# Time Series Forecasting with Hypernetworks Generating Parameters in Advance

arXiv: https://arxiv.org/abs/2211.12034 · HTML: https://mlsanity.com/paper/2211.12034/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [Neural Controlled Differential Equations for Irregular Time Series](https://mlsanity.com/paper/2005.08926/) (2020)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series](https://mlsanity.com/paper/1905.12374/) (2019)
- [Personalized Federated Learning using Hypernetworks](https://mlsanity.com/paper/2103.04628/) (2021)
- [Latent ODEs for Irregularly-Sampled Time Series](https://mlsanity.com/paper/1907.03907/) (2019)
- [Graph HyperNetworks for Neural Architecture Search](https://mlsanity.com/paper/1810.05749/) (2018)
- [Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case](https://mlsanity.com/paper/2001.08317/) (2020)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [Deep Subdomain Adaptation Network for Image Classification](https://mlsanity.com/paper/2106.09388/) (2021)
- [Bayesian Hypernetworks](https://mlsanity.com/paper/1710.04759/) (2017)
- [Deep Meta Functionals for Shape Representation](https://mlsanity.com/paper/1908.06277/) (2019)
- [GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/2210.02040/) (2022)
- [Hyper-Graph-Network Decoders for Block Codes](https://mlsanity.com/paper/1909.09036/) (2019)
- [Implicit Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1711.01297/) (2017)
- [Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems](https://mlsanity.com/paper/2011.10616/) (2020)
- [EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting](https://mlsanity.com/paper/2204.08771/) (2022)
- [Transferable Time-Series Forecasting under Causal Conditional Shift](https://mlsanity.com/paper/2111.03422/) (2021)
- [ANODEV2: A Coupled Neural ODE Evolution Framework](https://mlsanity.com/paper/1906.04596/) (2019)
- [Relaxed Parameter Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series](https://mlsanity.com/paper/1906.02898/) (2019)

## Built on by (most cited first, 4 of 4)

- [Structural Knowledge Informed Continual Multivariate Time Series Forecasting](https://mlsanity.com/paper/2402.12722/) (2024)
- [Forecasting with Hyper-Trees](https://mlsanity.com/paper/2405.07836/) (2024)
- [HN-MVTS: HyperNetwork-based Multivariate Time Series Forecasting](https://mlsanity.com/paper/2511.08340/) (2025)
- [AdaCast: Conditional Parameter Generation for Adaptive Time Series Forecasting](https://mlsanity.com/paper/2610.12240/) (2026)

## Abstract (arXiv)

Forecasting future outcomes from recent time series data is not easy, especially when the future data are different from the past (i.e. time series are under temporal drifts). Existing approaches show limited performances under data drifts, and we identify the main reason: It takes time for a model to collect sufficient training data and adjust its parameters for complicated temporal patterns whenever the underlying dynamics change. To address this issue, we study a new approach; instead of adjusting model parameters (by continuously re-training a model on new data), we build a hypernetwork that generates other target models' parameters expected to perform well on the future data. Therefore, we can adjust the model parameters beforehand (if the hypernetwork is correct). We conduct extensive experiments with 6 target models, 6 baselines, and 4 datasets, and show that our HyperGPA outperforms other baselines.