# Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting

arXiv: https://arxiv.org/abs/2302.08635 · HTML: https://mlsanity.com/paper/2302.08635/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Builds on (most cited first, 27 of 27)

- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction](https://mlsanity.com/paper/2002.11927/) (2020)
- [DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents](https://mlsanity.com/paper/1704.04394/) (2017)
- [It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction](https://mlsanity.com/paper/2004.02025/) (2020)
- [Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks](https://mlsanity.com/paper/1907.03395/) (2019)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning](https://mlsanity.com/paper/1809.08835/) (2018)
- [Human Trajectory Forecasting in Crowds: A Deep Learning Perspective](https://mlsanity.com/paper/2007.03639/) (2020)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [Composing graphical models with neural networks for structured representations and fast inference](https://mlsanity.com/paper/1603.06277/) (2016)
- [Learning Neural Causal Models from Unknown Interventions](https://mlsanity.com/paper/1910.01075/) (2019)
- [Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness](https://mlsanity.com/paper/1811.00007/) (2018)
- [External Validity: From Do-Calculus to Transportability Across Populations](https://mlsanity.com/paper/1503.01603/) (2015)
- [Identifiability of deep generative models without auxiliary information](https://mlsanity.com/paper/2206.10044/) (2022)
- [Learning Causal Semantic Representation for Out-of-Distribution Prediction](https://mlsanity.com/paper/2011.01681/) (2020)
- [Few-shot Domain Adaptation by Causal Mechanism Transfer](https://mlsanity.com/paper/2002.03497/) (2020)
- [Human Trajectory Prediction via Counterfactual Analysis](https://mlsanity.com/paper/2107.14202/) (2021)
- [Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective](https://mlsanity.com/paper/2111.14820/) (2021)
- [Domain Adaptation as a Problem of Inference on Graphical Models](https://mlsanity.com/paper/2002.03278/) (2020)
- [Causal Generative Neural Networks](https://mlsanity.com/paper/1711.08936/) (2017)
- [Learning causal representations for robust domain adaptation](https://mlsanity.com/paper/2011.06317/) (2020)
- [On the Necessity and Effectiveness of Learning the Prior of Variational Auto-Encoder](https://mlsanity.com/paper/1905.13452/) (2019)

## Built on by (most cited first, 13 of 13)

- [Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference](https://mlsanity.com/paper/2410.07673/) (2024)
- [Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations](https://mlsanity.com/paper/2312.04540/) (2023)
- [A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research](https://mlsanity.com/paper/2410.07066/) (2024)
- [Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction](https://mlsanity.com/paper/2505.06856/) (2025)
- [Out of Distribution Detection via Domain-Informed Gaussian Process State Space Models](https://mlsanity.com/paper/2309.06655/) (2023)
- [SSL Framework for Causal Inconsistency between Structures and Representations](https://mlsanity.com/paper/2310.18634/) (2023)
- [Distribution Shift Is Key to Learning Invariant Prediction](https://mlsanity.com/paper/2601.12296/) (2026)
- [CILF:Causality Inspired Learning Framework for Out-of-Distribution Vehicle Trajectory Prediction](https://mlsanity.com/paper/2307.05624/) (2023)
- [Towards Causal Relationship in Indefinite Data: Baseline Model and New Datasets](https://mlsanity.com/paper/2401.08221/) (2024)
- [Implicit Causal Representation Learning via Switchable Mechanisms](https://mlsanity.com/paper/2402.11124/) (2024)
- [C2INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention](https://mlsanity.com/paper/2411.12313/) (2024)
- [A Closer Look at the Application of Causal Inference in Graph Representation Learning](https://mlsanity.com/paper/2604.08890/) (2026)
- [Causal Representation Learning with Instantaneous and Lagged Relations via Nonstationarity](https://mlsanity.com/paper/2610.03452/) (2026)

## Abstract (arXiv)

Conventional supervised learning methods typically assume i.i.d samples and are found to be sensitive to out-of-distribution (OOD) data. We propose Generative Causal Representation Learning (GCRL) which leverages causality to facilitate knowledge transfer under distribution shifts. While we evaluate the effectiveness of our proposed method in human trajectory prediction models, GCRL can be applied to other domains as well. First, we propose a novel causal model that explains the generative factors in motion forecasting datasets using features that are common across all environments and with features that are specific to each environment. Selection variables are used to determine which parts of the model can be directly transferred to a new environment without fine-tuning. Second, we propose an end-to-end variational learning paradigm to learn the causal mechanisms that generate observations from features. GCRL is supported by strong theoretical results that imply identifiability of the causal model under certain assumptions. Experimental results on synthetic and real-world motion forecasting datasets show the robustness and effectiveness of our proposed method for knowledge transfer under zero-shot and low-shot settings by substantially outperforming the prior motion forecasting models on out-of-distribution prediction. Our code is available at https://github.com/sshirahmad/GCRL.