# Dual-branch Spatial-Temporal Self-supervised Representation for Enhanced Road Network Learning

arXiv: https://arxiv.org/abs/2511.06633 · HTML: https://mlsanity.com/paper/2511.06633/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [An Empirical Study of Graph Contrastive Learning](https://mlsanity.com/paper/2109.01116/) (2021)
- [Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics](https://mlsanity.com/paper/2211.09510/) (2022)
- [Continuous Trajectory Generation Based on Two-Stage GAN](https://mlsanity.com/paper/2301.07103/) (2023)
- [Jointly Contrastive Representation Learning on Road Network and Trajectory](https://mlsanity.com/paper/2209.06389/) (2022)
- [COLA: Cross-city Mobility Transformer for Human Trajectory Simulation](https://mlsanity.com/paper/2403.01801/) (2024)
- [Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition](https://mlsanity.com/paper/2211.12712/) (2022)
- [Graph Convolutional Networks for Road Networks](https://mlsanity.com/paper/1908.11567/) (2019)
- [Spatiotemporal-Augmented Graph Neural Networks for Human Mobility Simulation](https://mlsanity.com/paper/2306.09381/) (2023)
- [Road Network Representation Learning with the Third Law of Geography](https://mlsanity.com/paper/2406.04038/) (2024)
- [Graph Representation Learning for Road Type Classification](https://mlsanity.com/paper/2107.07791/) (2021)
- [Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation](https://mlsanity.com/paper/2304.07503/) (2023)
- [Holistic Semantic Representation for Navigational Trajectory Generation](https://mlsanity.com/paper/2501.02737/) (2025)
- [Transition Propagation Graph Neural Networks for Temporal Networks](https://mlsanity.com/paper/2304.07501/) (2023)
- [Semantic-Enhanced Representation Learning for Road Networks with Temporal Dynamics](https://mlsanity.com/paper/2403.11495/) (2024)

## Built on by (most cited first, 1 of 1)

- [MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification](https://mlsanity.com/paper/2604.26774/) (2026)

## Abstract (arXiv)

Road network representation learning (RNRL) has attracted increasing attention from both researchers and practitioners as various spatiotemporal tasks are emerging. Recent advanced methods leverage Graph Neural Networks (GNNs) and contrastive learning to characterize the spatial structure of road segments in a self-supervised paradigm. However, spatial heterogeneity and temporal dynamics of road networks raise severe challenges to the neighborhood smoothing mechanism of self-supervised GNNs. To address these issues, we propose a Dual-branch Spatial-Temporal self-supervised representation framework for enhanced road representations, termed as DST. On one hand, DST designs a mix-hop transition matrix for graph convolution to incorporate dynamic relations of roads from trajectories. Besides, DST contrasts road representations of the vanilla road network against that of the hypergraph in a spatial self-supervised way. The hypergraph is newly built based on three types of hyperedges to capture long-range relations. On the other hand, DST performs next token prediction as the temporal self-supervised task on the sequences of traffic dynamics based on a causal Transformer, which is further regularized by differentiating traffic modes of weekdays from those of weekends. Extensive experiments against state-of-the-art methods verify the superiority of our proposed framework. Moreover, the comprehensive spatiotemporal modeling facilitates DST to excel in zero-shot learning scenarios.