The DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Causal Discovery with Attention-Based Convolutional Neural Networks
Open accessAbstract
Having insight into the causal associations in a complex system facilitates decision making, e.g., for medical treatments, urban infrastructure improvements or financial investments. The amount of observational data grows, which enables the discovery of causal relationships between variables from observation of their behaviour in time. Existing methods for causal discovery from time series data do not yet exploit the representational power of deep learning. We therefore present the Temporal Causal Discovery Framework (TCDF), a deep learning framework that learns a causal graph structure by discovering causal relationships in observational time series data. TCDF uses attention-based convolutional neural networks combined with a causal validation step. By interpreting the internal parameters of the convolutional networks, TCDF can also discover the time delay between a cause and the occurrence of its effect. Our framework learns temporal causal graphs, which can include confounders and instantaneous effects. Experiments on financial and neuroscientific benchmarks show state-of-the-art performance of TCDF on discovering causal relationships in continuous time series data. Furthermore, we show that TCDF can circumstantially discover the presence of hidden confounders. Our broadly applicable framework can be used to gain novel insights into the causal dependencies in a complex system, which is important for reliable predictions, knowledge discovery and data-driven decision making.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Investigating causal relations by econometric models and cross-spectral methods
Granger, C. W. J. (1969) · Econometrica · doi:10.2307/1912791 · Cited by 22,989
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
The Cross‐Section of Expected Stock Returns
FAMA, E. F., & FRENCH, K. R. (1992) · The Journal of Finance · doi:10.1111/j.1540-6261.1992.tb04398.x · Cited by 17,261
Learning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911
Causation, Prediction, and Search
Spirtes, P., Glymour, C., & Scheines, R. (2001) · doi:10.7551/mitpress/1754.001.0001 · Cited by 4,521
Automatic Time Series Forecasting: The forecast Package for R
Hyndman, R. J., & Khandakar, Y. (2008) · Journal of Statistical Software · doi:10.18637/jss.v027.i03 · Cited by 3,511
Convolutional Sequence to Sequence Learning
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017) · arXiv · doi:10.48550/arxiv.1705.03122 · Cited by 2,850 · cited 2×
“Prior work on attention in deep learning mostly addresses recurrent networks, but Facebook’s FairSeq [38] for neural machine translation and the Attention Based Convolutional Neural Network [43] for modeling sentence pairs have shown that attention is very effective in CNNs.”
BackgroundNetwork modelling methods for FMRI
Smith, S. M., Miller, K. L., Salimi-Khorshidi, G., Webster, M., Beckmann, C. F., Nichols, T. E., Ramsey, J. D., & Woolrich, M. W. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2010.08.063 · Cited by 1,878
Conditional Image Generation with PixelCNN Decoders
van den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., & Kavukcuoglu, K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.05328 · Cited by 1,833
Dynamics of blood flow and oxygenation changes during brain activation: the Balloon model
Buxton, R. B., Wong, E. C., & Frank, L. R. (1998) · Magnetic Resonance in Medicine · doi:10.1002/mrm.1910390602 · Cited by 1,665
Making Things Happen: A Theory of Causal Explanation
Woodward, J. (2004) · doi:10.1093/0195155270.001.0001 · Cited by 1,302
Thinking Clearly About Correlations and Causation: Graphical Causal Models for Observational Data
Rohrer, J. M. (2018) · Advances in Methods and Practices in Psychological Science · doi:10.1177/2515245917745629 · Cited by 1,002
Detecting and quantifying causal associations in large nonlinear time series datasets
Runge, J., Nowack, P., Kretschmer, M., Flaxman, S., & Sejdinovic, D. (2019) · Science Advances · doi:10.1126/sciadv.aau4996 · Cited by 979
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
Yin, W., Schütze, H., Xiang, B., & Zhou, B. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00097 · Cited by 924
Elements of Causal Inference: Foundations and Learning Algorithms
Peters, J., Janzing, D., & Schölkopf, B. (2017) · OAPEN (The OAPEN Foundation) · Cited by 789
An Introduction to Causal Inference
Pearl, J. (2010) · The International Journal of Biostatistics · doi:10.2202/1557-4679.1203 · Cited by 755
Abdul, A., Vermeulen, J., Wang, D., Lim, B. Y., & Kankanhalli, M. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174156 · Cited by 743
Datta, A., Sen, S., & Zick, Y. (2016) · 2016 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2016.42 · Cited by 728
Detecting and quantifying causal associations in large nonlinear time series datasets
Runge, J., Nowack, P., Kretschmer, M., Flaxman, S., & Sejdinović, D. (2019) · Publication Database PIK (Potsdam Institute for Climate Impact Research (PIK)) · Cited by 713
Analysing connectivity with Granger causality and dynamic causal modelling
Friston, K., Moran, R., & Seth, A. K. (2013) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2012.11.010 · Cited by 684
From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
Martins, A. F. T., & Astudillo, R. F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02068 · Cited by 431
The Oxford Handbook of Causation
(2009) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780199279739.001.0001 · Cited by 423
