公开(公告)号：US20180254958A1

公开(公告)日：2018-09-06

申请号：US15890747

申请日：2018-02-07

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  Haifeng Chen

IPC: H04L12/24 ,  H04L12/751

CPC classification number: H04L41/147 ,  H04L41/024 ,  H04L41/12 ,  H04L41/142 ,  H04L41/16 ,  H04L45/02 ,  H04L45/20

Abstract: A computer-implemented method executed by at least one processor for performing link prediction with spatial and temporal consistency by employing a time-dependent matrix factorization technique is presented. The method includes developing, at a plurality of timestamps, relational data of a sequence of network structures each including a plurality of nodes and learning, by the at least one processor, a feature vector of each node of the plurality of nodes of the sequence of network structures by concurrently optimizing a temporal fitting constraint and a network propagation constraint. The method further includes determining a network structure at each timestamp, determining evolutionary patterns at each timestamp, and predicting links in a future network structure based on an evolution of the sequence of network structures within a user-defined sliding window by reducing time complexities of finding neighbors of each node of the plurality of nodes of the sequence of network structures.

公开(公告)号：US20250148293A1

公开(公告)日：2025-05-08

申请号：US18934676

申请日：2024-11-01

Applicant: NEC Laboratories America, Inc.

Inventor： Junxiang Wang ,  Wei Cheng ,  Haifeng Chen

IPC: G06N3/094

Abstract: Methods and systems include adapting an initial prompt to a target domain corresponding to an input time series to generate an adapted prompt. The adapted prompt and the input time series are combined. The input time series is processed with the adapted prompt using a modular transformer encoder that has a plurality of sub-encoders, with a policy network selecting a subset of the plurality of encoders that are applied to the input time series and the adapted prompt.

公开(公告)号：US20250103866A1

公开(公告)日：2025-03-27

申请号：US18890888

申请日：2024-09-20

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  Haifeng Chen ,  Dongsheng Luo

IPC: G06N3/047

Abstract: Methods and systems include processing an input graph using a graph neural network (GNN) to generate an output. An explanation sub-graph is generated using an explainer that identifies parts of the input graph that most influence the output. A fidelity measure of the explanation sub-graph is determined that is robust against distribution shifts. An action is performed responsive to the output, the explanation sub-graph, and the fidelity measure.

公开(公告)号：US20240378447A1

公开(公告)日：2024-11-14

申请号：US18650289

申请日：2024-04-30

Applicant: NEC Laboratories America, Inc.

Inventor： Xujiang Zhao ,  Haifeng Chen ,  Wei Cheng ,  Yanchi Liu

IPC: G06N3/09 ,  G06F40/205

Abstract: Systems and methods are provided for extracting relations from text data, including collecting labeled text data from diverse sources, including digital archives and online repositories, each source including sentences annotated with detailed grammatical structures. Initial relational data is generated from the grammatical structures by applying advanced parsing and machine learning techniques using a sophisticated rule-based algorithm. Training sets are generated for enhancing the diversity and complexity of a relation dataset by applying data augmentation techniques to the initial relational data. A neural network model is trained using an array of semantically equivalent but syntactically varied prompt templates designed to test and refine linguistic capabilities of a model. A final relation extraction output is determined by implementing a vote-based decision system integrating statistical analysis and utilizing a weighted voting mechanism to optimize extraction accuracy and reliability.

公开(公告)号：US20240135188A1

公开(公告)日：2024-04-25

申请号：US18545055

申请日：2023-12-19

Applicant: NEC Laboratories America, Inc.

Inventor： Liang Tong ,  Takehiko Mizoguchi ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Nauman Ahad

IPC: G06N3/0895 ,  G06N3/0442

CPC classification number: G06N3/0895 ,  G06N3/0442

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k-1 binary classifiers on top of the semi-supervised representations to obtain k-1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k-1 binary predictions by matching the inconsistent ones to consistent ones of the k-1 binary predictions. The method further includes aggregating the k-1 binary predictions to obtain an ordinal prediction.

