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

Temporal Inductive Path Neural Network for Temporal Knowledge Graph Reasoning (2309.03251v3)

Published 6 Sep 2023 in cs.AI and cs.LG

Abstract: Temporal Knowledge Graph (TKG) is an extension of traditional Knowledge Graph (KG) that incorporates the dimension of time. Reasoning on TKGs is a crucial task that aims to predict future facts based on historical occurrences. The key challenge lies in uncovering structural dependencies within historical subgraphs and temporal patterns. Most existing approaches model TKGs relying on entity modeling, as nodes in the graph play a crucial role in knowledge representation. However, the real-world scenario often involves an extensive number of entities, with new entities emerging over time. This makes it challenging for entity-dependent methods to cope with extensive volumes of entities, and effectively handling newly emerging entities also becomes a significant challenge. Therefore, we propose Temporal Inductive Path Neural Network (TiPNN), which models historical information in an entity-independent perspective. Specifically, TiPNN adopts a unified graph, namely history temporal graph, to comprehensively capture and encapsulate information from history. Subsequently, we utilize the defined query-aware temporal paths on a history temporal graph to model historical path information related to queries for reasoning. Extensive experiments illustrate that the proposed model not only attains significant performance enhancements but also handles inductive settings, while additionally facilitating the provision of reasoning evidence through history temporal graphs.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (64)
  1. How to explain individual classification decisions. Journal of Machine Learning Research 11 (June 2010), 1803–1831.
  2. TPmod: A Tendency-Guided Prediction Model for Temporal Knowledge Graph Completion. ACM Trans. Knowl. Discov. Data 15, 3, Article 41 (apr 2021), 17 pages. https://doi.org/10.1145/3443687
  3. Translating embeddings for modeling multi-relational data. Advances in neural information processing systems 26 (2013).
  4. ICEWS Coded Event Data. https://doi.org/10.7910/DVN/28075
  5. Principal neighbourhood aggregation for graph nets. Advances in Neural Information Processing Systems 33 (2020), 13260–13271.
  6. Hyte: Hyperplane-based temporally aware knowledge graph embedding. In Proceedings of the 2018 conference on empirical methods in natural language processing. 2001–2011.
  7. Convolutional 2D Knowledge Graph Embeddings. In 32nd AAAI Conference on Artificial Intelligence (AAAI-18), 2-7 February 2018, New Orleans, LA, USA.
  8. Adaptive Path-Memory Network for Temporal Knowledge Graph Reasoning. arXiv preprint arXiv:2304.12604 (2023).
  9. Predicting the co-evolution of event and knowledge graphs. In 2016 19th International Conference on Information Fusion (FUSION). IEEE, 98–105.
  10. AMIE: association rule mining under incomplete evidence in ontological knowledge bases. In Proceedings of the 22nd international conference on World Wide Web. 413–422.
  11. Learning Sequence Encoders for Temporal Knowledge Graph Completion. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 4816–4821.
  12. Learning sequence encoders for temporal knowledge graph completion. arXiv preprint arXiv:1809.03202 (2018).
  13. Matthew M. Gervais. 2017. RICH Economic Games for Networked Relationships and Communities: Development and Preliminary Validation in Yasawa, Fiji. Field Methods 29, 2 (2017), 113–129. https://doi.org/10.1177/1525822X16643709 arXiv:https://doi.org/10.1177/1525822X16643709
  14. Diachronic Embedding for Temporal Knowledge Graph Completion. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 3988–3995.
  15. Explainable subgraph reasoning for forecasting on temporal knowledge graphs. In International Conference on Learning Representations.
  16. Learning neural ordinary equations for forecasting future links on temporal knowledge graphs. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 8352–8364.
  17. Dyernie: Dynamic evolution of riemannian manifold embeddings for temporal knowledge graph completion. arXiv preprint arXiv:2011.03984 (2020).
  18. Knowledge graph embedding via dynamic mapping matrix. In Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (volume 1: Long papers). 687–696.
  19. Recurrent event network: Autoregressive structure inference over temporal knowledge graphs. arXiv preprint arXiv:1904.05530 (2019).
  20. Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs. In EMNLP.
  21. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
  22. Tensor Decompositions for temporal knowledge base completion. arXiv preprint arXiv:2004.04926 (2020).
  23. J. Leblay and M. W. Chekol. 2018. Deriving Validity Time in Knowledge Graph. In Companion of the the Web Conference. 1771–1776.
  24. Kalev Leetaru and Philip A Schrodt. 2013. GDELT: Global Data on Events, Location and Tone, 1979-2012. In ISA annual convention, Vol. 2. Citeseer, 1–49.
  25. TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 8517–8528. https://aclanthology.org/2022.emnlp-main.583
  26. Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, Dublin, Ireland, 290–296. https://doi.org/10.18653/v1/2022.acl-short.32
