Tesi etd-11182020-165258 |
Link copiato negli appunti
Tipo di tesi
Tesi di laurea magistrale
Autore
ATZENI, DANIELE
URN
etd-11182020-165258
Titolo
Learning Edge Representations by Contextual Graph Markov Model
Dipartimento
INFORMATICA
Corso di studi
DATA SCIENCE AND BUSINESS INFORMATICS
Relatori
relatore Prof. Bacciu, Davide
relatore Prof. Micheli, Alessio
relatore Dott. Errica, Federico
relatore Prof. Micheli, Alessio
relatore Dott. Errica, Federico
Parole chiave
- deep learning
- graph classification
- graph enconding
- link prediction
- machine learning
- probabilistic model
Data inizio appello
04/12/2020
Consultabilità
Non consultabile
Data di rilascio
04/12/2090
Riassunto
The Contextual Graph Markov Model (CGMM) is a constructive methodology to build a deep architecture comprising layers of probabilistic models that learn to encode graph-structured information in an incremental fashion.
This thesis extends the original CGMM model to admit the presence of continuous edge attributes while maintaining scalability and efficiency. Besides node and graph encodings, this new architecture also provides edge encodings, which can be used in combination with discriminative models to address edge classification and link prediction tasks.
We show that the proposed model achieves empirical performances that are comparable with the state-of-the-art on graph classification tasks and exhibits significant improvements on link prediction task with respect to CGMM.
This thesis extends the original CGMM model to admit the presence of continuous edge attributes while maintaining scalability and efficiency. Besides node and graph encodings, this new architecture also provides edge encodings, which can be used in combination with discriminative models to address edge classification and link prediction tasks.
We show that the proposed model achieves empirical performances that are comparable with the state-of-the-art on graph classification tasks and exhibits significant improvements on link prediction task with respect to CGMM.
File
Nome file | Dimensione |
---|---|
Tesi non consultabile. |