Networks enable the modeling of complex relationships among entities, where the properties of the relationships are often dynamic and uncertain. A road network, where nodes represent road junctions and edges represent roads, is an example of such dynamic, uncertain networks. The travel times of roads are dynamic due to varying traffic volumes and are also uncertain due to diverse driving behaviors and various events such as accidents and concerts.
The ADVANCE project aims at fleshing out a data-intensive paradigm to enable dynamic, uncertain networks, with a focus on applications in transportation. The project aims at (i) inventing means of learning accurately the dynamic and uncertain travel times from big trajectory data and (ii) inventing new routing algorithms that are able to utilize the captured dynamic, uncertain travel times.
ADVANCE is a project at Center for Data-Intensive Systems (Daisy), Aalborg University. It is funded by the Sapere Aude Research Leader programme, Independent Research Fund Denmark (IRFD) under agreement 8048-00038B and by the Department of Computer Science, Aalborg University.
Shufang Xie, Peng Han, Yingce Xia, Lijun Wu, Tao Qin, Chenjuan Guo, Bin Yang, and Rui Yan.
RetroGraph: Retrosynthetic Planning with Graph Search.
KDD 2022, To appear.
Sean Bin Yang, Chenjuan Guo, Jilin Hu, Bin Yang, Jian Tang, and Christian S. Jensen.
Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning.
ICDE 2022, To appear.
Miao Zhang, Shirui Pan, Xiaojun Chang, Steven Su, Jilin Hu, Reza Haffari, and Bin Yang.
BaLeNAS: Differentiable Architecture Search via Bayesian Learning Rule.
CVPR 2022, To appear.
David Campos, Tung Kieu, Chenjuan Guo, Feiteng Huang, Kai Zheng, Bin Yang, and Christian S. Jensen.
Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles.
PVLDB 2022, to appear.
Xinle Wu, Dalin Zhang, Chenjuan Guo, Chaoyang He, Bin Yang, and Christian S. Jensen.
AutoCTS: Automated Correlated Time Series Forecasting.
PVLDB 2022, to appear.
Sean Bin Yang, Chenjuan Guo, Jilin Hu, Jian Tang, and Bin Yang.
Unsupervised Path Representation Learning with Curriculum Negative Sampling.
IJCAI 2021: 3286-3292.
Sean Bin Yang, Chenjuan Guo, and Bin Yang.
Context-Aware Path Ranking in Road Networks.
TKDE, to appear.
Simon Aagaard Pedersen, Bin Yang, and Christian S. Jensen.
Anytime Stochastic Routing with Hybrid Learning.
PVLDB 13(9): 1555-1567 (2020).
Razvan-Gabriel Cirstea, Hilmar Gústafsson, Rasmus Riis Grønbæk Pedersen, Rolf Hakon Verder Sehested, Tamas Imre Winkler, and Bin Yang
A Road Segment Attribute Completion System.
IEEE MDM 2020, Demo paper.
Chenjuan Guo, Bin Yang, Jilin Hu, Christian S. Jensen, and Lu Chen.
Context-Aware, Preference-Based Vehicle Routing.
The VLDB Journal, to appear.
Jilin Hu, Bin Yang, Chenjuan Guo, Christian S. Jensen, and Hui Xiong.
Stochastic Origin-Destination Matrix Forecasting Using Dual-Stage Graph Convolutional, Recurrent Neural Networks.
ICDE 2020, 1417-1428.
Sean Bin Yang, and Bin Yang.
Learning to Rank Paths in Spatial Networks
ICDE 2020, 2006-2009.
Simon Aagaard Pedersen, Bin Yang, and Christian S. Jensen.
A Hybrid Learning Approach to Stochastic Routing
ICDE 2020, 2010-2013.
Simon Aagaard Pedersen, Bin Yang, and Christian S. Jensen.
Fast Stochastic Routing under Time-Varying Uncertainty.
The VLDB Journal 29(4): 819-839 (2020).
Jilin Hu, Chenjuan Guo, Bin Yang, and Christian S. Jensen.
Stochastic Weight Completion for Road Networks using Graph Convolutional Networks.
ICDE 2019, 1274-1285.
Christopher Hansen Nielsen, Simon Makne Randers
Estimating Travel Cost Distributions of Paths in Road Networks using Dual-Input LSTMs.
Aalborg University, 2020.
Ivan Iliev
Predicting Stochastic Demand using a Multi-Task Recurrent Mixture Density Network.
Aalborg University, 2020.
Jakob Meldgaard Kjær, Lasse Kristensen, Mads Alberg Christensen
Partitioned Graph Convolution using Adversarial and Regression Networks for Road Travel Speed Prediction.
Aalborg University, 2020.
Laurids Vinther Kirkeby, Mikkel Elkjær Holm
Utilizing Mixture Density Networks for Travel Time Probability Distribution Predictions.
Aalborg University, 2020.
If you are interested in hearing more about the ADVANCE project or a possible partnership, please contact Bin Yang by email byang@cs.aau.dk or by phone +45 9940 9976.