Application-oriented approaches to graph transformation provide structural features beyond vertices and edges, like composition in hierarchical graphs, inheritance in object-oriented graphs, multiplicity constraints, etc. Often, these features have a specific dynamic interpretation which requires complex embedding mechanisms and context conditions. For example, the deletion of a compound node u...

The Martin polynomial of an oriented Eulerian graph encodes information about families of cycles in the graph. This paper uses a transformation of the Martin polynomial that facilitates standard combinatorial manipulations. These manipulations result in several new identities for the Martin polynomial, including a di.erentiation formula. These identities are then applied to get new combinatoria...

Quality assessment of omnidirectional images has become increasingly urgent due to the rapid growth virtual reality applications. Different from traditional 2D and videos, contents can provide consumers with freely changeable viewports a larger field view covering 360 ° ×180 spherical surface, w...

Graph Convolutional Networks (GCNs) are increasingly adopted in large-scale graph-based recommender systems. Training GCN requires the minibatch generator traversing graphs and sampling sparsely located neighboring nodes to obtain their features. Since real-world often exceed capacity of GPU memory, current training systems keep feature table host memory rely on CPU collect sparse features befo...

The graph-oriented programming model (GOP) [4] aims at providing high-level abstractions for programming distributed system. In GOP, a language-level graph construct, consisting of user-specified logical graphs and the distributed implementation of various kinds of graph operations, is used as the underlying mechanism for programming the configuration, communication, and synchronization of the ...