Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literature: i) The model is inductive: it can embed new graphs without re-training in the presence of new data; ii) The method takes into account both micro-structures and macro-structures by looking at the attributed graphs at different scales; iii) The model is end-to-end differentiable: it is a building block that can be plugged into deep learning pipelines and allows for back-propagation. We show that combining a coarsening method having strong theoretical guarantees with mutual information maximization suffices to produce high quality embeddings. We evaluate them on classification tasks with common benchmarks of the literature. We show that our algorithm is competitive with state of the art among unsupervised graph representation learning methods.
Code (1)
Tasks
Graph Representation LearningRepresentation LearningSimilar Papers 제목 키워드 기반
Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
Hierarchical abstractions are a methodology for solving large-scale graph problems in various disciplines. Coarsening is one such approach: it generates a pyramid of graphs whereby the one in the next level is a structur…
Graph ClassificationUnsupervised Hierarchical Graph Representation Learning with Variational Bayes
Hierarchical graph representation learning is an emerging subject owing to the increasingly popular adoption of graph neural networks in machine learning and applications. Loosely speaking, work under this umbrella falls…
Graph ClassificationGraph Representation LearningRepresentation LearningAn Efficient Loop and Clique Coarsening Algorithm for Graph Classification
Graph Transformers (GTs) have made remarkable achievements in graph-level tasks. However, most existing works regard graph structures as a form of guidance or bias for enhancing node representations, which focuses on nod…
Graph ClassificationGraph Representation LearningRepresentation LearningMultiresolution Equivariant Graph Variational Autoencoder
In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each reso…
Graph GenerationImage GenerationLink Predictionmolecular representation+1Diversity Curves for Graph Representation Learning
Graph-level representations are crucial tools for characterising structural differences between graphs. However, comparing graphs with different cardinalities, even when sampled from the same underlying distribution, rem…
Graph Representation Learning