公开(公告)号：US11593672B2

公开(公告)日：2023-02-28

申请号：US16547862

申请日：2019-08-22

Applicant: International Business Machines Corporation ,  Rensselaer Polytechnic Institute

Inventor： Lingfei Wu ,  Mohammed J Zaki ,  Yu Chen

IPC: G06N5/04 ,  G06F17/16 ,  G06K9/62 ,  G06N3/04 ,  G06F40/295

Abstract: Aspects described herein include a method of conversational machine reading comprehension, as well as an associated system and computer program product. The method comprises receiving a plurality of questions relating to a context, and generating a sequence of context graphs. Each of the context graphs includes encoded representations of: (i) the context, (ii) a respective question of the plurality of questions, and (iii) a respective conversation history reflecting: (a) one or more previous questions relative to the respective question, and (b) one or more previous answers to the one or more previous questions. The method further comprises identifying, using at least one graph neural network, one or more temporal dependencies between adjacent context graphs of the sequence. The method further comprises predicting, based at least on the one or more temporal dependencies, an answer for a first question of the plurality of questions.

公开(公告)号：US11360763B2

公开(公告)日：2022-06-14

申请号：US17069402

申请日：2020-10-13

Applicant: International Business Machines Corporation

Inventor： Dakuo Wang ,  Lingfei Wu ,  Yi Wang ,  Xuye Liu ,  Chuang Gan ,  Si Er Han ,  Bei Chen ,  Ji Hui Yang

IPC: G06F8/73 ,  G06F40/169 ,  G06N20/00

Abstract: One embodiment of the invention provides a method for automated code annotation in machine learning (ML) and data science. The method comprises receiving, as input, a section of executable code. The method further comprises classifying, via a ML model, the section of executable code with a stage classification label indicative of a stage within a workflow for automated ML that the executable code applies to. The method further comprises categorizing, based on the stage classification label, the section of executable code with a category of annotation that is most appropriate for the section of executable code. The method further comprises generating a suggested annotation for the section of executable code based on the category of annotation. The method further comprises providing, as output, the suggested annotation to a display of an electronic device for user review. The suggested annotation is user interactable via the electronic device.

公开(公告)号：US20220027707A1

公开(公告)日：2022-01-27

申请号：US16938402

申请日：2020-07-24

Applicant: International Business Machines Corporation ,  Rensselaer Polytechnic Institute

Inventor： Lingfei Wu ,  Yu Chen ,  Mohammed J. Zaki

IPC: G06N3/04 ,  G06N5/02 ,  G06F16/901 ,  G06F16/242 ,  G06F17/16

Abstract: A method, a computer program product, and a system for subgraph guided knowledge graph question generation. The method includes inputting a knowledge graph subgraph and a target answer into a long short-term memory encoder. The method also includes producing embeddings relating to the nodes and the edges. The method includes indicating the embeddings associated with the target answer. The method includes applying a graph neural network encoder computation in an iterative manner to the embeddings, with updated embeddings produced by the GNN encoder acting as initial values that are applied to the GNN encoder for a next iteration, until final state embeddings are produced. The method includes computing a graph-level embedding based on the final state embeddings and computing, by a recurrent neural network decoder, a question relating to the target answer and the knowledge graph subgraph using the graph-level embedding.

公开(公告)号：US20220004720A1

公开(公告)日：2022-01-06

申请号：US16919208

申请日：2020-07-02

Applicant: International Business Machines Corporation

Inventor： Lingfei Wu ,  Chen Wang

IPC: G06F40/58 ,  G06N3/08 ,  G06F16/901 ,  G06F40/47

Abstract: Technology for using a bi-directed graph convolutional neural network (“BGCNN”) to convert RDF data into natural language text. Some embodiments perform RDF-to-Text generation by learning graph-augmented structural neural encoders, consisting of: (a) bidirected graph-based meta-paths encoder; (b) bidirected graph convolutional networks encoder, and (c) separated attention mechanism for combining encoders and decoder to translate RDF triplets to natural language description.

