DeepAI AI Chat
Log In Sign Up

Neighborhood-aware Scalable Temporal Network Representation Learning

by   Yuhong Luo, et al.

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 on 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 extremely time-consuming feature construction approaches. 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 down-sampled set of the neighboring nodes as keys, and allows fast construction of structural features for a joint neighborhood of multiple nodes. We also design 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 5.9 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 adopts 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:


page 1

page 2

page 3

page 4


Inductive Representation Learning on Temporal Graphs

Inductive representation learning on temporal graphs is an important ste...

Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks

Temporal networks serve as abstractions of many real-world dynamic syste...

Research on Joint Representation Learning Methods for Entity Neighborhood Information and Description Information

To address the issue of poor embedding performance in the knowledge grap...

Temporal-aware Language Representation Learning From Crowdsourced Labels

Learning effective language representations from crowdsourced labels is ...

Graph Neighborhood Attentive Pooling

Network representation learning (NRL) is a powerful technique for learni...

Scalable Motif Counting for Large-scale Temporal Graphs

One fundamental problem in temporal graph analysis is to count the occur...

SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning

Subgraph-based graph representation learning (SGRL) has recently emerged...

Code Repositories



view repo