Heterogeneous network representation learning: A unified framework with survey and benchmark
Since real-world objects and their interactions are often multi-modal and multi-typed,
heterogeneous networks have been widely used as a more powerful, realistic, and generic …
heterogeneous networks have been widely used as a more powerful, realistic, and generic …
Reinforced neighborhood selection guided multi-relational graph neural networks
Graph Neural Networks (GNNs) have been widely used for the representation learning of
various structured graph data, typically through message passing among nodes by …
various structured graph data, typically through message passing among nodes by …
Transfer learning of graph neural networks with ego-graph information maximization
Graph neural networks (GNNs) have achieved superior performance in various applications,
but training dedicated GNNs can be costly for large-scale graphs. Some recent work started …
but training dedicated GNNs can be costly for large-scale graphs. Some recent work started …
Higher-order attribute-enhancing heterogeneous graph neural networks
Graph neural networks (GNNs) have been widely used in deep learning on graphs. They
can learn effective node representations that achieve superior performances in graph …
can learn effective node representations that achieve superior performances in graph …
Lime: Low-Cost and Incremental Learning for Dynamic Heterogeneous Information Networks
Understanding the interconnected relationships of large-scale information networks like
social, scholar and Internet of Things networks is vital for tasks like recommendation and …
social, scholar and Internet of Things networks is vital for tasks like recommendation and …
Conditional structure generation through graph variational generative adversarial nets
Graph embedding has been intensively studied recently, due to the advance of various
neural network models. Theoretical analyses and empirical studies have pushed forward the …
neural network models. Theoretical analyses and empirical studies have pushed forward the …
Diffmg: Differentiable meta graph search for heterogeneous graph neural networks
In this paper, we propose a novel framework to automatically utilize task-dependent
semantic information which is encoded in heterogeneous information networks (HINs) …
semantic information which is encoded in heterogeneous information networks (HINs) …
Submodular hypergraphs: p-laplacians, cheeger inequalities and spectral clustering
P Li, O Milenkovic - International Conference on Machine …, 2018 - proceedings.mlr.press
We introduce submodular hypergraphs, a family of hypergraphs that have different
submodular weights associated with different cuts of hyperedges. Submodular hypergraphs …
submodular weights associated with different cuts of hyperedges. Submodular hypergraphs …
MultiSage: Empowering GCN with contextualized multi-embeddings on web-scale multipartite networks
Graph convolutional networks (GCNs) are a powerful class of graph neural networks.
Trained in a semi-supervised end-to-end fashion, GCNs can learn to integrate node features …
Trained in a semi-supervised end-to-end fashion, GCNs can learn to integrate node features …
Nettaxo: Automated topic taxonomy construction from text-rich network
The automated construction of topic taxonomies can benefit numerous applications,
including web search, recommendation, and knowledge discovery. One of the major …
including web search, recommendation, and knowledge discovery. One of the major …