# CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularization

arXiv: https://arxiv.org/abs/2601.20355 · HTML: https://mlsanity.com/paper/2601.20355/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 28 Jan 2026.

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

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding](https://mlsanity.com/paper/2205.09753/) (2022)
- [DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving](https://mlsanity.com/paper/2304.01168/) (2023)
- [Panoptic Scene Graph Generation with Semantics-Prototype Learning](https://mlsanity.com/paper/2307.15567/) (2023)
- [Ontology based Scene Creation for the Development of Automated Vehicles](https://mlsanity.com/paper/1704.01006/) (2017)
- [Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions](https://mlsanity.com/paper/2009.06435/) (2020)
- [Causal Representation Learning Made Identifiable by Grouping of Observational Variables](https://mlsanity.com/paper/2310.15709/) (2023)
- [GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving](https://mlsanity.com/paper/2403.19098/) (2024)
- [RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding](https://mlsanity.com/paper/2304.08600/) (2023)
- [roadscene2vec: A Tool for Extracting and Embedding Road Scene-Graphs](https://mlsanity.com/paper/2109.01183/) (2021)
- [HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation](https://mlsanity.com/paper/2403.12033/) (2024)
- [Linear Causal Representation Learning from Unknown Multi-node Interventions](https://mlsanity.com/paper/2406.05937/) (2024)
- [A Causal Adjustment Module for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2503.17862/) (2025)
- [Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation](https://mlsanity.com/paper/2503.13947/) (2025)
- [FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing](https://mlsanity.com/paper/2310.16073/) (2023)
- [SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation](https://mlsanity.com/paper/2412.11026/) (2024)
- [Robustness May be More Brittle than We Think under Different Degrees of Distribution Shifts](https://mlsanity.com/paper/2310.06622/) (2023)
- [Knowledge Graphs of Driving Scenes to Empower the Emerging Capabilities of Neurosymbolic AI](https://mlsanity.com/paper/2411.03225/) (2024)
- [A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2505.23451/) (2025)

## Abstract (arXiv)

Scene graphs provide structured abstractions for scene understanding, yet they often overfit to spurious correlations, severely hindering out-of-distribution generalization. To address this limitation, we propose CURVE, a causality-inspired framework that integrates variational uncertainty modeling with uncertainty-guided structural regularization to suppress high-variance, environment-specific relations. Specifically, we apply prototype-conditioned debiasing to disentangle invariant interaction dynamics from environment-dependent variations, promoting a sparse and domain-stable topology. Empirically, we evaluate CURVE in zero-shot transfer and low-data sim-to-real adaptation, verifying its ability to learn domain-stable sparse topologies and provide reliable uncertainty estimates to support risk prediction under distribution shifts.