Self-Supervised Contrastive Learning for Individual and Collective Outlier Detection in Semantic Trajectories
Open Access
- 24 April 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 12 (4) , 1-27
Abstract
Semantic trajectories enrich spatiotemporal data with textual semantics such as trip purposes and activities at points of interest, enabling the discovery of outlier behaviors relevant to public health, social security, and urban planning. Existing detectors often depend on hand crafted rules and rarely fuse space, time, and text in a transferable way. We propose TOD4Traj , an unsupervised and transfer ready framework for human semantic trajectories that detects anomalies at both the individual and collective levels. TOD4Traj first unifies modalities through spatiotemporal to semantic contrastive alignment so heterogeneous signals share a common representation. It then learns regular mobility via temporal contrastive learning that aligns the same weekday and separates different weekdays. Deviations are scored by combining a consistency score against a user’s own history with a population score based on a small set of learned centroids that capture low rank mobility regularities. For group analysis, we introduce a population level contrastive objective and a collective outlier score that compare a date’s population embedding with historical weekday prototypes, revealing collective abnormality. Across simulated cities and a GeoLife derived dataset, TOD4Traj consistently outperforms strong baselines on both tasks and shows robust zero shot transfer across cities, demonstrating effectiveness, robustness, and adaptability for outlier detection in human semantic trajectories.Keywords
Funding Information
- Intelligence Advanced Research Projects Activity
- Interior Business Center (140D0423C0025)
- NSF (No. 2432418, No. 2414115, No. 2007716, No. 2007976, No. 1942594, No. 1907805, No. 2318831, and No. 2125530)
This publication has 46 references indexed in Scilit:
- Predicting building types using OpenStreetMapScientific Reports, 2022
- Urban life: a model of people and placesComputational and Mathematical Organization Theory, 2021
- RUTOD: real-time urban traffic outlier detection on streaming trajectoryNeural Computing and Applications, 2021
- STCCD: Semantic trajectory clustering based on community detection in networksExpert Systems with Applications, 2020
- A hierarchical autoencoder learning model for path prediction and abnormality detectionPattern Recognition Letters, 2020
- An overview on trajectory outlier detectionArtificial Intelligence Review, 2018
- Popularity-aware spatial keyword search on activity trajectoriesWorld Wide Web, 2016
- Entropy-based outlier detection using semi-supervised approach with few positive examplesPattern Recognition Letters, 2014
- Characteristics and classification of outlier detection techniques for wireless sensor networks in harsh environments: a surveyArtificial Intelligence Review, 2012
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998