# Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting

arXiv: https://arxiv.org/abs/2410.12593 · HTML: https://mlsanity.com/paper/2410.12593/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 60 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Builds on (most cited first, 30 of 36)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)
- [Deep Learning for Spatio-Temporal Data Mining: A Survey](https://mlsanity.com/paper/1906.04928/) (2019)
- [Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2208.05233/) (2022)
- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams](https://mlsanity.com/paper/2009.00919/) (2020)
- [Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey](https://mlsanity.com/paper/2303.14483/) (2023)
- [LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting](https://mlsanity.com/paper/2306.08259/) (2023)
- [Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis](https://mlsanity.com/paper/2310.06119/) (2023)
- [UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction](https://mlsanity.com/paper/2402.11838/) (2024)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [AirFormer: Predicting Nationwide Air Quality in China with Transformers](https://mlsanity.com/paper/2211.15979/) (2022)
- [Scalable Spatiotemporal Graph Neural Networks](https://mlsanity.com/paper/2209.06520/) (2022)
- [ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation](https://mlsanity.com/paper/2312.01728/) (2023)
- [TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning](https://mlsanity.com/paper/2106.06273/) (2021)
- [A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data](https://mlsanity.com/paper/2404.14999/) (2024)
- [Taming Local Effects in Graph-based Spatiotemporal Forecasting](https://mlsanity.com/paper/2302.04071/) (2023)
- [Low-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputation](https://mlsanity.com/paper/2104.14936/) (2021)
- [A Nonconvex Low-Rank Tensor Completion Model for Spatiotemporal Traffic Data Imputation](https://mlsanity.com/paper/2003.10271/) (2020)
- [Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting](https://mlsanity.com/paper/2405.10800/) (2024)
- [FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction](https://mlsanity.com/paper/2405.17898/) (2024)

## Built on by (most cited first, 10 of 10)

- [Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting](https://mlsanity.com/paper/2506.00635/) (2025)
- [Spatiotemporal Causal Decoupling Model for Air Quality Forecasting](https://mlsanity.com/paper/2505.20119/) (2025)
- [UrbanFM: Scaling Urban Spatio-Temporal Foundation Models](https://mlsanity.com/paper/2602.20677/) (2026)
- [Select, then Balance: Exploring Exogenous Variable Modeling of Spatio-Temporal Forecasting](https://mlsanity.com/paper/2509.05779/) (2025)
- [MixTTE: Multi-Level Mixture-of-Experts for Scalable and Adaptive Travel Time Estimation](https://mlsanity.com/paper/2601.02943/) (2026)
- [Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training](https://mlsanity.com/paper/2602.19113/) (2026)
- [CoMemNet: A Continual Memory Network with Drift-Aware Sampling for Traffic Prediction](https://mlsanity.com/paper/2605.05738/) (2026)
- [A2TTA: Anchored-and-Agile Test-Time Adaptation for Evolving Traffic Sensor Networks](https://mlsanity.com/paper/2607.25875/) (2026)
- [RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction](https://mlsanity.com/paper/2608.20656/) (2026)
- [More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting](https://mlsanity.com/paper/2609.31325/) (2026)

## Abstract (arXiv)

The widespread deployment of sensing devices leads to a surge in data for spatio-temporal forecasting applications such as traffic flow, air quality, and wind energy. Although spatio-temporal graph neural networks have achieved success in modeling various static spatio-temporal forecasting scenarios, real-world spatio-temporal data are typically received in a streaming manner, and the network continuously expands with the installation of new sensors. Thus, spatio-temporal forecasting in streaming scenarios faces dual challenges: the inefficiency of retraining models over newly arrived data and the detrimental effects of catastrophic forgetting over long-term history. To address these challenges, we propose a novel prompt tuning-based continuous forecasting method, following two fundamental tuning principles guided by empirical and theoretical analysis: expand and compress, which effectively resolve the aforementioned problems with lightweight tuning parameters. Specifically, we integrate the base spatio-temporal graph neural network with a continuous prompt pool, utilizing stored prompts (i.e., few learnable parameters) in memory, and jointly optimize them with the base spatio-temporal graph neural network. This method ensures that the model sequentially learns from the spatio-temporal data stream to accomplish tasks for corresponding periods. Extensive experimental results on multiple real-world datasets demonstrate the multi-faceted superiority of our method over the state-of-the-art baselines, including effectiveness, efficiency, universality, etc.