  27. Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 408–417.
  28. Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the AAAI conference on artificial intelligence, Vol. 29.
  29. Representation learning for natural language processing. Springer Nature.
  30. YAGO3: A Knowledge Base from Multilingual Wikipedias. In 7th biennial conference on innovative data systems research. CIDR Conference.
  31. Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 15524–15543. https://proceedings.mlr.press/v162/miao22a.html
  32. Holographic embeddings of knowledge graphs. In Proceedings of the AAAI conference on artificial intelligence, Vol. 30.
  33. A three-way model for collective learning on multi-relational data.. In Icml, Vol. 11. 3104482–3104584.
  34. LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding. In Pacific-Asia Conference on Knowledge Discovery and Data Mining.
  35. Context-enhanced entity and relation embedding for knowledge graph completion. arXiv preprint arXiv:2012.07011 (2020).
  36. DRUM: End-to-End Differentiable Rule Mining on Knowledge Graphs. Curran Associates Inc., Red Hook, NY, USA.
  37. Temporal reasoning over event knowledge graphs. In Workshop on Knowledge Base Construction, Reasoning and Mining.
  38. Modeling Relational Data with Graph Convolutional Networks. arXiv preprint arXiv:1703.06103 (2017).
  39. End-to-end structure-aware convolutional networks for knowledge base completion. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 3060–3067.
  40. Graph Hawkes Transformer for Extrapolated Reasoning on Temporal Knowledge Graphs. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 7481–7493.
  41. TimeTraveler: Reinforcement learning for temporal knowledge graph forecasting. arXiv preprint arXiv:2109.04101 (2021).
  42. TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting. arXiv preprint arXiv:2109.04101 (2021).
  43. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. arXiv preprint arXiv:1902.10197 (2019).
  44. Inductive Relation Prediction by Subgraph Reasoning. arXiv: Learning (2020).
  45. Know-evolve: Deep temporal reasoning for dynamic knowledge graphs. In international conference on machine learning. PMLR, 3462–3471.
  46. Dyrep: Learning representations over dynamic graphs. In International conference on learning representations.
  47. Complex embeddings for simple link prediction. In International conference on machine learning. PMLR, 2071–2080.
  48. Complex Embeddings for Simple Link Prediction. JMLR.org (2016).
  49. Composition-based multi-relational graph convolutional networks. arXiv preprint arXiv:1911.03082 (2019).
  50. Incremental Mobile User Profiling: Reinforcement Learning with Spatial Knowledge Graph for Modeling Event Streams. In KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23-27, 2020. ACM, 853–861.
  51. Modeling spatio-temporal neighbourhood for personalized point-of-interest recommendation. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, Luc De Raedt (Ed.). International Joint Conferences on Artificial Intelligence, 3530–3536. https://doi.org/10.24963/ijcai.2022/490 31st International Joint Conference on Artificial Intelligence, IJCAI 2022 ; Conference date: 23-07-2022 Through 29-07-2022.
  52. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the AAAI conference on artificial intelligence, Vol. 28.
  53. Max Welling and Thomas N Kipf. 2016. Semi-supervised classification with graph convolutional networks. In J. International Conference on Learning Representations (ICLR 2017).
  54. TransG: A generative mixture model for knowledge graph embedding. arXiv preprint arXiv:1509.05488 (2015).
  55. Inductive representation learning on temporal graphs. arXiv preprint arXiv:2002.07962 (2020).
  56. On variational learning of controllable representations for text without supervision. In International Conference on Machine Learning. PMLR, 10534–10543.
  57. Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575 (2014).
  58. Differentiable learning of logical rules for knowledge base reasoning. Advances in neural information processing systems 30 (2017).
  59. A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment.. In IJCAI. 4135–4141.
  60. Matthew D. Zeiler and Rob Fergus. 2014. Visualizing and Understanding Convolutional Networks. In Computer Vision – ECCV 2014, David Fleet, Tomas Pajdla, Bernt Schiele, and Tinne Tuytelaars (Eds.). Springer International Publishing, Cham, 818–833.
  61. Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks. (2020).
  62. Learning from history: Modeling temporal knowledge graphs with sequential copy-generation networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4732–4740.
  63. Neural-Symbolic Models for Logical Queries on Knowledge Graphs. arXiv preprint arXiv:2205.10128 (2022).
  64. Neural bellman-ford networks: A general graph neural network framework for link prediction. Advances in Neural Information Processing Systems 34 (2021).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Hao Dong (175 papers)
  2. Pengyang Wang (44 papers)
  3. Meng Xiao (114 papers)
  4. Zhiyuan Ning (27 papers)
  5. Pengfei Wang (176 papers)
  6. Yuanchun Zhou (62 papers)
Citations (10)
View on Semantic Scholar