# Deep Imbalanced Time-series Forecasting via Local Discrepancy Density

arXiv: https://arxiv.org/abs/2302.13563 · HTML: https://mlsanity.com/paper/2302.13563/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 27 Feb 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)

## Built on by (most cited first, 7 of 7)

- [Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization](https://mlsanity.com/paper/2308.06879/) (2023)
- [Self-Supervised Contrastive Learning for Long-term Forecasting](https://mlsanity.com/paper/2402.02023/) (2024)
- [Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Models](https://mlsanity.com/paper/2506.00457/) (2025)
- [Loss Shaping Constraints for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2402.09373/) (2024)
- [Goal-Oriented Time-Series Forecasting: Foundation Framework Design](https://mlsanity.com/paper/2504.17493/) (2025)
- [Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling](https://mlsanity.com/paper/2411.14042/) (2024)
- [Class-Aware Contrastive Optimization for Imbalanced Text Classification](https://mlsanity.com/paper/2410.22197/) (2024)

## Abstract (arXiv)

Time-series forecasting models often encounter abrupt changes in a given period of time which generally occur due to unexpected or unknown events. Despite their scarce occurrences in the training set, abrupt changes incur loss that significantly contributes to the total loss. Therefore, they act as noisy training samples and prevent the model from learning generalizable patterns, namely the normal states. Based on our findings, we propose a reweighting framework that down-weights the losses incurred by abrupt changes and up-weights those by normal states. For the reweighting framework, we first define a measurement termed Local Discrepancy (LD) which measures the degree of abruptness of a change in a given period of time. Since a training set is mostly composed of normal states, we then consider how frequently the temporal changes appear in the training set based on LD. Our reweighting framework is applicable to existing time-series forecasting models regardless of the architectures. Through extensive experiments on 12 time-series forecasting models over eight datasets with various in-output sequence lengths, we demonstrate that applying our reweighting framework reduces MSE by 10.1% on average and by up to 18.6% in the state-of-the-art model.