{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:37:40Z","timestamp":1777696660970,"version":"3.51.4"},"reference-count":30,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2024,7,17]]},"abstract":"<jats:p>We introduce a new inductive bias for learning in dynamic event-based human systems. This is intended to partially address the issue of deep learning in chaotic systems. Instead of fitting the data to polynomial expansions that are expressive enough to approximate the generative functions or of inducing a universal approximator to learn the patterns and inductive bias, we only assume that the relationship between the input features and output classes changes over time, and embed this assumption through a form of dynamic contrastive learning in pre-training, where pre-training labels contain information about the class labels and time periods. We do this by extending and integrating two separate forms of contrastive learning. We note that this approach is not equivalent to inserting an extra feature into the input data that contains time period, because the input data cannot contain the label. We illustrate the approach on a recently designed learning algorithm for event-based graph time-series classification, and demonstrate its value on real-world data.<\/jats:p>","DOI":"10.3233\/ida-230555","type":"journal-article","created":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T12:15:43Z","timestamp":1706271343000},"page":"909-919","source":"Crossref","is-referenced-by-count":0,"title":["Improved learning in human evolutionary systems with dynamic contrastive learning"],"prefix":"10.1177","volume":"28","author":[{"given":"Joseph","family":"Johnson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christophe","family":"Giraud-Carrier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bradley","family":"Hatch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-230555_ref2","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1007\/s10618-016-0483-9","article-title":"The great time series classification bake off: A review and experimental evaluation of recent algorithmic advances","volume":"31","author":"Bagnall","year":"2017","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"2","key":"10.3233\/IDA-230555_ref3","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"5","key":"10.3233\/IDA-230555_ref4","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1086\/228631","article-title":"Power and centrality: A family of measures","volume":"92","author":"Bonacich","year":"1987","journal-title":"American Journal of Sociology"},{"issue":"4","key":"10.3233\/IDA-230555_ref5","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.socnet.2004.08.007","article-title":"Calculating status with negative relations","volume":"26","author":"Bonacich","year":"2004","journal-title":"Social Networks"},{"issue":"5","key":"10.3233\/IDA-230555_ref7","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1037\/h0046049","article-title":"Structural balance: A generalization of heider\u2019s theory","volume":"63","author":"Cartwright","year":"1956","journal-title":"Psychological Review"},{"key":"10.3233\/IDA-230555_ref8","doi-asserted-by":"crossref","first-page":"1997","DOI":"10.1007\/s10994-020-05910-7","article-title":"Evaluating time series forecasting models: An empirical study on performance estimation methods","volume":"109","author":"Cerqueira","year":"2020","journal-title":"Machine Learning"},{"key":"10.3233\/IDA-230555_ref9","unstructured":"N.R. Chilkuri and C. Eliasmith, Parallelizing legendre memory unit training, in: International Conference on Machine Learning, PMLR, 2021, pp. 1898\u20131907."},{"key":"10.3233\/IDA-230555_ref10","doi-asserted-by":"crossref","unstructured":"G. Corani, A. Benavoli and M. Zaffalon, Time series forecasting with gaussian processes needs priors, in: Machine Learning and Knowledge Discovery in Databases, Applied Data Science Track: European Conference, ECML PKDD 2021, Bilbao, Spain, September 13\u201317, 2021, Proceedings, Part IV 21, Springer, 2021, pp. 103\u2013117.","DOI":"10.1007\/978-3-030-86514-6_7"},{"issue":"5","key":"10.3233\/IDA-230555_ref11","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1007\/s10618-020-00701-z","article-title":"Rocket: Exceptionally fast and accurate time series classification using random convolutional kernels","volume":"34","author":"Dempster","year":"2020","journal-title":"Data Mining and Knowledge Discovery"},{"key":"10.3233\/IDA-230555_ref12","doi-asserted-by":"crossref","unstructured":"J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li and L. Fei-Fei, Imagenet: A large-scale hierarchical image database, in: 2009 IEEE Conference on Computer Vision and Pattern Recognition, Ieee, 2009, pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.3233\/IDA-230555_ref14","doi-asserted-by":"crossref","unstructured":"R. Guha, R. Kumar, P. Raghavan and A. Tomkins, Propagation of trust and distrust, in: Proceedings of the 13th International Conference on World Wide Web, ACM, 2004, pp. 403\u2013412.","DOI":"10.1145\/988672.988727"},{"key":"10.3233\/IDA-230555_ref15","first-page":"143","article-title":"On the notion of balance of a signed graph","volume":"2","author":"Harary","journal-title":"Michigan Mathematical