# ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting

arXiv: https://arxiv.org/abs/2002.04155 · HTML: https://mlsanity.com/paper/2002.04155/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2020.

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

- [Deterministic Guidance Diffusion Model for Probabilistic Weather Forecasting](https://mlsanity.com/paper/2312.02819/) (2023)
- [Masked Multi-Step Probabilistic Forecasting for Short-to-Mid-Term Electricity Demand](https://mlsanity.com/paper/2302.06818/) (2023)
- [Masked Multi-Step Multivariate Time Series Forecasting with Future Information](https://mlsanity.com/paper/2209.14413/) (2022)
- [MatrixNet: Learning over symmetry groups using learned group representations](https://mlsanity.com/paper/2501.09571/) (2025)
- [AutoTS: Automatic Time Series Forecasting Model Design Based on Two-Stage Pruning](https://mlsanity.com/paper/2203.14169/) (2022)
- [Deep Learning for Prawn Farming: Forecasting and Anomaly Detection](https://mlsanity.com/paper/2205.06359/) (2022)
- [Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports](https://mlsanity.com/paper/2111.13812/) (2021)

## Abstract (arXiv)

Recurrent and convolutional neural networks are the most common architectures used for time series forecasting in deep learning literature. These networks use parameter sharing by repeating a set of fixed architectures with fixed parameters over time or space. The result is that the overall architecture is time-invariant (shift-invariant in the spatial domain) or stationary. We argue that time-invariance can reduce the capacity to perform multi-step-ahead forecasting, where modelling the dynamics at a range of scales and resolutions is required. We propose ForecastNet which uses a deep feed-forward architecture to provide a time-variant model. An additional novelty of ForecastNet is interleaved outputs, which we show assist in mitigating vanishing gradients. ForecastNet is demonstrated to outperform statistical and deep learning benchmark models on several datasets.