公开(公告)号：US20240127072A1

公开(公告)日：2024-04-18

申请号：US18545025

申请日：2023-12-19

Applicant: NEC Laboratories America, Inc.

Inventor： Liang Tong ,  Takehiko Mizoguchi ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Nauman Ahad

IPC: G06N3/0895 ,  G06N3/0442

CPC classification number: G06N3/0895 ,  G06N3/0442

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k−1 binary classifiers on top of the semi-supervised representations to obtain k−1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k−1 binary predictions by matching the inconsistent ones to consistent ones of the k−1 binary predictions. The method further includes aggregating the k−1 binary predictions to obtain an ordinal prediction.

公开(公告)号：US20240046128A1

公开(公告)日：2024-02-08

申请号：US18471564

申请日：2023-09-21

Applicant: NEC Laboratories America, Inc.

Inventor： Wenchao Yu ,  Wei Cheng ,  Haifeng Chen ,  Yuncong Chen ,  Xuchao Zhang ,  Tianxiang Zhao

IPC: G16H50/20

CPC classification number: G16H50/20

Abstract: A method for learning a self-explainable imitator by discovering causal relationships between states and actions is presented. The method includes obtaining, via an acquisition component, demonstrations of a target task from experts for training a model to generate a learned policy, training the model, via a learning component, the learning component computing actions to be taken with respect to states, generating, via a dynamic causal discovery component, dynamic causal graphs for each environment state, encoding, via a causal encoding component, discovered causal relationships by updating state variable embeddings, and outputting, via an output component, the learned policy including trajectories similar to the demonstrations from the experts.

公开(公告)号：US20240037403A1

公开(公告)日：2024-02-01

申请号：US18484872

申请日：2023-10-11

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  Dongkuan Xu ,  Haifeng Chen

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method for performing contrastive learning for graph tasks and datasets by employing an information-aware graph contrastive learning framework is presented. The method includes obtaining two semantically similar views of a graph coupled with a label for training by employing a view augmentation component, feeding the two semantically similar views into respective encoder networks to extract latent representations preserving both structure and attribute information in the two views, optimizing a contrastive loss based on a contrastive mode by maximizing feature consistency between the latent representations, training a neural network with the optimized contrastive loss, and predicting a new graph label or a new node label in the graph.

公开(公告)号：US20240037401A1

公开(公告)日：2024-02-01

申请号：US18484851

申请日：2023-10-11

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  Dongkuan Xu ,  Haifeng Chen

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method for performing contrastive learning for graph tasks and datasets by employing an information-aware graph contrastive learning framework is presented. The method includes obtaining two semantically similar views of a graph coupled with a label for training by employing a view augmentation component, feeding the two semantically similar views into respective encoder networks to extract latent representations preserving both structure and attribute information in the two views, optimizing a contrastive loss based on a contrastive mode by maximizing feature consistency between the latent representations, training a neural network with the optimized contrastive loss, and predicting a new graph label or a new node label in the graph.

公开(公告)号：US20240005154A1

公开(公告)日：2024-01-04

申请号：US18370092

申请日：2023-09-19

Applicant: NEC Laboratories America, Inc.

Inventor： Jingchao Ni ,  Wei Cheng ,  Haifeng Chen

IPC: G06N3/08 ,  G06N7/01

CPC classification number: G06N3/08 ,  G06N7/01

Abstract: A computer-implemented method for model building is provided. The method includes receiving a training set of medical records and model hyperparameters. The method further includes initializing an encoder as a Dual-Channel Combiner Network (DCNN) and initialize distribution related parameters. The method also includes performing, by a hardware processor, a forward computation to (1) the DCNN to obtain the embeddings of the medical records, and (2) the distribution related parameters to obtain class probabilities. The method additionally includes checking by a convergence evaluator if the iterative optimization has converged. The method further includes performing model personalization responsive to model convergence by encoding the support data of a new patient and using the embeddings and event subtype labels to train a personalized classifier.