Nec Corporation

Jingchao Ni

Haifeng Chen

Wei Cheng

Bo Zong

LuAn Tang

Wenchao Yu

Dongjin Song

Guofei Jiang

Zhengzhang Chen

Yanchi Liu

Dongkuan Xu

Liang Tong

Cheng Zheng

Denghui Zhang

Xin Dong

Yizhou Zhang

Methods and systems for training a model include determining class prototypes of time series samples from a training dataset. A task corresponding to the time series samples is encoded using the class prototypes and a task-level configuration. A likelihood value is determined based on outputs of a time series density model, a task-class distance from a task embedding model, and a task density model. Parameters of the time series density model, the task embedding model, and the task density model are adjusted responsive to the likelihood value.

SNR detection with few-shot trained models

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.

Superclass-conditional Gaussian mixture model for personalized prediction on dialysis events

Superclass-conditional gaussian mixture model for personalized prediction on dialysis events

A method for executing a multi-task deep learning model for learning trends in multivariate time series is presented. The method includes collecting multi-variate time series data from a plurality of sensors, jointly learning both local and global contextual features for predicting a trend of the multivariate time series by employing a tensorized long short-term memory (LSTM) with adaptive shared memory (TLASM) to learn historical dependency of historical trends, and employing a multi-task one-dimensional convolutional neural network (1dCNN) to extract salient features from local raw time series data to model a short-term dependency between local time series data and subsequent trends.

Tensorized LSTM with adaptive shared memory for learning trends in multivariate time series

A method for employing a unified semi-supervised deep learning (DL) framework for turbulence forecasting is presented. The method includes extracting historical and forecasted weather features of a spatial region, calculating turbulence indexes to fill feature cubes, each feature cube representing a grid-based 3D region, and building an encoder-decoder framework based on convolutional long short-term memory (ConvLSTM) to model spatio-temporal correlations or patterns causing turbulence. The method further includes employing a dual label guessing component to dynamically integrate complementary signals from a turbulence forecasting network and a turbulence detection network to generate pseudo-labels, reweighing the generated pseudo-labels by a heuristic label quality detector based on KL-Divergence, applying a hybrid loss function to predict turbulence conditions, and generating a turbulence dataset including the predicted turbulence conditions.

Semi-supervised deep model for turbulence forecasting

A method for employing a supervised graph sparsification (SGS) network to use feedback from subsequent graph learning tasks to guide graph sparsification is presented. The method includes, in a training phase, generating sparsified subgraphs by edge sampling from input training graphs following a learned distribution, feeding the sparsified subgraphs to a prediction/classification component, collecting a predication/classification error, and updating parameters of the learned distribution based on a gradient derived from the predication/classification error. The method further includes, in a testing phase, generating sparsified subgraphs by edge sampling from input testing graphs following the learned distribution, feeding the sparsified subgraphs to the prediction/classification component, and outputting prediction/classification results to a visualization device.

Method for supervised graph sparsification

Methods and systems for detecting and responding to anomalous nodes in a network include inferring temporal factors, using a computer-implemented neural network, that represent changes in a network graph across time steps, with a temporal factor for each time step depending on a temporal factor for a previous time step. An invariant factor is inferred that represents information about the network graph that does not change across the time steps. The temporal factors and the invariant factor are combined into a combined temporal-invariant representation. It is determined that an unlabeled node is anomalous, based on the combined temporal-invariant representation. A security action is performed responsive to the determination that unlabeled node is anomalous.

Node classification in dynamic networks using graph factorization

Systems and methods for predicting system device failure are provided. The method includes representing device failure related data associated with the devices from a predetermined domain by temporal graphs for each of the devices. The method also includes extracting vector representations based on temporal graph features from the temporal graphs that capture both temporal and structural correlation in the device failure related data. The method further includes predicting, based on the vector representations and device failure related metrics in the predetermined domain, one or more of the devices that is expected to fail within a predetermined time.

Performance prediction from communication data

A method for implementing a recommendation system using an asymmetrically hierarchical network includes, for a user and an item corresponding to a user-item pair, aggregating, using asymmetrically designed sentence aggregators, respective ones of a set of item sentence embeddings and a set of user sentence embeddings to generate a set of item review embeddings based on first item attention weights and a set of user review embeddings based on first user attention weights, respectively, aggregating, using asymmetrically designed review aggregators, respective ones of the set of item review embeddings and the set of user review embeddings to generate an item embedding based on a second item attention weights and a user embedding based on second user attention weights, respectively, and predicting a rating of the user-item pair based on the item embedding and the user embedding.

Asymmetrically hierarchical networks with attentive interactions for interpretable review-based recommendation

Systems and methods for implementing dynamic graph analysis (DGA) to detect anomalous network traffic are provided. The method includes processing communications and profile data associated with multiple devices to determine dynamic graphs. The method includes generating features to model temporal behaviors of network traffic generated by the multiple devices based on the dynamic graphs. The method also includes formulating a list of prediction results for sources of the anomalous network traffic from the multiple devices based on the temporal behaviors.

Dynamic transaction graph analysis

Systems and methods for implementing sequence data based temporal behavior analysis (SDTBA) to extract features for characterizing temporal behavior of network traffic are provided. The method includes extracting communication and profile data associated with one or more devices to determine sequences of data associated with the devices. The method includes generating temporal features to model anomalous network traffic. The method also includes inputting, into an anomaly detection process for anomalous network traffic, the temporal features and the sequences of data associated with the devices and formulating a list of prediction results of anomalous network traffic associated with the devices.

Temporal behavior analysis of network traffic

Systems and methods for predicting system device failure are provided. The method includes performing graph-based predictive maintenance (GBPM) to determine a trained ensemble classification model for detecting maintenance ready components that includes extracted node features and graph features. The method includes constructing, based on testing data and the trained ensemble classification model, an attributed temporal graph and the extracted node features and graph features. The method further includes concatenating the extracted node features and graph features. The method also includes determining, based on the trained ensemble classification model, a list of prediction results of components that are to be scheduled for component maintenance.

Graph-based predictive maintenance

Systems and methods for implementing heterogeneous feature integration for device behavior analysis (HFIDBA) are provided. The method includes representing each of multiple devices as a sequence of vectors for communications and as a separate vector for a device profile. The method also includes extracting static features, temporal features, and deep embedded features from the sequence of vectors to represent behavior of each device. The method further includes determining, by a processor device, a status of a device based on vector representations of each of the multiple devices.

Anomalous account detection from transaction data

A computer-implemented method for diagnosing system faults by fine-grained causal anomaly inference is presented. The computer-implemented method includes identifying functional modules impacted by causal anomalies and backtracking causal anomalies in impaired functional modules by a low-rank network diffusion model. An invariant network and a broken network are inputted into the system, the invariant network and the broken network being jointly clustered to learn a degree of broken severities of different clusters as a result of fault propagations.

Growing community of inventors

Princeton, NJ, United States of America

Jingchao Ni