Disentangled and Self-Explainable Node Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Piaggesi, Simone, Panisson, André, Khosla, Megha
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912652570132480
author Piaggesi, Simone
Panisson, André
Khosla, Megha
author_facet Piaggesi, Simone
Panisson, André
Khosla, Megha
contents Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining graph model decisions, the interpretability of unsupervised node embeddings remains underexplored. To bridge this gap, we introduce DiSeNE (Disentangled and Self-Explainable Node Embedding), a framework that generates self-explainable embeddings in an unsupervised manner. Our method employs disentangled representation learning to produce dimension-wise interpretable embeddings, where each dimension is aligned with distinct topological structure of the graph. We formalize novel desiderata for disentangled and interpretable embeddings, which drive our new objective functions, optimizing simultaneously for both interpretability and disentanglement. Additionally, we propose several new metrics to evaluate representation quality and human interpretability. Extensive experiments across multiple benchmark datasets demonstrate the effectiveness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21043
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Disentangled and Self-Explainable Node Representation Learning
Piaggesi, Simone
Panisson, André
Khosla, Megha
Machine Learning
Artificial Intelligence
Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining graph model decisions, the interpretability of unsupervised node embeddings remains underexplored. To bridge this gap, we introduce DiSeNE (Disentangled and Self-Explainable Node Embedding), a framework that generates self-explainable embeddings in an unsupervised manner. Our method employs disentangled representation learning to produce dimension-wise interpretable embeddings, where each dimension is aligned with distinct topological structure of the graph. We formalize novel desiderata for disentangled and interpretable embeddings, which drive our new objective functions, optimizing simultaneously for both interpretability and disentanglement. Additionally, we propose several new metrics to evaluate representation quality and human interpretability. Extensive experiments across multiple benchmark datasets demonstrate the effectiveness of our approach.
title Disentangled and Self-Explainable Node Representation Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.21043