162 papers with code ยท
Graphs

Link prediction is a task to estimate the probability of links between nodes in a graph.

( Image credit: Inductive Representation Learning on Large Graphs )

In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recurrent-DBN) -- to study interpretable hidden structures from dynamic relational data.

Moreover, node and topological features can be temporal as well, whose patterns the node embeddings should also capture.

In this work, we take a closer look at the evaluation of two families of methods for enriching information from knowledge graphs: Link Prediction and Entity Alignment.

Graph embedding has recently gained momentum in the research community, in particular after the introduction of random walk and neural network based approaches.

An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large networks.

In this paper, we study the fundamental problem of random walk for network embedding.

Link prediction aims to reveal missing edges in a graph.

We consider the large-scale query-document retrieval problem: given a query (e. g., a question), return the set of relevant documents (e. g., paragraphs containing the answer) from a large document corpus.

In contrast with previous work, we show that our method can generalize from training for the single-hop, link prediction task, to answering queries with more complex structures.

Often, the link status of a node pair can be queried, which can be used as additional information by the link prediction algorithm.