公开(公告)号：US20240086731A1

公开(公告)日：2024-03-14

申请号：US18154637

申请日：2023-01-13

Applicant: Huazhong University of Science and Technology

Inventor： Feng ZHAO ,  Mingtao CHEN ,  Kangzheng LIU ,  Hai JIN

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: The present invention relates to a knowledge-graph extrapolating method and system based on multi-layer perception, the method comprising: using relational graph convolutional network encoders to learn embedding representations, and capturing dynamic evolution of a fact; designing emerging task processing units to construct multiple layers of entity sets, and assigning a matching historical relevance; classifying prediction tasks into different reasoning scenes, and connecting them to the corresponding processing unit for partition of entity sets; and using a multi-class task solving method to acquire predicted probability distributions of target entities, and taking the highest one as a prediction answer, so as to accomplish extrapolation of a temporal knowledge graph, wherein the prediction tasks are classified into different reasoning scenes according to whether it contains any entity or relation that has never appeared historically. The knowledge-graph extrapolating system comprises a processor that can run program code information of the disclosed method.

公开(公告)号：US20230401466A1

公开(公告)日：2023-12-14

申请号：US17961798

申请日：2022-10-07

Applicant: Huazhong University of Science and Technology

Inventor： Feng ZHAO ,  Kangzheng LIU ,  Hai JIN

IPC: G06N5/04 ,  G06N5/022 ,  G06N3/0499 ,  G06F17/16

CPC classification number: G06N5/04 ,  G06N5/022 ,  G06N3/0499 ,  G06F17/16

Abstract: The present invention relates to a method for temporal knowledge graph reasoning based on distributed attention, comprising: recombining a temporal knowledge graph in a temporal serialization manner, accurately expressing the structural dependencies between time-evolution features and temporal subgraphs, and then extracting historical repetition facts and historical frequency information based on the sparse matrix storing historical subgraph information; assigning, by the query fact, initial first-layer attention to the facts that are historically repeated using an attention mechanism, and then by capturing the latest changes in the historical frequency information, assigning attention reward and punishment of the second-layer attention to the scores of the first-layer attention, respectively, to make attention more adaptable to time-varying features; finally, using the scores of the two layers of attention to make reasoning-based prediction about future events. Compared with traditional prediction methods, the present invention endows learnable distributed attention on different historical timestamps instead of obtaining a fixed embedding representation through an encoder, so that the model has better ability to solve time-varying problems.