# Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs

arXiv: https://arxiv.org/abs/2211.08568 · HTML: https://mlsanity.com/paper/2211.08568/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 15 Nov 2022.

## Builds on (most cited first, 26 of 26)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Neural Processes](https://mlsanity.com/paper/1807.01622/) (2018)
- [Attentive Neural Processes](https://mlsanity.com/paper/1901.05761/) (2019)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling](https://mlsanity.com/paper/2207.04179/) (2022)
- [Motifs in Temporal Networks](https://mlsanity.com/paper/1612.09259/) (2016)
- [Neural Spatio-Temporal Point Processes](https://mlsanity.com/paper/2011.04583/) (2020)
- [APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding](https://mlsanity.com/paper/2011.11545/) (2020)
- [Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination](https://mlsanity.com/paper/2206.01535/) (2022)
- [Temporal Knowledge Graph Forecasting with Neural ODE](https://mlsanity.com/paper/2101.05151/) (2021)
- [Neural ODE Processes](https://mlsanity.com/paper/2103.12413/) (2021)
- [Sequential Neural Processes](https://mlsanity.com/paper/1906.10264/) (2019)
- [TREND: TempoRal Event and Node Dynamics for Graph Representation Learning](https://mlsanity.com/paper/2203.14303/) (2022)
- [Task-adaptive Neural Process for User Cold-Start Recommendation](https://mlsanity.com/paper/2103.06137/) (2021)
- [Pseudo-Riemannian Graph Convolutional Networks](https://mlsanity.com/paper/2106.03134/) (2021)
- [Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes](https://mlsanity.com/paper/2011.12916/) (2020)
- [Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Model](https://mlsanity.com/paper/2109.02058/) (2021)
- [How Neural Processes Improve Graph Link Prediction](https://mlsanity.com/paper/2109.14894/) (2021)

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

- [Learning Strong Graph Neural Networks with Weak Information](https://mlsanity.com/paper/2305.18457/) (2023)
- [Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs](https://mlsanity.com/paper/2306.07608/) (2023)
- [Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2304.08183/) (2023)
- [DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs](https://mlsanity.com/paper/2408.06966/) (2024)
- [A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects](https://mlsanity.com/paper/2308.02457/) (2023)
- [Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networks](https://mlsanity.com/paper/2503.23167/) (2025)
- [Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting](https://mlsanity.com/paper/2305.06587/) (2023)
- [Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach](https://mlsanity.com/paper/2307.01204/) (2023)
- [Latent Conditional Diffusion-based Data Augmentation for Continuous-Time Dynamic Graph Model](https://mlsanity.com/paper/2407.08500/) (2024)
- [TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction](https://mlsanity.com/paper/2510.23577/) (2025)
- [Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation](https://mlsanity.com/paper/2304.05749/) (2023)
- [How to Bridge Spatial and Temporal Heterogeneity in Link Prediction? A Contrastive Method](https://mlsanity.com/paper/2411.00612/) (2024)
- [TGFormer: Towards Temporal Graph Transformer with Auto-Correlation Mechanism](https://mlsanity.com/paper/2605.24971/) (2026)

## Abstract (arXiv)

Link prediction on dynamic graphs is an important task in graph mining. Existing approaches based on dynamic graph neural networks (DGNNs) typically require a significant amount of historical data (interactions over time), which is not always available in practice. The missing links over time, which is a common phenomenon in graph data, further aggravates the issue and thus creates extremely sparse and dynamic graphs. To address this problem, we propose a novel method based on the neural process, called Graph Sequential Neural ODE Process (GSNOP). Specifically, GSNOP combines the advantage of the neural process and neural ordinary differential equation that models the link prediction on dynamic graphs as a dynamic-changing stochastic process. By defining a distribution over functions, GSNOP introduces the uncertainty into the predictions, making it generalize to more situations instead of overfitting to the sparse data. GSNOP is also agnostic to model structures that can be integrated with any DGNN to consider the chronological and geometrical information for link prediction. Extensive experiments on three dynamic graph datasets show that GSNOP can significantly improve the performance of existing DGNNs and outperform other neural process variants.