Many graph-based algorithms in high performance computing (HPC) use approximate solutions due to having algorithms that are computationally expensive or serial in nature. Neural acceleration, i.e., ...

Struct2GO is a protein function prediction model based on self-attention graph pooling, which utilizes structural information from AlphaFold2 to augment the accuracy and generality of the model's ...

Learning embeddings for entities and relations in knowledge graph (KG) have benefited many downstream tasks. In recent years, scoring functions, the crux of KG learning, have been human designed to ...

Welcome to follow the latest overview research on research intelligent agents brought by the Institute of Automation, Chinese ...

But we have more information than edges: we know that our graph is really a discrete representation of a two-dimensional surface. Wobbliness distortions in the parameterization correspond to high ...

Some aspects of fractional calculus of zeta functions along with application of Shannon entropy has been discussed in [8]. The dimer problem and Huckel’s theory are two examples of usage of graph ...

It will be useful to regulate AI, but primarily at the application level. For example, AI applications to medical diagnosis should be regulated very differently from AI applications to self-driving ...