# Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version

arXiv: https://arxiv.org/abs/2203.16110 · HTML: https://mlsanity.com/paper/2203.16110/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Graph Representation Learning via Graphical Mutual Information Maximization](https://mlsanity.com/paper/2002.01169/) (2020)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version](https://mlsanity.com/paper/2203.15737/) (2022)
- [Curriculum Pre-training for End-to-End Speech Translation](https://mlsanity.com/paper/2004.10093/) (2020)
- [Predicting Path Failure In Time-Evolving Graphs](https://mlsanity.com/paper/1905.03994/) (2019)
- [DeepCas: an End-to-end Predictor of Information Cascades](https://mlsanity.com/paper/1611.05373/) (2016)
- [AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version](https://mlsanity.com/paper/2112.11174/) (2021)
- [CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation](https://mlsanity.com/paper/2005.00329/) (2020)
- [Unsupervised Path Representation Learning with Curriculum Negative Sampling](https://mlsanity.com/paper/2106.09373/) (2021)
- [Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version](https://mlsanity.com/paper/2111.11108/) (2021)
- [Learning to Route with Sparse Trajectory Sets---Extended Version](https://mlsanity.com/paper/1802.07980/) (2018)

## Built on by (most cited first, 15 of 15)

- [LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version](https://mlsanity.com/paper/2302.12721/) (2023)
- [LightPath: Lightweight and Scalable Path Representation Learning](https://mlsanity.com/paper/2307.10171/) (2023)
- [Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Era](https://mlsanity.com/paper/2403.14151/) (2024)
- [Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting](https://mlsanity.com/paper/2211.16126/) (2022)
- [BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysis](https://mlsanity.com/paper/2412.00953/) (2024)
- [MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version](https://mlsanity.com/paper/2411.18428/) (2024)
- [Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning](https://mlsanity.com/paper/2502.06870/) (2025)
- [Fully Automated Correlated Time Series Forecasting in Minutes](https://mlsanity.com/paper/2411.05833/) (2024)
- [RED: Effective Trajectory Representation Learning with Comprehensive Information](https://mlsanity.com/paper/2411.15096/) (2024)
- [Spatio-Temporal Trajectory Foundation Model - Recent Advances and Future Directions](https://mlsanity.com/paper/2511.20729/) (2025)
- [Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models](https://mlsanity.com/paper/2410.13196/) (2024)
- [Data Driven Decision Making with Time Series and Spatio-temporal Data](https://mlsanity.com/paper/2503.08473/) (2025)
- [REFINE: Trajectory Representation Learning via Closed-Loop Transcription -- Extended Version](https://mlsanity.com/paper/2609.07206/) (2026)
- [DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version](https://mlsanity.com/paper/2609.07316/) (2026)
- [When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning](https://mlsanity.com/paper/2609.15305/) (2026)

## Abstract (arXiv)

In step with the digitalization of transportation, we are witnessing a growing range of path-based smart-city applications, e.g., travel-time estimation and travel path ranking. A temporal path(TP) that includes temporal information, e.g., departure time, into the path is fundamental to enable such applications. In this setting, it is essential to learn generic temporal path representations(TPRs) that consider spatial and temporal correlations simultaneously and that can be used in different applications, i.e., downstream tasks. Existing methods fail to achieve the goal since (i) supervised methods require large amounts of task-specific labels when training and thus fail to generalize the obtained TPRs to other tasks; (ii) through unsupervised methods can learn generic representations, they disregard the temporal aspect, leading to sub-optimal results. To contend with the limitations of existing solutions, we propose a Weakly-Supervised Contrastive (WSC) learning model. We first propose a temporal path encoder that encodes both the spatial and temporal information of a temporal path into a TPR. To train the encoder, we introduce weak labels that are easy and inexpensive to obtain and are relevant to different tasks, e.g., temporal labels indicating peak vs. off-peak hours from departure times. Based on the weak labels, we construct meaningful positive and negative temporal path samples by considering both spatial and temporal information, which facilities training the encoder using contrastive learning by pulling closer to the positive samples' representations while pushing away the negative samples' representations. To better guide contrastive learning, we propose a learning strategy based on Curriculum Learning such that the learning performs from easy to hard training instances. Experiments studies verify the effectiveness of the proposed method.