncited by 0
  27. 2024CADReN: Contextual Anchor-Driven Relational Network for Controllable Cross-Graphs Node Importance Estimationcited by 0
  28. 2025Importance Ranking in Complex Networks via Influence-aware Causal Node Embeddingcited by 0
  29. 2026MQ-GNN: A Multi-Queue Pipelined Architecture for Scalable and Efficient GNN Trainingcited by 0
  30. 2026PiGRAND: Physics-informed Graph Neural Diffusion for Intelligent Additive Manufacturingcited by 0
  31. 2026Learning over Positive and Negative Edges with Contrastive Message Passingcited by 0