# CausalTAD: Causal Implicit Generative Model for Debiased Online Trajectory Anomaly Detection

arXiv: https://arxiv.org/abs/2412.18820 · HTML: https://mlsanity.com/paper/2412.18820/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 55 references that are in the map.
- First posted on arXiv 25 Dec 2024.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)
- [Deep Stable Learning for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2104.07876/) (2021)
- [Visual Commonsense R-CNN](https://mlsanity.com/paper/2002.12204/) (2020)
- [Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates](https://mlsanity.com/paper/2005.00649/) (2020)
- [Stable Prediction across Unknown Environments](https://mlsanity.com/paper/1806.06270/) (2018)
- [Deconfounded Recommendation for Alleviating Bias Amplification](https://mlsanity.com/paper/2105.10648/) (2021)
- [Spatio-Temporal Trajectory Similarity Measures: A Comprehensive Survey and Quantitative Study](https://mlsanity.com/paper/2303.05012/) (2023)
- [Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning](https://mlsanity.com/paper/2211.08415/) (2022)
- [Coupled IGMM-GANs for deep multimodal anomaly detection in human mobility data](https://mlsanity.com/paper/1809.02728/) (2018)

## Built on by (most cited first, 6 of 6)

- [Spatio-Temporal Trajectory Foundation Model - Recent Advances and Future Directions](https://mlsanity.com/paper/2511.20729/) (2025)
- [Towards Physics-informed Diffusion for Anomaly Detection in Trajectories](https://mlsanity.com/paper/2506.06999/) (2025)
- [Graph Enhanced Trajectory Anomaly Detection](https://mlsanity.com/paper/2509.18386/) (2025)
- [Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization](https://mlsanity.com/paper/2601.21078/) (2026)
- [CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection](https://mlsanity.com/paper/2511.16929/) (2025)
- [When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning](https://mlsanity.com/paper/2609.15305/) (2026)

## Abstract (arXiv)

Trajectory anomaly detection, aiming to estimate the anomaly risk of trajectories given the Source-Destination (SD) pairs, has become a critical problem for many real-world applications. Existing solutions directly train a generative model for observed trajectories and calculate the conditional generative probability P(T|C) as the anomaly risk, where T and C represent the trajectory and SD pair respectively. However, we argue that the observed trajectories are confounded by road network preference which is a common cause of both SD distribution and trajectories. Existing methods ignore this issue limiting their generalization ability on out-of-distribution trajectories. In this paper, we define the debiased trajectory anomaly detection problem and propose a causal implicit generative model, namely CausalTAD, to solve it. CausalTAD adopts do-calculus to eliminate the confounding bias of road network preference and estimates P(T|do(C)) as the anomaly criterion. Extensive experiments show that CausalTAD can not only achieve superior performance on trained trajectories but also generally improve the performance of out-of-distribution data, with improvements of 2.1% ~ 5.7% and 10.6% ~ 32.7% respectively.