The Effects of Randomness on the Stability of Node Embeddings

05/20/2020
by   Tobias Schumacher, et al.
2

We systematically evaluate the (in-)stability of state-of-the-art node embedding algorithms due to randomness, i.e., the random variation of their outcomes given identical algorithms and graphs. We apply five node embeddings algorithms—HOPE, LINE, node2vec, SDNE, and GraphSAGE—to synthetic and empirical graphs and assess their stability under randomness with respect to (i) the geometry of embedding spaces as well as (ii) their performance in downstream tasks. We find significant instabilities in the geometry of embedding spaces independent of the centrality of a node. In the evaluation of downstream tasks, we find that the accuracy of node classification seems to be unaffected by random seeding while the actual classification of nodes can vary significantly. This suggests that instability effects need to be taken into account when working with node embeddings. Our work is relevant for researchers and engineers interested in the effectiveness, reliability, and reproducibility of node embedding approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/14/2021

Adversarial Attack on Network Embeddings via Supervised Network Poisoning

Learning low-level node embeddings using techniques from network represe...
research
04/25/2018

Factors Influencing the Surprising Instability of Word Embeddings

Despite the recent popularity of word embedding methods, there is only a...
research
06/16/2022

On the Surprising Behaviour of node2vec

Graph embedding techniques are a staple of modern graph learning researc...
research
07/10/2020

Next Waves in Veridical Network Embedding

Embedding nodes of a large network into a metric (e.g., Euclidean) space...
research
11/26/2018

DynamicGEM: A Library for Dynamic Graph Embedding Methods

DynamicGEM is an open-source Python library for learning node representa...
research
05/29/2020

A Process for the Evaluation of Node Embedding Methods in the Context of Node Classification

Node embedding methods find latent lower-dimensional representations whi...
research
10/01/2020

N odeS ig: Random Walk Diffusion meets Hashing for Scalable Graph Embeddings

Learning node representations is a crucial task with a plethora of inter...

Please sign up or login with your details

Forgot password? Click here to reset