Task-Specific Temporal Node Embedding

EasyChair Preprint 5807

Abstract

Graph embedding aims to learn a representation of graphs' nodes in a latent low-dimensional space. The purpose is to encode the graph’s structural information. While the majority of real-world networks is dynamic, literature generally focuses on static networks and overlooks evolution patterns. In a previous article entitled "TemporalNode2vec: Temporal Node Embedding in Temporal Networks", we introduced a dynamic graph embedding method that learns continuous time-aware vertex representations. In this paper, we adapt TemporalNode2vec to tackle especially the node classification related tasks. Overall, we prove that task-specific embedding improves data efficiency significantly comparing to task-agnostic embedding.

Keyphrases: Dynamic network embeddings, graph representation learning, latent representations

@booklet{EasyChair:5807,
  author    = {Mounir Haddad and Cécile Bothorel and Philippe Lenca and Dominique Bedart},
  title     = {Task-Specific Temporal Node Embedding},
  howpublished = {EasyChair Preprint 5807},
  year      = {EasyChair, 2021}}