Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Jointly Contrastive Representation Learning on Road Network and Trajectory

About

Road network and trajectory representation learning are essential for traffic systems since the learned representation can be directly used in various downstream tasks (e.g., traffic speed inference, and travel time estimation). However, most existing methods only contrast within the same scale, i.e., treating road network and trajectory separately, which ignores valuable inter-relations. In this paper, we aim to propose a unified framework that jointly learns the road network and trajectory representations end-to-end. We design domain-specific augmentations for road-road contrast and trajectory-trajectory contrast separately, i.e., road segment with its contextual neighbors and trajectory with its detour replaced and dropped alternatives, respectively. On top of that, we further introduce the road-trajectory cross-scale contrast to bridge the two scales by maximizing the total mutual information. Unlike the existing cross-scale contrastive learning methods on graphs that only contrast a graph and its belonging nodes, the contrast between road segment and trajectory is elaborately tailored via novel positive sampling and adaptive weighting strategies. We conduct prudent experiments based on two real-world datasets with four downstream tasks, demonstrating improved performance and effectiveness. The code is available at https://github.com/mzy94/JCLRNT.

Zhenyu Mao, Ziyue Li, Dedong Li, Lei Bai, Rui Zhao• 2022

Related benchmarks

TaskDatasetResultRank
Destination PredictionBeijing
Top-5 Accuracy18.79
28
Destination PredictionPorto
Acc@535.08
28
Trajectory Similarity SearchPorto (test)
HR@10.8064
24
Estimated Time of ArrivalPorto
MAPE (%)25.44
21
Path RankingXi'an
Kendall's Tau0.7024
13
Similar Trajectory RetrievalBeijing (test)
HR@189.85
13
Road Label PredictionChengdu (test)
Macro F1 Score63.76
13
Path RankingBeijing
Kendall's τ0.6352
13
Path RankingChengdu
Kendall's τ0.7526
13
Similar Trajectory RetrievalChengdu (test)
HR@175.21
13
Showing 10 of 20 rows

Other info

Follow for update