TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning (2312.15816v2)
Abstract: Conventional embedding-based models approach event time prediction in temporal knowledge graphs (TKGs) as a ranking problem. However, they often fall short in capturing essential temporal relationships such as order and distance. In this paper, we propose TEILP, a logical reasoning framework that naturally integrates such temporal elements into knowledge graph predictions. We first convert TKGs into a temporal event knowledge graph (TEKG) which has a more explicit representation of time in term of nodes of the graph. The TEKG equips us to develop a differentiable random walk approach to time prediction. Finally, we introduce conditional probability density functions, associated with the logical rules involving the query interval, using which we arrive at the time prediction. We compare TEILP with state-of-the-art methods on five benchmark datasets. We show that our model achieves a significant improvement over baselines while providing interpretable explanations. In particular, we consider several scenarios where training samples are limited, event types are imbalanced, and forecasting the time of future events based on only past events is desired. In all these cases, TEILP outperforms state-of-the-art methods in terms of robustness.
- Temporal knowledge graph completion: A survey. arXiv preprint arXiv:2201.08236.
- Time in a box: advancing knowledge graph completion with temporal scopes. In Proceedings of the 11th on Knowledge Capture Conference, 121–128.
- Multi-granularity Temporal Question Answering over Knowledge Graphs. In Rogers, A.; Boyd-Graber, J.; and Okazaki, N., eds., Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 11378–11392. Toronto, Canada: Association for Computational Linguistics.
- Hyte: Hyperplane-based temporally aware knowledge graph embedding. In Proceedings of the 2018 conference on empirical methods in natural language processing, 2001–2011.
- Learning Sequence Encoders for Temporal Knowledge Graph Completion. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 4816–4821. Brussels, Belgium: Association for Computational Linguistics.
- Diachronic embedding for temporal knowledge graph completion. In Proceedings of the AAAI conference on artificial intelligence, volume 34, 3988–3995.
- Graph hawkes neural network for forecasting on temporal knowledge graphs. arXiv preprint arXiv:2003.13432.
- Temporal knowledge base completion: New algorithms and evaluation protocols. arXiv preprint arXiv:2005.05035.
- Overview of the TAC2011 Knowledge Base Population (KBP) Track. In Presentation at the Fourth Text Analysis Conference (TAC 2011), November, 14–15.
- Tensor Decompositions for Temporal Knowledge Base Completion. In International Conference on Learning Representations.
- Gdelt: Global data on events, location, and tone, 1979–2012. In ISA annual convention, volume 2, 1–49. Citeseer.
- Explaining point processes by learning interpretable temporal logic rules. In International Conference on Learning Representations.
- Temporal Logic Point Processes. In III, H. D.; and Singh, A., eds., Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, 5990–6000. PMLR.
- Tlogic: Temporal logical rules for explainable link forecasting on temporal knowledge graphs. In Proceedings of the AAAI conference on artificial intelligence, volume 36, 4120–4127.
- An Adaptive Logical Rule Embedding Model for Inductive Reasoning over Temporal Knowledge Graphs. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 7304–7316.
- Learning Temporal Rules from Knowledge Graph Streams. In AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering.
- 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, 794–803.
- Question Answering Over Temporal Knowledge Graphs. arXiv:2106.01515.
- NeuSTIP: A Novel Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs. arXiv:2305.11301.
- Surdeanu, M. 2013. Overview of the TAC2013 Knowledge Base Population Evaluation: English Slot Filling and Temporal Slot Filling. TAC, 8: 2.
- Know-evolve: Deep temporal reasoning for dynamic knowledge graphs. In international conference on machine learning, 3462–3471. PMLR.
- TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs. In The Eleventh International Conference on Learning Representations.
- Differentiable learning of logical rules for knowledge base reasoning. Advances in neural information processing systems, 30.