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：US20230351213A1

公开(公告)日：2023-11-02

申请号：US17935833

申请日：2022-09-27

Applicant: Huazhong University of Science and Technology

Inventor： Feng ZHAO ,  Xiangyu Gui ,  Hai Jin ,  Ruilin Zhao

IPC: G06N5/02

CPC classification number: G06N5/022

Abstract: The present invention relates to an interference-based method for knowledge graph completion and system thereof, wherein the method at least comprises: when performing sampling on a knowledge graph, constructing a knowledge graph completion model; performing model training and performance evaluation on the knowledge graph completion model; and performing prediction on missing elements of incomplete triples in the knowledge graph; the knowledge graph completion model is constructed through: based on optical interference and superposition principles, constructing a score function from data of superposed luminous intensities, mirroring the triples in the knowledge graph to a process of superposition of the luminous intensities, and differentiating between positives and negatives obtained during the sampling of the knowledge graph.

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.

公开(公告)号：US20220147836A1

公开(公告)日：2022-05-12

申请号：US17169869

申请日：2021-02-08

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Feng ZHAO ,  Tao XU ,  Langjunqing JIN ,  Hai JIN

IPC: G06N5/02 ,  G06F40/295 ,  G06N3/08 ,  G06N3/04 ,  G06F40/30

Abstract: The present invention relates to method and device for text-enhanced knowledge graph joint representation learning, the method at least comprises: learning a structure vector representation based on entity objects and their relation linking in a knowledge graph and forming structure representation vectors; discriminating credibility of reliable feature information and building an attention mechanism model, aggregating vectors of different sentences and obtain association-discriminated text representation vectors; and building a joint representation learning model, and using a dynamic parameter-generating strategy to perform joint learning for the text representation vectors and the structure representation vectors based on the joint representation learning model. The present invention selective enhances entity/relation vectors based on significance of associated texts, so as to provide improved semantic expressiveness, and uses 2D convolution operations to train joint representation vectors. As compared to traditional translation models, the disclosed model has better performance in tasks like link prediction and triad classification.

公开(公告)号：US20230351153A1

公开(公告)日：2023-11-02

申请号：US17938058

申请日：2022-10-05

Applicant: Huazhong University of Science and Technology

Inventor： Feng ZHAO ,  Cheng Yan ,  Hai Jin

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/0427 ,  G06N3/08 ,  G06N3/0472

Abstract: The present invention relates to knowledge graph reasoning model, system and reasoning method based on Bayesian few-shot learning, wherein the method at least comprises: building a Gaussian mixture model to entities and relations in a knowledge graph so as to reduce uncertainty of the knowledge graph; taking each said entity as a task to simulate a meta-training process of a newly appearing entity in the dynamic knowledge graph and perform task sampling; constructing a meta learner based on a graph neural network and conducing random reasoning; and training the meta learner so as to use a support set to represent the newly appearing entity. The trained knowledge graph reasoning model in the present invention is highly adaptive and able to infer new facts or new entities without retraining.

公开(公告)号：US20230297553A1

公开(公告)日：2023-09-21

申请号：US17821633

申请日：2022-08-23

Applicant: Huazhong University of Science and Technology

Inventor： Feng ZHAO ,  Langjunqing JIN ,  Hai Jin

IPC: G06F16/22 ,  G06F16/28 ,  G06F40/30

CPC classification number: G06F16/2228 ,  G06F16/288 ,  G06F40/30

Abstract: The present invention relates to a relation-enhancement knowledge graph embedding method and system, wherein the method at least comprises: performing collaborative coordinate-transformation on entities in the knowledge graph; performing relation core enhancement by means of relation-entropy weighting, so as to endow entity vectors with strong relation property; building an interpretability mechanism for a knowledge graph embedding model, and accounting for effectiveness and feasibility of the relation enhancement by proving convergence of the knowledge graph embedding model; and using a dynamic parameter-adjusting strategy to perform learn representation learning of to the vectors in the knowledge graph, and configuring deviation control to ensure accurate embedding. The present invention can measure rationality of facts with improved accuracy, prove through reasoning the modeling ability of the model from the perspective of complex relation pairs, perform vector computing for entities and relations, thereby accomplishes knowledge graph embedding and reasoning.

公开(公告)号：US20190130572A1

公开(公告)日：2019-05-02

申请号：US16094473

申请日：2016-10-09

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Xuming ZHANG ,  Fei ZHU ,  Jingke ZHANG ,  Jinxia REN ,  Feng ZHAO ,  Guanyu LI ,  Mingyue DING

IPC: G06T7/00 ,  G06T3/00 ,  G16H30/40 ,  G06T3/60 ,  G06T11/00

Abstract: The present invention discloses a registration method and system for a non-rigid multi-modal medical image. The registration method comprises: obtaining local descriptors of a reference image according to Zernike moments of order 0 and repetition 0 and Zernike moments of order 1 and repetition 1 of the reference image; obtaining local descriptors of a floating image according to Zernike moments of order 0 and repetition 0 and Zernike moments of order 1 and repetition 1 of the floating image; and finally obtaining a registration image according to the local descriptors of the reference image and the floating image. In the present, by using self-similarity of the multi-modal medical image and adopting the Zernike moment based local descriptor, the non-rigid multi-modal medical image registration is thus converted into the non-rigid mono-modal medical image registration, thereby greatly improving its accuracy and robustness.