Inicio  /  Algorithms  /  Vol: 13 Par: 9 (2020)  /  Artículo
ARTÍCULO
TITULO

Hierarchical and Unsupervised Graph Representation Learning with Loukas?s Coarsening

Louis Béthune    
Yacouba Kaloga    
Pierre Borgnat    
Aurélien Garivier and Amaury Habrard    

Resumen

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.

 Artículos similares

       
 
Min-Hsien Weng, Shaoqun Wu and Mark Dyer    
With the rapidly growing number of scientific publications, researchers face an increasing challenge of discovering the current research topics and methodologies in a scientific domain. This paper describes an unsupervised topic detection approach that u... ver más
Revista: Applied Sciences

 
Jefry Yanto and Rhea P. Liem    
Fuel burn accounts for up to 25% 25 % of an aircraft?s total operating cost and has become one of the most important decision factors in the airline industry. Hence, prudent fuel estimation is essential for airlines to ensure smooth operation in the upc... ver más
Revista: Aerospace

 
Alessia Sarica, Maria Grazia Vaccaro, Andrea Quattrone and Aldo Quattrone    
Cluster analysis is widely applied in the neuropsychological field for exploring patterns in cognitive profiles, but traditional hierarchical and non-hierarchical approaches could be often poorly effective or even inapplicable on certain type of data. Mo... ver más
Revista: Algorithms

 
Nur Restu Prayoga, Tresna Maulana Fahrudin, Made Kamisutara, Angga Rahagiyanto, Tahegga Primananda Alfath, Latipah, Slamet Winardi, Kunto Eko Susilo     Pág. 200 - 220
The rejection on ratification of the revision of Indonesian Code Law or known as RKUHP and Corruption Law raises several opinions from various perspectives in social media. Twitter as one of many platforms affected, has more than 19.5 million users in In... ver más

 
Rigas Kotsakis, Maria Matsiola, George Kalliris and Charalampos Dimoulas    
The current paper focuses on the investigation of spoken-language classification in audio broadcasting content. The approach reflects a real-word scenario, encountered in modern media/monitoring organizations, where semi-automated indexing/documentation ... ver más
Revista: Information