Co-Neighbor Encoding Schema: A Light-cost Structure Encoding Method for Dynamic Link Prediction

TL;DR

This paper introduces CNES, a novel, efficient structure encoding method for dynamic link prediction that reduces computation time by storing and updating neighborhood information, outperforming existing approaches.

Contribution

The paper proposes CNES, a memory-efficient, hashtable-based structure encoding schema for dynamic graphs, enabling faster and more accurate link prediction.

Findings

CNES significantly reduces encoding time compared to traditional methods.

CNE-N achieves superior accuracy in dynamic link prediction tasks.

Extensive experiments validate the effectiveness and efficiency of CNES across multiple datasets.

Abstract

Structure encoding has proven to be the key feature to distinguishing links in a graph. However, Structure encoding in the temporal graph keeps changing as the graph evolves, repeatedly computing such features can be time-consuming due to the high-order subgraph construction. We develop the Co-Neighbor Encoding Schema (CNES) to address this issue. Instead of recomputing the feature by the link, CNES stores information in the memory to avoid redundant calculations. Besides, unlike the existing memory-based dynamic graph learning method that stores node hidden states, we introduce a hashtable-based memory to compress the adjacency matrix for efficient structure feature construction and updating with vector computation in parallel. Furthermore, CNES introduces a Temporal-Diverse Memory to generate long-term and short-term structure encoding for neighbors with different structural information. A dynamic graph learning framework, Co-Neighbor Encoding Network (CNE-N), is proposed using the aforementioned techniques. Extensive experiments on thirteen public datasets verify the effectiveness and efficiency of the proposed method.