Heterogeneous Hyper-Network Embedding
18th IEEE International Conference on Data Mining, ICDM 2018, Singapore, Singapur, 17 - 20 Kasım 2018, cilt.2018-November, ss.875-880, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 2018-November
- Doi Numarası: 10.1109/icdm.2018.00104
- Basıldığı Şehir: Singapore
- Basıldığı Ülke: Singapur
- Sayfa Sayıları: ss.875-880
- Anahtar Kelimeler: Heterogeneous hypergraph, Network embedding, Similarity learning
- Boğaziçi Üniversitesi Adresli: Hayır
Özet
Heterogeneous hyper-networks is used to represent multi-modal and composite interactions between data points. In such networks, several different types of nodes form a hyperedge. Heterogeneous hyper-network embedding learns a distributed node representation under such complex interactions while preserving the network structure. However, this is a challenging task due to the multiple modalities and composite interactions. In this study, a deep approach is proposed to embed heterogeneous attributed hyper-networks with complicated and non-linear node relationships. In particular, a fully-connected and graph convolutional layers are designed to project different types of nodes into a common low-dimensional space, a tuple-wise similarity function is proposed to preserve the network structure, and a ranking based loss function is used to improve the similarity scores of hyperedges in the embedding space. The proposed approach is evaluated on synthetic and real world datasets and a better performance is obtained compared with baselines.