Kernel Method for Nonlinear Granger Causality
Marinazzo, D., Pellicoro, M., & Stramaglia, S. (2008) · Physical Review Letters · doi:10.1103/physrevlett.100.144103 · Cited by 400
Conditional Time Series Forecasting with Convolutional Neural Networks
Borovykh, A., Bohté, S. M., & Oosterlee, C. W. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.04691 · Cited by 362
Chen, Y., Bressler, S. L., & Ding, M. (2006) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2005.06.011 · Cited by 343
Causal discovery and inference: concepts and recent methodological advances
Spirtes, P., & Zhang, K. (2016) · Applied Informatics · doi:10.1186/s40535-016-0018-x · Cited by 304
Quinn, C. J., Coleman, T. P., Kiyavash, N., & Hatsopoulos, N. G. (2011) · Journal of Computational Neuroscience · doi:10.1007/s10827-010-0247-2 · Cited by 273
Causal Effect Inference with Deep Latent-Variable Models
Louizos, C., Shalit, U., Mooij, J. M., Sontag, D. A., Zemel, R. S., & Welling, M. (2017) · UvA-DARE (University of Amsterdam) · doi:10.48550/arxiv.1705.08821 · Cited by 267
Janzing, D., Balduzzi, D., Grosse‐Wentrup, M., & Schölkopf, B. (2013) · The Annals of Statistics · doi:10.1214/13-aos1145 · Cited by 216
Introduction to Causal Inference
Spirtes, P. (2010) · doi:10.5555/1756006.1859905 · Cited by 208
Statistical Inference for Variable Importance
van der Laan, M. J. (2006) · The International Journal of Biostatistics · doi:10.2202/1557-4679.1008 · Cited by 165
Causal Inference in Time Series Analysis
Eichler, M. (2012) · Wiley series in probability and statistics · doi:10.1002/9781119945710.ch22 · Cited by 155
Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling
Shen, T., Zhou, T., Long, G., Jiang, J. B., Wang, S., & Chengqi Zhang, B. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/604 · Cited by 155
Causal discovery algorithms: A practical guide
Malinsky, D., & Danks, D. J. (2017) · Philosophy Compass · doi:10.1111/phc3.12470 · Cited by 148
Universal Estimation of Directed Information
Jiao, J., Permuter, H. H., Zhao, L., Kim, Y.-H., & Weissman, T. (2013) · IEEE Transactions on Information Theory · doi:10.1109/tit.2013.2267934 · Cited by 117
Autoregressive Convolutional Neural Networks for Asynchronous Time SeriesPreprint
Bińkowski, M., Marti, G., & Donnat, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.04122 · Cited by 116
Causality, Probability, and Time
Kleinberg, S. (2012) · Cambridge University Press eBooks · doi:10.1017/cbo9781139207799 · Cited by 85
Causal Inference on Time Series using Restricted Structural Equation Models
Peters, J., Janzing, D., & Schölkopf, B. (2013) · Max Planck Digital Library · Cited by 84
AR Identification of Latent-Variable Graphical Models
Zorzi, M., & Sepulchre, R. J. (2015) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2015.2491678 · Cited by 78
Papana, A., Kyrtsou, C., Kugiumtzis, D., & Diks, C. G. H. (2015) · Computational Economics · doi:10.1007/s10614-015-9491-x · Cited by 77
A copula approach to assessing Granger causality
Hu, M., & Liang, H. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2014.06.013 · Cited by 76
On the usefulness of attention for object recognition
Walther, D. B., Rutishauser, U., Koch, C., & Perona, P. (2004) · Cited by 72
Sparse plus low rank network identification: A nonparametric approach
Zorzi, M., & Chiuso, A. (2017) · Automatica · doi:10.1016/j.automatica.2016.08.014 · Cited by 72
Hyvärinen, A., Shimizu, S., & Hoyer, P. O. (2008) · International Conference on Machine Learning · doi:10.1145/1390156.1390210 · Cited by 71
Learning causality and causality-related learning: some recent progress
Zhang, K., Schölkopf, B., Spirtes, P., & Glymour, C. (2017) · National Science Review · doi:10.1093/nsr/nwx137 · Cited by 65
Search for Additive Nonlinear Time Series Causal Models
Chu, T., & Glymour, C. (2008) · Cited by 62
Luo, Q., Ge, T., Fabian Grabenhorst, B., Feng, J., & Rolls, E. T. (2013) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003265 · Cited by 61
Causal Generative Neural NetworksPreprint
Goudet, O., Kalainathan, D., Caillou, P., Guyon, I., López-Paz, D., & Sébag, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.08936 · Cited by 57
Convolutional Sequence Modeling Revisited
Bai, S., Kolter, J. Z., & Koltun, V. (2018) · International Conference on Learning Representations · Cited by 57
An interpretable LSTM neural network for autoregressive exogenous modelPreprint
Guo, T., Lin, T., & Lu, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.05251 · Cited by 43
The relationship between transfer entropy and directed information
Liu, Y., & Aviyente, S. (2012) · doi:10.1109/ssp.2012.6319809 · Cited by 20
Cited by
Deep Learning for Medical Anomaly Detection – A Survey
Fernando, T., Gammulle, H., Denman, S., Sridharan, S., & Fookes, C. (2022) · ACM Computing Surveys · doi:10.1145/3464423 · Cited by 399
Root Cause Analysis in Microservice Using Neural Granger Causal Discovery
Lin, C.-M., Chang, C., Wang, W.-Y., Wang, K.-D., & Peng, W.-C. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i1.27772 · Cited by 39
MRCA: metric-level root cause analysis for microservices via multi-modal data
Wang, Y., Zhu, Z., Fu, Q., Ma, Y., & He, P. (2024) · Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/3691620.3695485 · Cited by 18
Metadata
- Authors
- Nauta, M., Bucur, D., & Seifert, C.
- Venue
- Machine Learning and Knowledge Extraction
- Publisher
- MDPI AG
- Published
- 2019-01-07
- Volume
- 1
- Issue
- 1
- Pages
- 312-340
- ISSN
- 2504-4990 (ISSN-L)
- OpenAlex
- W2908623803
- Cited by
- 262
- References
- 55
- FWCI
- 9.44
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.