Neighborhood-aware Scalable Temporal Network Representation Learning

TL;DR

This paper introduces NAT, a scalable neighborhood-aware model for temporal network representation learning that efficiently captures joint neighborhood information, improving link prediction accuracy and speed on large-scale networks.

Contribution

NAT replaces traditional single-vector node representations with a dictionary-based neighborhood encoding and a GPU-friendly data structure, enabling fast, scalable structural feature extraction.

Findings

Outperforms state-of-the-art baselines in link prediction accuracy.

Achieves significant speed-up in feature construction and prediction tasks.

Effectively captures joint neighborhood information in large-scale temporal networks.

Abstract

Temporal networks have been widely used to model real-world complex systems such as financial systems and e-commerce systems. In a temporal network, the joint neighborhood of a set of nodes often provides crucial structural information useful for predicting whether they may interact at a certain time. However, recent representation learning methods for temporal networks often fail to extract such information or depend on online construction of structural features, which is time-consuming. To address the issue, this work proposes Neighborhood-Aware Temporal network model (NAT). For each node in the network, NAT abandons the commonly-used one-single-vector-based representation while adopting a novel dictionary-type neighborhood representation. Such a dictionary representation records a downsampled set of the neighboring nodes as keys, and allows fast construction of structural features for a joint neighborhood of multiple nodes. We also design a dedicated data structure termed N-cache to support parallel access and update of those dictionary representations on GPUs. NAT gets evaluated over seven real-world large-scale temporal networks. NAT not only outperforms all cutting-edge baselines by averaged 1.2% and 4.2% in transductive and inductive link prediction accuracy, respectively, but also keeps scalable by achieving a speed-up of 4.1-76.7x against the baselines that adopt joint structural features and achieves a speed-up of 1.6-4.0x against the baselines that cannot adopt those features. The link to the code: https: //github.com/Graph-COM/Neighborhood-Aware-Temporal-Network.