# Out-of-Distribution Generalized Dynamic Graph Neural Network with Disentangled Intervention and Invariance Promotion

arXiv: https://arxiv.org/abs/2311.14255 · HTML: https://mlsanity.com/paper/2311.14255/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 146 references that are in the map.
- First posted on arXiv 24 Nov 2023.

## Builds on (most cited first, 8 of 8)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Generalizing Graph Neural Networks on Out-Of-Distribution Graphs](https://mlsanity.com/paper/2111.10657/) (2021)
- [WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series](https://mlsanity.com/paper/2203.09978/) (2022)
- [Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey](https://mlsanity.com/paper/2203.10480/) (2022)
- [DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability](https://mlsanity.com/paper/2111.10447/) (2021)

## Built on by (most cited first, 8 of 8)

- [Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts](https://mlsanity.com/paper/2403.05026/) (2024)
- [A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation](https://mlsanity.com/paper/2410.19265/) (2024)
- [RealTCD: Temporal Causal Discovery from Interventional Data with Large Language Model](https://mlsanity.com/paper/2404.14786/) (2024)
- [Out-of-Distribution Generalized Dynamic Graph Neural Network for Human Albumin Prediction](https://mlsanity.com/paper/2311.15545/) (2023)
- [Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problem](https://mlsanity.com/paper/2505.24178/) (2025)
- [Towards OOD Generalization in Dynamic Graphs via Causal Invariant Learning](https://mlsanity.com/paper/2603.01626/) (2026)
- [Causal-aware Graph Neural Architecture Search under Distribution Shifts](https://mlsanity.com/paper/2405.16489/) (2024)
- [Catch Causal Signals from Edges for Label Imbalance in Graph Classification](https://mlsanity.com/paper/2501.01707/) (2025)

## Abstract (arXiv)

Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to handle distribution shifts, which naturally exist in dynamic graphs, mainly because the patterns exploited by DyGNNs may be variant with respect to labels under distribution shifts. In this paper, we propose Disentangled Intervention-based Dynamic graph Attention networks with Invariance Promotion (I-DIDA) to handle spatio-temporal distribution shifts in dynamic graphs by discovering and utilizing invariant patterns, i.e., structures and features whose predictive abilities are stable across distribution shifts. Specifically, we first propose a disentangled spatio-temporal attention network to capture the variant and invariant patterns. By utilizing the disentangled patterns, we design a spatio-temporal intervention mechanism to create multiple interventional distributions and an environment inference module to infer the latent spatio-temporal environments, and minimize the variance of predictions among these intervened distributions and environments, so that our model can make predictions based on invariant patterns with stable predictive abilities under distribution shifts. Extensive experiments demonstrate the superiority of our method over state-of-the-art baselines under distribution shifts. Our work is the first study of spatio-temporal distribution shifts in dynamic graphs, to the best of our knowledge.