International Business Machines Corporation

Yuya Jeremy Ong

Mu Qiao

Eric Kevin Butler

Aly Megahed

Robert Engel

Nitin Ramchandani

Ramani Ranjan Routray

Divyesh Jadav

Roger C Raphael

Berthold Reinwald

Nathalie Baracaldo Angel

Claudio Santos Pinhanez

Prithviraj Sen

Marisa Affonso Vasconcelos

Yi Zhou

Rogerio Abreu De Paula

Joseph Latone

German H Flores

Nicholas Linck

Mario Motta

Barbara Anne Jones

Systems, computer-implemented methods, and computer program products to facilitate generalization of a quantum imaginary time evolution process and simulation by tensor networks are provided. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a universal component that generalizes a quantum imaginary time evolution process to provide a quantum imaginary time evolution ansatz process. The computer executable components can further comprise a simulation component that applies the quantum imaginary time evolution ansatz process to one or more general multi-body quantum systems.

Generalization of a quantum imaginary time evolution process and simulation by tensor networks

A method, a computer program product, and a system of training a machine learning model using federated learning with extreme gradient boosting. The method includes computing an epsilon hyperparameter using training dataset sizes from a first party and a second party. The method also includes transmitting a machine learning model and the epsilon hyperparameter to the first party and the second party and receiving a first model update and a second model update from the first party and the second party respectively. The method further includes fusing the first model update and the second model update to produce a global histogram and determining at least one split candidate in a decision tree used by the machine learning model using the global histogram. The method also includes rebuilding the machine learning model by adding the split candidate to a decision tree of the machine learning model.

Federated learning technique for applied machine learning

A method of using a computing device to compare performance of multiple algorithms. The method includes receiving, by a computing device, multiple algorithms to assess. The computing device further receives a total amount of resources to allocate to the multiple algorithms. The computing device additionally assigns a fair share of the total amount of resources to each of the multiple algorithms. The computing device still further executes each of the multiple algorithms using the assigned fair share of the total amount of resources. The computing device additionally compares the performance of each of the multiple based on at least one of multiple hardware relative utility metrics describing a hardware relative utility of any given resource allocation for each of the multiple algorithms.

Fair simultaneous comparison of parallel machine learning models

A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations that include analyzing interactions by a user within a network and generating a user profile for the user. The operations by the processor may further include identifying an attempt by the user to share a post via the network and prompting the user with a personalized alert to evaluate the post, wherein the personalized alert is generated based on the interactions, the user profile, and the properties of the post.

Personalized alert generation based on information dissemination

A computer-implemented method is provided for predicting future data values or target labels of multivariate time series data. The method includes receiving the multivariate time series data having present values, systematic missing values, and random missing values. The method further includes masking the present values, the systematic missing values, and the random missing values using triplet encodings. The method also includes determining time intervals between current missing values, from among the systematic missing values and the random missing values, and immediately preceding ones of the present values. The method additionally includes training, by a computing device, at least one recurrent neural network with the triplet encodings, the time intervals, and multivariate time series data to perform a feedforward pass on the recurrent neural network predicting the future data values or the target labels. A forward imputation is utilized by the computing device to impute any of the current missing values.

Predicting multivariate time series with systematic and random missing values

A computer-implemented method according to one embodiment includes receiving historical two-dimensional (2D) multivariate time series data; transforming the historical 2D multivariate time series data into a three-dimensional (3D) temporal tensor; training one or more deep volumetric 3D convolutional neural networks (CNNs), utilizing the 3D temporal tensor; and predicting future values for additional multivariate time series data, utilizing the one or more trained deep volumetric 3D CNNs.

Performing multivariate time series prediction with three-dimensional transformations

Techniques for augmenting data visualizations based on user interactions to enhance user experience are provided. In one aspect, a method for providing real-time recommendations to a user includes: capturing user interactions with a data visualization, wherein the user interactions include images captured as the user interacts with the data visualization; building stacks of the user interactions, wherein the stacks of the user interactions are built from sequences of the user interactions captured over time; generating embeddings for the stacks of the user interactions; finding clusters of embeddings having similar properties; and making the real-time recommendations to the user based on the clusters of embeddings having the similar properties.

Interaction-based visualization to augment user experience

A method loads training samples and forms training data set from the training samples. The method uses the bidirectional LSTM recurrent neural network that includes one or more input cells and one or more output cells and trains it with the training data set. The method determines a sensitive information and confidence values based on analyzing a text with the trained neural network. The method selects predicted samples from the text, where the sensitive information confidence value corresponding to a one or more predicted samples is above a threshold value, based on determining that a sensitive information accuracy has improved. The method forms a new training data set, where the new training data set comprises the samples and the verified one or more predicted samples based on the verified one or more predicted samples, and trains the previously trained neural network with the new training data set.

Growing community of inventors

Tenafly, NJ, United States of America

Yuya Jeremy Ong