Visa International Service Association

Michael Yeh

Wei Zhang

Yan Zheng

Liang Wang

Hao Yang

Junpeng Wang

Zhongfang Zhuang

Yu-San Lin

Liang Gou

Yuhang Wu

Bo Dong

Huiyuan Chen

Yuwei Wang

Prince Osei Aboagye

Mengting Gu

Fei Wang

Dhruv Gelda

Shubham Jain

Lan Wang

Jiarui Sun

Xiaoting Li

Provided are systems for analyzing a relational database using embedding learning that may include at least one processor programmed or configured to generate one or more entity-relation matrices from a relational database and perform, for each entity-relation matrix of the one or more entity-relation matrices, an embedding learning process on an embedding associated with an entity. When performing the embedding learning process on the embedding associated with the entity, the at least one processor is programmed or configured to generate an updated embedding associated with the entity. Computer-implemented methods and computer program products are also provided.

System, method, and computer program product for analyzing a relational database using embedding learning

Systems, methods, and computer program products are provided for saving memory during training of knowledge graph neural networks. The method includes receiving a training dataset including a first set of knowledge graph embeddings associated with a plurality of entities for a first layer of a knowledge graph, inputting the training dataset into a knowledge graph neural network to generate at least one further set of knowledge graph embeddings associated with the plurality of entities for at least one further layer of the knowledge graph, quantizing the at least one further set of knowledge graph embeddings to provide at least one set of quantized knowledge graph embeddings, storing the at least one set of quantized knowledge graph embeddings in a memory, and dequantizing the at least one set of quantized knowledge graph embeddings to provide at least one set of dequantized knowledge graph embeddings.

System, method, and computer program product for saving memory during training of knowledge graph neural networks

A method is disclosed. The method comprises determining a time series, a subsequence length. The length of the time series may then be determined, and an initial matrix profile may then be computed. The method may then form a processed matrix profile for a first subsequence of the subsequence length by applying the first subsequence to the initial matrix profile. A second subsequence may then be determined from the processed matrix profile. The method may then include comparing the second subsequence to other subsequences in a dictionary and adding it to the dictionary. The subsequences in the dictionary may be used to generate a plurality of subsequence matrix profiles. The method may then include forming an approximate matrix profile using the plurality of subsequence matrix profiles and then determining one or more anomalies in the time series or another time series using the approximate matrix profile.

Error-bounded approximate time series join using compact dictionary representation of time series

Provided is a method for normalizing embeddings for cross-embedding alignment. The method may include applying mean centering to the at least one embedding set, applying spectral normalization to the at least one embedding set, and/or applying length normalization to the at least one embedding set. Spectral normalization may include decomposing the at least one embedding set, determining an average singular value of the at least one embedding set, determining a respective substitute singular value for each respective singular value of a diagonal matrix, and/or replacing the at least one embedding set with a product of the at least one embedding set, a right singular vector, and an inverse of the substitute diagonal matrix. The mean centering, spectral normalization, and/or length normalization may be iteratively repeated for a configurable number of iterations. A system and computer program product are also disclosed.

Method, system, and computer program product for normalizing embeddings for cross-embedding alignment

Provided is a system for analyzing features associated with entities using an embedding tree, the system including at least one processor programmed or configured to receive a dataset associated with a plurality of entities, wherein the dataset comprises a plurality of data instances for a plurality of entities. The processor may be programmed or configured to generate at least two embeddings based on the dataset and determine split criteria for partitioning an embedding space of at least one embedding tree associated with the dataset based on feature data associated with an entity and embedding data associated with the at least two embeddings. The processor may be programmed or configured to generate at least one embedding tree having a plurality of nodes based on the split criteria. Methods and computer program products are also provided.

System, method, and computer program product for feature analysis using an embedding tree

Described are a system, method, and computer program product for dynamic node classification in temporal-based machine learning classification models. The method includes receiving graph data of a discrete time dynamic graph including graph snapshots, and node classifications associated with all nodes in the discrete time dynamic graph. The method includes converting the discrete time dynamic graph to a time-augmented spatio-temporal graph and generating an adjacency matrix based on a temporal walk of the time-augmented spatio-temporal graph. The method includes generating an adaptive information transition matrix based on the adjacency matrix and determining feature vectors based on the nodes and the node attribute matrix of each graph snapshot. The method includes generating and propagating initial node representations across information propagation layers using the adaptive information transition matrix and classifying a node of the discrete time dynamic graph subsequent to the first time period based on final node representations.

