# Spatio-Temporal Deep Graph Infomax

arXiv: https://arxiv.org/abs/1904.06316 · HTML: https://mlsanity.com/paper/1904.06316/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2019.

## Built on by (most cited first, 21 of 21)

- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive](https://mlsanity.com/paper/2105.07342/) (2021)
- [Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities](https://mlsanity.com/paper/2302.01018/) (2023)
- [Prototypical Graph Contrastive Learning](https://mlsanity.com/paper/2106.09645/) (2021)
- [Fair Node Representation Learning via Adaptive Data Augmentation](https://mlsanity.com/paper/2201.08549/) (2022)
- [Graph Neural Networks: Methods, Applications, and Opportunities](https://mlsanity.com/paper/2108.10733/) (2021)
- [Fairness-Aware Node Representation Learning](https://mlsanity.com/paper/2106.05391/) (2021)
- [Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective](https://mlsanity.com/paper/2402.13556/) (2024)
- [Data Augmentation on Graphs: A Technical Survey](https://mlsanity.com/paper/2212.09970/) (2022)
- [Graph Neural Networks for Traffic Forecasting](https://mlsanity.com/paper/2104.13096/) (2021)
- [Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment](https://mlsanity.com/paper/2301.02791/) (2023)
- [Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck](https://mlsanity.com/paper/2309.07200/) (2023)
- [FairNorm: Fair and Fast Graph Neural Network Training](https://mlsanity.com/paper/2205.09977/) (2022)
- [Disambiguated Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2402.08824/) (2024)
- [Joint-Embedding Masked Autoencoder for Self-supervised Learning of Dynamic Functional Connectivity from the Human Brain](https://mlsanity.com/paper/2403.06432/) (2024)
- [Graph Prompting for Graph Learning Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2506.08326/) (2025)
- [A Generative Self-Supervised Framework using Functional Connectivity in fMRI Data](https://mlsanity.com/paper/2312.01994/) (2023)
- [Unifying Graph Contrastive Learning via Graph Message Augmentation](https://mlsanity.com/paper/2401.03638/) (2024)
- [Propagation on Multi-relational Graphs for Node Regression](https://mlsanity.com/paper/2110.08185/) (2021)
- [Graph Representation Learning via Aggregation Enhancement](https://mlsanity.com/paper/2201.12843/) (2022)

## Abstract (arXiv)

Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce Spatio-Temporal Deep Graph Infomax (STDGI)---a fully unsupervised node representation learning approach based on mutual information maximization that exploits both the temporal and spatial dynamics of the graph. Our model tackles the challenging task of node-level regression by training embeddings to maximize the mutual information between patches of the graph, at any given time step, and between features of the central nodes of patches, in the future. We demonstrate through experiments and qualitative studies that the learned representations can successfully encode relevant information about the input graph and improve the predictive performance of spatio-temporal auto-regressive forecasting models.