Journal"},{"issue":"52","key":"10.3233\/IDA-230555_ref16","first-page":"5","article-title":"Forecasting trends and seasonals by exponentially weighted moving averages","volume":"52","author":"Holt","year":"1957","journal-title":"ONR Memorandum"},{"issue":"8","key":"10.3233\/IDA-230555_ref17","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1073\/pnas.79.8.2554","article-title":"Neural networks and physical systems with emergent collective computational abilities","volume":"79","author":"Hopfield","year":"1982","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.3233\/IDA-230555_ref23","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/IDA-230555_ref25","doi-asserted-by":"crossref","unstructured":"S. Kumar, F. Spezzano, V. Subrahmanian and C. Faloutsos, Edge weight prediction in weighted signed networks, in: 2016 IEEE 16th International Conference on Data Mining (ICDM), IEEE, 2016, pp. 221\u2013230.","DOI":"10.1109\/ICDM.2016.0033"},{"issue":"6","key":"10.3233\/IDA-230555_ref26","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1109\/TCSS.2020.3023729","article-title":"The family of assortativity coefficients in signed social networks","volume":"7","author":"Li","year":"2020","journal-title":"IEEE Transactions on Computational Social Systems"},{"issue":"5","key":"10.3233\/IDA-230555_ref30","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1177\/0022343316663032","article-title":"Organized violence, 1989\u20132015","volume":"53","author":"Melander","year":"2016","journal-title":"Journal of Peace Research"},{"key":"10.3233\/IDA-230555_ref31","first-page":"11297","article-title":"On the difficulty of learning chaotic dynamics with rnns","volume":"35","author":"Mikhaeil","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/IDA-230555_ref32","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1007577530334","article-title":"Prequential and cross-validated regression estimation","volume":"33","author":"Modha","year":"1998","journal-title":"Machine Learning"},{"issue":"20","key":"10.3233\/IDA-230555_ref33","doi-asserted-by":"crossref","first-page":"208701","DOI":"10.1103\/PhysRevLett.89.208701","article-title":"Assortative mixing in networks","volume":"89","author":"Newman","year":"2002","journal-title":"Physical Review Letters"},{"key":"10.3233\/IDA-230555_ref34","doi-asserted-by":"crossref","unstructured":"A. Nguyen, J. Yosinski and J. Clune, Deep neural networks are easily fooled: High confidence predictions for unrecognizable images, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp.\u00a0427\u2013436.","DOI":"10.1109\/CVPR.2015.7298640"},{"issue":"3","key":"10.3233\/IDA-230555_ref37","doi-asserted-by":"crossref","first-page":"e0118432","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the roc plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PloS One"},{"key":"10.3233\/IDA-230555_ref38","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1007\/s10618-014-0377-7","article-title":"The boss is concerned with time series classification in the presence of noise","volume":"29","author":"Sch\u00e4fer","year":"2015","journal-title":"Data Mining and Knowledge Discovery"},{"key":"10.3233\/IDA-230555_ref39","unstructured":"P. Sch\u00e4fer and M. H\u00f6gqvist, Sfa: a symbolic fourier approximation and index for similarity search in high dimensional datasets, in: Proceedings of the 15th International Conference on Extending Database Technology, 2012, pp. 516\u2013527."},{"key":"10.3233\/IDA-230555_ref40","doi-asserted-by":"crossref","unstructured":"P. Sermanet, C. Lynch, Y. Chebotar, J. Hsu, E. Jang, S. Schaal, S. Levine and G. Brain, Time-contrastive networks: Self-supervised learning from video, in: 2018 IEEE International Conference on Robotics and Automation (ICRA), IEEE, 2018, pp. 1134\u20131141.","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"10.3233\/IDA-230555_ref41","doi-asserted-by":"crossref","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich, Going deeper with convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"7","key":"10.3233\/IDA-230555_ref45","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1162\/neco.1996.8.7.1341","article-title":"The lack of a priori distinctions between learning algorithms","volume":"8","author":"Wolpert","year":"1996","journal-title":"Neural Computation"},{"issue":"7310","key":"10.3233\/IDA-230555_ref47","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.1038\/nature09319","article-title":"Statistical inference for noisy nonlinear ecological dynamic systems","volume":"466","author":"Wood","year":"2010","journal-title":"Nature"},{"key":"10.3233\/IDA-230555_ref48","doi-asserted-by":"crossref","unstructured":"M.D. Zeiler and R. Fergus, Visualizing and understanding convolutional networks, in: Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part I 13, Springer, 2014, pp. 818\u2013833.","DOI":"10.1007\/978-3-319-10590-1_53"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-230555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:20:38Z","timestamp":1777454438000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-230555"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,17]]},"references-count":30,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/ida-230555","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,17]]}}}