Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
arXiv:2211.08568 · doi:10.1145/3539597.3570465
Abstract
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.
arXiv commentAccepted by WSDM2023
References in corpus (17)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
- Motifs in Temporal Networks
- Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
- Temporal motifs in time-dependent networks
- APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding
- TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
- Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
- Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination
- Neural Processes
- Sequential Neural Processes
- Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling
- Pseudo-Riemannian Graph Convolutional Networks
- Message Passing Neural Processes
- Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
- A Comprehensive Survey on Distributed Training of Graph Neural Networks
- How Neural Processes Improve Graph Link Prediction