公开(公告)号：US20210357746A1

公开(公告)日：2021-11-18

申请号：US16875919

申请日：2020-05-15

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Lingfei Wu ,  Tengfei Ma

IPC: G06N3/08 ,  G06N3/04

Abstract: A computer-implemented method for calculating a similarity between a pair of graph-structured objects by learning-based techniques. The operations include computing the node embeddings of a pair of graph-structured objects of two computer graphs utilizing a hierarchical graph matching network (HGMN). A first component of the HGMN performs graph matching of global-level graph interactions of the two computer graphs. A second component of the HGMN performs graph matching of cross-level node-graph interactions of the two computer graphs. There is an aggregating of features learned from the graph matching of the global-level graph interactions and the cross-level node-graph interactions. At least one of a graph-graph classification or a graph-graph regression is performed utilizing the learned features of the two computer graphs.

公开(公告)号：US20210149959A1

公开(公告)日：2021-05-20

申请号：US17136688

申请日：2020-12-29

Applicant: International Business Machines Corporation

Inventor： Lingfei Wu ,  Kun Xu ,  Wei Zhang

IPC: G06F16/901 ,  G06F17/16 ,  G06N20/00

Abstract: Systems, computer-implemented methods, and computer program products that facilitate random graph embedding components are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a random graph component that can generate a random graph based on node embeddings corresponding to a data graph. The computer executable components can further comprise a graph embedding component that can compute a graph feature matrix corresponding to the data graph based on a distance between the random graph and the data graph.

公开(公告)号：US10936658B2

公开(公告)日：2021-03-02

申请号：US16146700

申请日：2018-09-28

Applicant: International Business Machines Corporation

Inventor： Lingfei Wu ,  Kun Xu ,  Wei Zhang

IPC: G06F16/00 ,  G06F16/901 ,  G06F17/16 ,  G06N20/00

Abstract: Systems, computer-implemented methods, and computer program products that facilitate task-dependent analysis of various types of data graphs, based at least on generation of a random graph based on node embeddings corresponding to a data graph, and compution of a graph feature matrix corresponding to the data graph based on a distance between the random graph and the data graph.

公开(公告)号：US10817294B2

公开(公告)日：2020-10-27

申请号：US15457526

申请日：2017-03-13

Applicant: International Business Machines Corporation

Inventor： Liana Liyow Fong ,  Wei Tan ,  Michael Witbrock ,  Lingfei Wu

IPC: G06F9/30

Abstract: A block coordinate descent method, system, and computer program product for partitioning a global feature matrix into blocks, each node of the nodes of the blocks having a block size of a number of the blocks over a number of the nodes, selecting, at each node, a subset of the blocks from the blocks, and in one of the nodes, launching a thread to simultaneously update a closed-form solution by minimizing a single coordinate in one of the blocks.

公开(公告)号：US20190318249A1

公开(公告)日：2019-10-17

申请号：US15952698

申请日：2018-04-13

Applicant: International Business Machines Corporation

Inventor： Kun Xu ,  Lingfei Wu ,  Vadim Sheinin ,  Wei Zhang

IPC: G06N5/02 ,  G06N7/00 ,  G06F17/30

Abstract: Technologies for interpretable general reasoning system using key value memory networks are described. Aspects include processing a complex question having at least two subject and relation pairs into keys in key memory locations, and importing entities of a knowledge base as values into value memory locations based on the keys and importing a STOP key. Other aspects include generating a query representation, a key representation of the keys in the key memory locations, and a value representation of the values in the value memory locations; and updating the query representation into an updated query representation over one or more iterations by combining the query representation with the value representation and the key representations until the STOP key is detected.

公开(公告)号：US20190156243A1

公开(公告)日：2019-05-23

申请号：US15817544

申请日：2017-11-20

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Shen Li ,  Xiang Ni ,  Michael Witbrock ,  Lingfei Wu

IPC: G06N99/00 ,  G06F17/28

Abstract: A method and system of creating a model for large scale data analytics is provided. Training data is received in a form of a data matrix X and partitioned into a plurality of partitions. A random matrix T is generated. A feature matrix is determined based on multiplying the partitioned training data by the random matrix T. A predicted data {tilde over (y)} is determined for each partition via a stochastic average gradient (SAG) of each partition. A number of SAG values is reduced based on a number of rows n in the data matrix X. For each iteration, a sum of the reduced SAG values is determined, as well as a full gradient based on the sum of the reduced SAG values from all rows n, by distributed parallel processing. The model parameters w are updated based on the full gradient for each partition.