LGSINov 15, 2022

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

arXiv:2211.08568v141 citationsh-index: 66
Originality Incremental advance
AI Analysis

This addresses the problem of missing links and data sparsity in dynamic graphs for graph mining applications, but it is incremental as it builds on neural processes and neural ODEs.

The paper tackles link prediction on dynamic and sparse graphs, where existing methods require extensive historical data, by proposing Graph Sequential Neural ODE Process (GSNOP), which significantly improves performance of dynamic graph neural networks in experiments on three datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes