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

Selective Temporal Knowledge Graph Reasoning (2404.01695v1)

Published 2 Apr 2024 in cs.LG

Abstract: Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently. TKG reasoning aims to predict future facts based on given historical ones. However, existing TKG reasoning models are unable to abstain from predictions they are uncertain, which will inevitably bring risks in real-world applications. Thus, in this paper, we propose an abstention mechanism for TKG reasoning, which helps the existing models make selective, instead of indiscriminate, predictions. Specifically, we develop a confidence estimator, called Confidence Estimator with History (CEHis), to enable the existing TKG reasoning models to first estimate their confidence in making predictions, and then abstain from those with low confidence. To do so, CEHis takes two kinds of information into consideration, namely, the certainty of the current prediction and the accuracy of historical predictions. Experiments with representative TKG reasoning models on two benchmark datasets demonstrate the effectiveness of the proposed CEHis.

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 (52)
  1. Peter L Bartlett and Marten H Wegkamp. 2008. Classification with a reject option using a hinge loss. Journal of Machine Learning Research, 9(8).
  2. Temporal knowledge graph completion: A survey. arXiv preprint arXiv:2201.08236.
  3. Boosting with abstention. Advances in Neural Information Processing Systems, 29.
  4. David Roxbee Cox and Valerie Isham. 1980. Point processes, volume 12. CRC Press.
  5. Improving selective visual question answering by learning from your peers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 24049–24059.
  6. Hyte: Hyperplane-based temporally aware knowledge graph embedding. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2001–2011.
  7. Learning dynamic context graphs for predicting social events. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 1007–1016.
  8. Dynamic knowledge graph based multi-event forecasting. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 1585–1595.
  9. Temporal knowledge graph forecasting with neural ode. arXiv preprint arXiv:2101.05151.
  10. Towards better selective classification. In The Eleventh International Conference on Learning Representations.
  11. Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning, pages 1050–1059. PMLR.
  12. Yonatan Geifman and Ran El-Yaniv. 2017. Selective classification for deep neural networks. Advances in neural information processing systems, 30.
  13. Yonatan Geifman and Ran El-Yaniv. 2019. Selectivenet: A deep neural network with an integrated reject option. In International conference on machine learning, pages 2151–2159. PMLR.
  14. Diachronic embedding for temporal knowledge graph completion. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 3988–3995.
  15. Support vector machines with a reject option. Advances in neural information processing systems, 21.
  16. Dyernie: Dynamic evolution of riemannian manifold embeddings for temporal knowledge graph completion. arXiv preprint arXiv:2011.03984.
  17. Explainable subgraph reasoning for forecasting on temporal knowledge graphs. In International Conference on Learning Representations.
  18. 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, pages 8352–8364.
  19. Graph hawkes neural network for forecasting on temporal knowledge graphs. 8th Automated Knowledge Base Construction (AKBC).
  20. Alan G Hawkes. 2018. Hawkes processes and their applications to finance: a review. Quantitative Finance, 18(2):193–198.
  21. Dan Hendrycks and Kevin Gimpel. 2016. A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136.
  22. Self-adaptive training: beyond empirical risk minimization. Advances in neural information processing systems, 33:19365–19376.
  23. Recurrent event network: Autoregressive structure inference over temporal knowledge graphs. In EMNLP.
  24. Recurrent event network for reasoning over temporal knowledge graphs. arXiv preprint arXiv:1904.05530.
  25. Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation. arXiv preprint arXiv:2302.09664.
  26. Hawkes processes. arXiv preprint arXiv:1507.02822.
  27. Towards temporal knowledge graph embeddings with arbitrary time precision. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 685–694.
  28. Tirgn: time-guided recurrent graph network with local-global historical patterns for temporal knowledge graph reasoning. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022, pages 2152–2158. ijcai. org.
  29. Complex evolutional pattern learning for temporal knowledge graph reasoning. arXiv preprint arXiv:2203.07782.
  30. Hismatch: Historical structure matching based temporal knowledge graph reasoning. arXiv preprint arXiv:2210.09708.
  31. Search from history and reason for future: Two-stage reasoning on temporal knowledge graphs. arXiv preprint arXiv:2106.00327.
  32. 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, pages 408–417.
  33. Tlogic: Temporal logical rules for explainable link forecasting on temporal knowledge graphs. In Proceedings of the AAAI conference on artificial intelligence, volume 36, pages 4120–4127.
  34. Deep gamblers: Learning to abstain with portfolio theory. Advances in Neural Information Processing Systems, 32.
  35. Temporal knowledge graph completion using box embeddings. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 7779–7787.
  36. Self-correcting process for high quality patterning by atomic layer deposition. Acs Nano, 9(9):8710–8717.
  37. Planned protest modeling in news and social media. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 29, pages 3920–3927.
  38. Evokg: Jointly modeling event time and network structure for reasoning over temporal knowledge graphs. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pages 794–803.
  39. Using social media to predict the future: a systematic literature review. arXiv preprint arXiv:1706.06134.
  40. Vatsal Raina and Mark Gales. 2022. Answer uncertainty and unanswerability in multiple-choice machine reading comprehension. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1020–1034.
  41. The use of twitter to track levels of disease activity and public concern in the us during the influenza a h1n1 pandemic. PloS one, 6(5):e19467.
  42. Timetraveler: Reinforcement learning for temporal knowledge graph forecasting. arXiv preprint arXiv:2109.04101.
  43. Dyrep: Learning representations over dynamic graphs.
  44. Matias Valdenegro-Toro. 2023. Sub-ensembles for fast uncertainty estimation in neural networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4119–4127.
  45. Kgat: Knowledge graph attention network for recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 950–958.
  46. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the AAAI conference on artificial intelligence, volume 28.
  47. Reliable visual question answering: Abstain rather than answer incorrectly. In European Conference on Computer Vision, pages 148–166. Springer.
  48. The art of abstention: Selective prediction and error regularization for natural language processing. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1040–1051.
  49. Temporal knowledge graph reasoning with historical contrastive learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 4765–4773.
  50. Dynamic graph neural networks for sequential recommendation. IEEE Transactions on Knowledge and Data Engineering, 35(5):4741–4753.
  51. Learning from history: Modeling temporal knowledge graphs with sequential copy-generation networks. arXiv preprint arXiv:2012.08492.
  52. Transformer hawkes process. In International conference on machine learning, pages 11692–11702. PMLR.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Zhongni Hou (4 papers)
  2. Xiaolong Jin (38 papers)
  3. Zixuan Li (63 papers)
  4. Long Bai (87 papers)
  5. Jiafeng Guo (161 papers)
  6. Xueqi Cheng (274 papers)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets