Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning (2205.15319v2)

Published 30 May 2022 in cs.LG and cs.AI

Abstract: Due to the popularity of Graph Neural Networks (GNNs), various GNN-based methods have been designed to reason on knowledge graphs (KGs). An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step. Existing methods use hand-designed propagation paths, ignoring the correlation between the entities and the query relation. In addition, the number of involved entities will explosively grow at larger propagation steps. In this work, we are motivated to learn an adaptive propagation path in order to filter out irrelevant entities while preserving promising targets. First, we design an incremental sampling mechanism where the nearby targets and layer-wise connections can be preserved with linear complexity. Second, we design a learning-based sampling distribution to identify the semantically related entities. Extensive experiments show that our method is powerful, efficient, and semantic-aware. The code is available at https://github.com/LARS-research/AdaProp.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. Relational inductive biases, deep learning, and graph networks. Technical Report. arXiv:1806.01261.
  2. Estimating or propagating gradients through stochastic neurons for conditional computation. Technical Report. arXiv:1308.3432.
  3. Translating embeddings for modeling multi-relational data. In NeurIPS. 2787–2795.
  4. Unifying knowledge graph learning and recommendation: Towards a better understanding of user preferences. In TheWebConf. 151–161.
  5. FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. In ICLR.
  6. A review: Knowledge reasoning over knowledge graph. Expert Systems with Applications 141 (2020), 112948.
  7. RLogic: Recursive Logical Rule Learning from Knowledge Graphs. In KDD. 179–189.
  8. Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks. In SIGKDD. 257–266.
  9. Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. In ICLR.
  10. Convolutional 2D knowledge graph embeddings. In AAAI.
  11. Convolutional 2d knowledge graph embeddings. In AAAI.
  12. Differentiable Reasoning over a Virtual Knowledge Base. In ICLR.
  13. Relation matters in sampling: a scalable multi-relational graph neural network for drug-drug interaction prediction. Technical Report. arXiv:2105.13975.
  14. Neural Message Passing for Quantum Chemistry. In ICML. 1263–1272.
  15. Inductive representation learning on large graphs. In NeurIPS. 1024–1034.
  16. Knowledge graphs. ACM Computing Surveys (CSUR) 54, 4 (2021), 1–37.
  17. Adaptive Sampling Towards Fast Graph Representation Learning. In NeurIPS, Vol. 31. 4558–4567.
  18. Knowledge graph embedding based question answering. In WSDM. 105–113.
  19. Categorical Reparameterization with Gumbel-Softmax. In ICLR.
  20. A survey on knowledge graphs: Representation, acquisition and applications. Technical Report. arXiv:2002.00388.
  21. D. P Kingma and J. Ba. 2014. Adam: A method for stochastic optimization. Technical Report. arXiv:1412.6980.
  22. T. N Kipf and M. Welling. 2016. Semi-supervised classification with graph convolutional networks. In ICLR.
  23. S. Kok and P. Domingos. 2007. Statistical predicate invention. In ICML. 433–440.
  24. Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement. In ICML. PMLR, 3499–3508.
  25. Communicative Message Passing for Inductive Relation Reasoning.. In AAAI. 4294–4302.
  26. Fine-grained evaluation of rule-and embedding-based systems for knowledge graph completion. In ISWC. Springer, 3–20.
  27. A. Mnih and K. Gregor. 2014. Neural variational inference and learning in belief networks. In ICML. PMLR, 1791–1799.
  28. K. Oono and T. Suzuki. 2019. Graph Neural Networks Exponentially Lose Expressive Power for Node Classification. In ICLR.
  29. Automatic differentiation in PyTorch. In ICLR.
  30. RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs. In ICLR.
  31. DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs. In NeurIPS. 15347–15357.
  32. Modeling relational data with graph convolutional networks. In ESWC. Springer, 593–607.
  33. Yago: A core of semantic knowledge. In The WebConf. 697–706.
  34. Rotate: Knowledge graph embedding by relational rotation in complex space. In ICLR.
  35. R. S Sutton and A. Barto. 2018. Reinforcement learning: An introduction. MIT press.
  36. Inductive Relation Prediction by Subgraph Reasoning. Technical Report. arXiv:1911.06962.
  37. K. Toutanova and D. Chen. 2015. Observed versus latent features for knowledge base and text inference. In PWCVSMC. 57–66.
  38. Composition-based multi-relational graph convolutional networks.
  39. Knowledge graph embedding: A survey of approaches and applications. TKDE 29, 12 (2017), 2724–2743.
  40. Kgat: Knowledge graph attention network for recommendation. In SIGKDD. 950–958.
  41. R. J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning Journal 8, 3-4 (1992), 229–256.
  42. A comparison of greedy search algorithms. In Proceedings of the International Symposium on Combinatorial Search, Vol. 1. 129–136.
  43. S. Xie and S. Ermon. 2019. Reparameterizable Subset Sampling via Continuous Relaxations. In IJCAI.
  44. DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning. In EMNLP. 564–573.
  45. Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning. In ICLR.
  46. Differentiable learning of logical rules for knowledge base reasoning. In NeurIPS. 2319–2328.
  47. A comprehensive survey of graph neural networks for knowledge graphs. IEEE Access 10 (2022), 75729–75741.
  48. Performance-Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks. In SIGKDD. 2046–2056.
  49. SumGNN: multi-typed drug interaction prediction via efficient knowledge graph summarization. Bioinformatics 37, 18 (2021), 2988–2995.
  50. Decoupling the Depth and Scope of Graph Neural Networks. In NeurIPS, Vol. 34.
  51. GraphSAINT: Graph Sampling Based Inductive Learning Method. In ICLR.
  52. Quaternion knowledge graph embeddings. NeurIPS 32 (2019).
  53. Y. Zhang and Q. Yao. 2022. Knowledge Graph Reasoning with Relational Directed Graph. In TheWebConf.
  54. Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding. In NeurIPS, Vol. 33.
  55. AutoSF: Searching scoring functions for knowledge graph embedding. In ICDE. IEEE, 433–444.
  56. Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction. In NeurIPS.
  57. Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks. NeurIPS 32 (2019), 11249–11259.
Citations (34)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now