# Universal hidden monotonic trend estimation with contrastive learning

arXiv: https://arxiv.org/abs/2210.09817 · HTML: https://mlsanity.com/paper/2210.09817/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning](https://mlsanity.com/paper/1805.08651/) (2018)
- [Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA](https://mlsanity.com/paper/1605.06336/) (2016)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [A Survey of Label-noise Representation Learning: Past, Present and Future](https://mlsanity.com/paper/2011.04406/) (2020)
- [Likelihood-free inference by ratio estimation](https://mlsanity.com/paper/1611.10242/) (2016)
- [Self-supervised representation learning from electroencephalography signals](https://mlsanity.com/paper/1911.05419/) (2019)
- [Likelihood-free inference via classification](https://mlsanity.com/paper/1407.4981/) (2014)
- [Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening](https://mlsanity.com/paper/1808.08833/) (2018)
- [Robust contrastive learning and nonlinear ICA in the presence of outliers](https://mlsanity.com/paper/1911.00265/) (2019)
- [Time Series Source Separation with Slow Flows](https://mlsanity.com/paper/2007.10182/) (2020)
- [Serial-EMD: Fast Empirical Mode Decomposition Method for Multi-dimensional Signals Based on Serialization](https://mlsanity.com/paper/2106.15319/) (2021)

## Abstract (arXiv)

In this paper, we describe a universal method for extracting the underlying monotonic trend factor from time series data. We propose an approach related to the Mann-Kendall test, a standard monotonic trend detection method and call it contrastive trend estimation (CTE). We show that the CTE method identifies any hidden trend underlying temporal data while avoiding the standard assumptions used for monotonic trend identification. In particular, CTE can take any type of temporal data (vector, images, graphs, time series, etc.) as input. We finally illustrate the interest of our CTE method through several experiments on different types of data and problems.