High sparse Knowledge Graph is a key challenge to solve the Knowledge Graph Completion task. Due to the sparsity of the KGs, there are not enough first-order neighbors to learn the features of ...

On the 19th of February 2025, M.Sc. Andreas Grigorjew defends his PhD thesis on Algorithms and Graph Structures for Splitting Network Flows, in Theory and Practice. The thesis is related to research ...

DynIMTS replaces static graphs with instance-attention that updates edge weights on the fly, delivering SOTA imputation and P12 classification ...