SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations

by   Sebastian Mežnar, et al.

Learning from real-life complex networks is a lively research area, with recent advances in learning information-rich, low-dimensional network node representations. However, state-of-the-art methods offer little insights as the features that constitute the learned node representations are not interpretable and are as such less applicable to sensitive settings in biomedical or user profiling tasks, where bias detection is highly relevant. The proposed SNoRe (Symbolic Node Representations) algorithm is capable of learning symbolic, human-understandable representations of individual network nodes based on the similarity of neighborhood hashes to nodes chosen as features. SNoRe's interpretable features are suitable for direct explanation of individual predictions, which we demonstrate by coupling it with the widely used instance explanation tool SHAP to obtain nomograms representing the relevance of individual features for a given classification, which is to our knowledge one of the first such attempts in a structural node embedding setting. In the experimental evaluation on 11 real-life datasets, SNoRe proved to be competitive to strong baselines, such as variational graph autoencoders, node2vec and LINE. The vectorized implementation of SNoRe scales to large networks, making it suitable for many contemporary network analysis tasks.



There are no comments yet.


page 21

page 22


Symbolic Graph Embedding using Frequent Pattern Mining

Relational data mining is becoming ubiquitous in many fields of study. I...

COLOGNE: Coordinated Local Graph Neighborhood Sampling

Representation learning for graphs enables the application of standard m...

Deep Kernel Supervised Hashing for Node Classification in Structural Networks

Node classification in structural networks has been proven to be useful ...

Spectral Graph Wavelets for Structural Role Similarity in Networks

Nodes residing in different parts of a graph can have similar structural...

Transfer Learning for Node Regression Applied to Spreading Prediction

Understanding how information propagates in real-life complex networks y...

FONDUE: A Framework for Node Disambiguation Using Network Embeddings

Real-world data often presents itself in the form of a network. Examples...

Revisited Experimental Comparison of Node-Link and Matrix Representations

Visualizing network data is applicable in domains such as biology, engin...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.