Nowadays, a lot of data is in the form of Knowledge Graphs aiming at representing information as a set of nodes and relationships between them. This paper proposes an efficient framework to create informative embeddings for node classification on large knowledge graphs. Such embeddings capture how a particular node of the graph interacts with his neighborhood and indicate if it is either isolated or part of a bigger clique. Since a homogeneous graph is necessary to perform this kind of analysis, the framework exploits the metapath approach to split the heterogeneous graph into multiple homogeneous graphs. The proposed pipeline includes an unsupervised attentive neural network to merge different metapaths and produce node embeddings suitable for classification. Preliminary experiments on the IMDb dataset demonstrate the validity of the proposed approach, which can defeat current state-of-the-art unsupervised methods.
Towards unsupervised machine learning approaches for knowledge graphs
Falchi F;Manghi P;De Bonis M;Messina N
2022
Abstract
Nowadays, a lot of data is in the form of Knowledge Graphs aiming at representing information as a set of nodes and relationships between them. This paper proposes an efficient framework to create informative embeddings for node classification on large knowledge graphs. Such embeddings capture how a particular node of the graph interacts with his neighborhood and indicate if it is either isolated or part of a bigger clique. Since a homogeneous graph is necessary to perform this kind of analysis, the framework exploits the metapath approach to split the heterogeneous graph into multiple homogeneous graphs. The proposed pipeline includes an unsupervised attentive neural network to merge different metapaths and produce node embeddings suitable for classification. Preliminary experiments on the IMDb dataset demonstrate the validity of the proposed approach, which can defeat current state-of-the-art unsupervised methods.File | Dimensione | Formato | |
---|---|---|---|
prod_468960-doc_190102.pdf
accesso aperto
Descrizione: Towards unsupervised machine learning approaches for knowledge graphs
Tipologia:
Versione Editoriale (PDF)
Dimensione
942.42 kB
Formato
Adobe PDF
|
942.42 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.