2000 character limit reached
Interpretable Neural Temporal Point Processes for Modelling Electronic Health Records (2404.08007v1)
Published 9 Apr 2024 in cs.LG
Abstract: Electronic Health Records (EHR) can be represented as temporal sequences that record the events (medical visits) from patients. Neural temporal point process (NTPP) has achieved great success in modeling event sequences that occur in continuous time space. However, due to the black-box nature of neural networks, existing NTPP models fall short in explaining the dependencies between different event types. In this paper, inspired by word2vec and Hawkes process, we propose an interpretable framework inf2vec for event sequence modelling, where the event influences are directly parameterized and can be learned end-to-end. In the experiment, we demonstrate the superiority of our model on event prediction as well as type-type influences learning.
- Principal component analysis. Wiley interdisciplinary reviews: computational statistics, 2(4):433–459, 2010.
- Neural ordinary differential equations. Advances in Neural Information Processing Systems, 31, 2018.
- Retain: An interpretable predictive model for healthcare using reverse time attention mechanism. In Neural Information Processing Systems, 2016. URL https://api.semanticscholar.org/CorpusID:948039.
- Empirical evaluation of gated recurrent neural networks on sequence modeling. ArXiv, abs/1412.3555, 2014.
- A survey of the state of explainable ai for natural language processing. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pp. 447–459, 2020.
- Learning point processes using recurrent graph network. In 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE, 2022.
- Recurrent marked temporal point processes: Embedding event history to vector. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1555–1564, 2016.
- Neural temporal point processes for modelling electronic health records. ArXiv, abs/2007.13794, 2020. URL https://api.semanticscholar.org/CorpusID:220831434.
- Yulong Gu. Attentive neural point processes for event forecasting. In AAAI Conference on Artificial Intelligence, 2021. URL https://api.semanticscholar.org/CorpusID:235306506.
- Alan G Hawkes. Point spectra of some mutually exciting point processes. Journal of the Royal Statistical Society: Series B (Methodological), 33(3):438–443, 1971a.
- Alan G Hawkes. Spectra of some self-exciting and mutually exciting point processes. Biometrika, 58(1):83–90, 1971b.
- Explainable ai: A review of machine learning interpretability methods. Entropy, 23(1):18, 2020.
- Integrating classification and association rule mining. In Knowledge Discovery and Data Mining, 1998. URL https://api.semanticscholar.org/CorpusID:232928.
- Link-aware link prediction over temporal graph by pattern recognition. In International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 2023. URL https://api.semanticscholar.org/CorpusID:260170307.
- Discovery of frequent episodes in event sequences. Data Mining and Knowledge Discovery, 1:259–289, 1997. URL https://api.semanticscholar.org/CorpusID:6987161.
- The neural hawkes process: A neurally self-modulating multivariate point process. Advances in Neural Information Processing Systems, 30, 2017.
- Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems, 26, 2013.
- Explainable artificial intelligence: a comprehensive review. Artificial Intelligence Review, pp. 1–66, 2022.
- Fully neural network based model for general temporal point processes. Advances in Neural Information Processing Systems, 32, 2019.
- Neural temporal point processes: A review. ArXiv, abs/2104.03528, 2021.
- Unipoint: Universally approximating point processes intensities. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp. 9685–9694, 2021.
- Attention is all you need. Advances in Neural Information Processing Systems, 30, 2017.
- Modeling inter-dependence between time and mark in multivariate temporal point processes. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 1986–1995, 2022.
- Self-attentive hawkes process. In International Conference on Machine Learning, pp. 11183–11193. PMLR, 2020a.
- Cause: Learning granger causality from event sequences using attribution methods. Proceedings of the … International Conference on Machine Learning. International Conference on Machine Learning, 119:11235–11245, 2020b. URL https://api.semanticscholar.org/CorpusID:211171699.
- Neural relation inference for multi-dimensional temporal point processes via message passing graph. In International Joint Conference on Artificial Intelligence, 2021. URL https://api.semanticscholar.org/CorpusID:237100690.
- Learning social infectivity in sparse low-rank networks using multi-dimensional hawkes processes. In International Conference on Artificial Intelligence and Statistics, 2013. URL https://api.semanticscholar.org/CorpusID:8326502.
- Automatic integration for fast and interpretable neural point processes. In Conference on Learning for Dynamics & Control, 2023. URL https://api.semanticscholar.org/CorpusID:259178556.
- Transformer hawkes process. In International Conference on Machine Learning, pp. 11692–11702. PMLR, 2020.
- Bingqing Liu (8 papers)