[HTML][HTML] Learning heterogeneous knowledge base embeddings for explainable recommendation

Q Ai, V Azizi, X Chen, Y Zhang - Algorithms, 2018 - mdpi.com
Providing model-generated explanations in recommender systems is important to user
experience. State-of-the-art recommendation algorithms—especially the collaborative …

A comprehensive survey of edge prediction in social networks: Techniques, parameters and challenges

B Pandey, PK Bhanodia, A Khamparia… - Expert Systems with …, 2019 - Elsevier
Recent development in the area of social networks has sought attention of the researchers
to crunch and analyse the data and information of the users to retrieve relevant knowledge …

Translating embeddings for modeling multi-relational data

A Bordes, N Usunier, A Garcia-Duran… - Advances in neural …, 2013 - proceedings.neurips.cc
We consider the problem of embedding entities and relationships of multi-relational data in
low-dimensional vector spaces. Our objective is to propose a canonical model which is easy …

Modeling relation paths for representation learning of knowledge bases

Y Lin, Z Liu, H Luan, M Sun, S Rao, S Liu - arXiv preprint arXiv …, 2015 - arxiv.org
Representation learning of knowledge bases (KBs) aims to embed both entities and
relations into a low-dimensional space. Most existing methods only consider direct relations …

Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes

K Sun, Z Lin, Z Zhu - Proceedings of the AAAI conference on artificial …, 2020 - ojs.aaai.org
Abstract Graph Convolutional Networks (GCNs) play a crucial role in graph learning tasks,
however, learning graph embedding with few supervised signals is still a difficult problem. In …

A latent factor model for highly multi-relational data

R Jenatton, N Roux, A Bordes… - Advances in neural …, 2012 - proceedings.neurips.cc
Many data such as social networks, movie preferences or knowledge bases are multi-
relational, in that they describe multiple relationships between entities. While there is a large …

Self-supervised hyperboloid representations from logical queries over knowledge graphs

N Choudhary, N Rao, S Katariya, K Subbian… - Proceedings of the Web …, 2021 - dl.acm.org
Knowledge Graphs (KGs) are ubiquitous structures for information storage in several real-
world applications such as web search, e-commerce, social networks, and biology. Querying …

[PDF][PDF] Discriminative deep random walk for network classification

J Li, J Zhu, B Zhang - Proceedings of the 54th Annual Meeting of …, 2016 - aclanthology.org
Abstract Deep Random Walk (DeepWalk) can learn a latent space representation for
describing the topological structure of a network. However, for relational network …

Adagcn: Adaboosting graph convolutional networks into deep models

K Sun, Z Zhu, Z Lin - arXiv preprint arXiv:1908.05081, 2019 - arxiv.org
The design of deep graph models still remains to be investigated and the crucial part is how
to explore and exploit the knowledge from different hops of neighbors in an efficient way. In …

Stochastic blockmodels meet graph neural networks

N Mehta, LC Duke, P Rai - International Conference on …, 2019 - proceedings.mlr.press
Stochastic blockmodels (SBM) and their variants, $ eg $, mixed-membership and
overlapping stochastic blockmodels, are latent variable based generative models for graphs …