# Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting

arXiv: https://arxiv.org/abs/2110.10380 · HTML: https://mlsanity.com/paper/2110.10380/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 20 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [Learning to Remember Rare Events](https://mlsanity.com/paper/1703.03129/) (2017)

## Built on by (most cited first, 19 of 19)

- [Spatio-Temporal Meta-Graph Learning for Traffic Forecasting](https://mlsanity.com/paper/2211.14701/) (2022)
- [Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank](https://mlsanity.com/paper/2308.09727/) (2023)
- [TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts](https://mlsanity.com/paper/2403.02600/) (2024)
- [Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting](https://mlsanity.com/paper/2405.10800/) (2024)
- [STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting](https://mlsanity.com/paper/2308.10425/) (2023)
- [DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps](https://mlsanity.com/paper/2208.06979/) (2022)
- [TILDE-Q: A Transformation Invariant Loss Function for Time-Series Forecasting](https://mlsanity.com/paper/2210.15050/) (2022)
- [Multi-scale Traffic Pattern Bank for Cross-city Few-shot Traffic Forecasting](https://mlsanity.com/paper/2402.00397/) (2024)
- [XXLTraffic: Expanding and Extremely Long Traffic forecasting beyond test adaptation](https://mlsanity.com/paper/2406.12693/) (2024)
- [FDTI: Fine-grained Deep Traffic Inference with Roadnet-enriched Graph](https://mlsanity.com/paper/2306.10945/) (2023)
- [MegaCRN: Meta-Graph Convolutional Recurrent Network for Spatio-Temporal Modeling](https://mlsanity.com/paper/2212.05989/) (2022)
- [Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting](https://mlsanity.com/paper/2411.09251/) (2024)
- [ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting](https://mlsanity.com/paper/2509.13753/) (2025)
- [Dynamic Sheaf Diffusion Networks with Adaptive Local Structure for Heterogeneous Spatio-Temporal Graph Learning](https://mlsanity.com/paper/2604.11275/) (2026)
- [From XXLTraffic to EvoXXLTraffic: Scaling Traffic Forecasting to Sensor-Evolving Networks](https://mlsanity.com/paper/2605.29768/) (2026)
- [STLGRU: Spatio-Temporal Lightweight Graph GRU for Traffic Flow Prediction](https://mlsanity.com/paper/2212.04548/) (2022)
- [Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction](https://mlsanity.com/paper/2408.07100/) (2024)
- [Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting](https://mlsanity.com/paper/2411.11448/) (2024)
- [Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting](https://mlsanity.com/paper/2512.09398/) (2025)

## Abstract (arXiv)

Traffic forecasting is a challenging problem due to complex road networks and sudden speed changes caused by various events on roads. A number of models have been proposed to solve this challenging problem with a focus on learning spatio-temporal dependencies of roads. In this work, we propose a new perspective of converting the forecasting problem into a pattern matching task, assuming that large data can be represented by a set of patterns. To evaluate the validness of the new perspective, we design a novel traffic forecasting model, called Pattern-Matching Memory Networks (PM-MemNet), which learns to match input data to the representative patterns with a key-value memory structure. We first extract and cluster representative traffic patterns, which serve as keys in the memory. Then via matching the extracted keys and inputs, PM-MemNet acquires necessary information of existing traffic patterns from the memory and uses it for forecasting. To model spatio-temporal correlation of traffic, we proposed novel memory architecture GCMem, which integrates attention and graph convolution for memory enhancement. The experiment results indicate that PM-MemNet is more accurate than state-of-the-art models, such as Graph WaveNet with higher responsiveness. We also present a qualitative analysis result, describing how PM-MemNet works and achieves its higher accuracy when road speed rapidly changes.