Incremental embedding for temporal networks

04/06/2019
by   Tomasz Kajdanowicz, et al.
0

Prediction over edges and nodes in graphs requires appropriate and efficiently achieved data representation. Recent research on representation learning for dynamic networks resulted in a significant progress. However, the more precise and accurate methods, the greater computational and memory complexity. Here, we introduce ICMEN - the first-in-class incremental meta-embedding method that produces vector representations of nodes respecting temporal dependencies in the graph. ICMEN efficiently constructs nodes' embedding from historical representations by linearly convex combinations making the process less memory demanding than state-of-the-art embedding algorithms. The method is capable of constructing representation for inactive and new nodes without a need to re-embed. The results of link prediction on several real-world datasets shown that applying ICMEN incremental meta-method to any base embedding approach, we receive similar results and save memory and computational power. Taken together, our work proposes a new way of efficient online representation learning in dynamic complex networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/30/2020

Temporal Network Representation Learning via Historical Neighborhoods Aggregation

Network embedding is an effective method to learn low-dimensional repres...
research
06/21/2021

ConvDySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention and Convolutional Neural Networks

Learning node representations on temporal graphs is a fundamental step t...
research
02/25/2020

Network Representation Learning for Link Prediction: Are we improving upon simple heuristics?

Network representation learning has become an active research area in re...
research
10/14/2020

InstantEmbedding: Efficient Local Node Representations

In this paper, we introduce InstantEmbedding, an efficient method for ge...
research
07/03/2016

node2vec: Scalable Feature Learning for Networks

Prediction tasks over nodes and edges in networks require careful effort...
research
06/24/2022

MultiSAGE: a multiplex embedding algorithm for inter-layer link prediction

Research on graph representation learning has received great attention i...
research
12/14/2021

Efficient Dynamic Graph Representation Learning at Scale

Dynamic graphs with ordered sequences of events between nodes are preval...

Please sign up or login with your details

Forgot password? Click here to reset