System, method, and computer program product for dynamic node classification in temporal-based machine learning classification models

Embodiments for training a recommendation system to provide merchant recommendations comprise receiving, by a processor, raw merchant embeddings and raw user embeddings generated from payment transaction records, wherein the raw merchant embeddings include a plurality of embedded features. A generative adversarial network (GAN) is trained to generate modified merchant embeddings from the raw merchant embeddings, where the modified embeddings remove a location feature. Subsequent to training and responsive to receiving a request for merchant recommendations in the target location for the target user, the GAN and a trained preference model are used to generate a list of merchant rankings based on a new set of modified merchant embeddings, past preferences of a target user, and the target location to recommend merchants in the target location.

Unsupervised embeddings disentanglement using a gan for merchant recommendations

Described are a system, method, and computer program product for multivariate event prediction using multi-stream recurrent neural networks. The method includes receiving event data from a sample time period and generating feature vectors for each subperiod of each day. The method also includes providing the feature vectors as inputs to a set of first recurrent neural network (RNN) models and generating first outputs for each RNN node. The method further includes merging the first outputs for each same subperiod to form aggregated time-series layers. The method further includes providing the aggregated time-series layers as an input to a second RNN model and generating final outputs for each RNN node of the second RNN model.

System, method, and computer program product for multivariate event prediction using multi-stream recurrent neural networks

Disclosed are a system, method, and computer program product for user network activity anomaly detection. The method includes generating a multilayer graph from network resource data, and generating an adjacency matrix associated with each layer of the multilayer graph to produce a plurality of adjacency matrices. The method further includes assigning a weight to each adjacency matrix to produce a plurality of weights, and generating a merged single layer graph by merging the plurality of layers based on a weighted sum of the plurality of adjacency matrices using the plurality of weights. The method further includes generating a set of anomaly scores by generating, for each node in the merged single layer graph, an anomaly score. The method further includes determining a set of anomalous users based on the set of anomaly scores, detecting fraudulent network activity based on the set of anomalous users, and executing a fraud mitigation process.

System, method, and computer program product for user network activity anomaly detection

A method includes receiving a first data set comprising embeddings of first and second types, generating a fixed adjacency matrix from the first dataset, and applying a first stochastic binary mask to the fixed adjacency matrix to obtain a first subgraph of the fixed adjacency matrix. The method also includes processing the first subgraph through a first layer of a graph convolutional network (GCN) to obtain a first embedding matrix, and applying a second stochastic binary mask to the fixed adjacency matrix to obtain a second subgraph of the fixed adjacency matrix. The method includes processing the first embedding matrix and the second subgraph through a second layer of the GCN to obtain a second embedding matrix, and then determining a plurality of gradients of a loss function, and modifying the first stochastic binary mask and the second stochastic binary mask using at least one of the plurality of gradients.

Structured graph convolutional networks with stochastic masks for network embeddings

Provided is a system for analyzing a multivariate time series that includes at least one processor programmed or configured to receive a time series of historical data points, determine a historical time period, determine a contemporary time period, determine a first time series of data points associated with a historical transaction metric from the historical time period, determine a second time series of data points associated with a historical target transaction metric from the historical time period, determine a third time series of data points associated with a contemporary transaction metric from the contemporary time period, and generate a machine learning model, wherein the machine learning model is configured to provide an output that comprises a predicted time series of data points associated with a contemporary target transaction metric. Methods and computer program products are also provided.

System, method, and computer program product for analyzing multivariate time series using a convolutional Fourier network

Provided are systems for analyzing a relational database using embedding learning that may include at least one processor programmed or configured to generate one or more entity-relation matrices from a relational database and perform, for each entity-relation matrix of the one or more entity-relation matrices, an embedding learning process on an embedding associated with an entity. When performing the embedding learning process on the embedding associated with the entity, the at least one processor is programmed or configured to generate an updated embedding associated with the entity. Computer implemented methods and computer-program products are also provided.

Described are a system, method, and computer program product for user network activity anomaly detection. The method includes receiving network resource data associated with network resource activity of a plurality of users and generating a plurality of layers of a multilayer graph from the network resource data. Each layer of the plurality of layers may include a plurality of nodes, which are associated with users, connected by a plurality of edges, which are representative of node interdependency. The method also includes generating a plurality of adjacency matrices from the plurality of layers and generating a merged single layer graph based on a weighted sum of the plurality of adjacency matrices. The method further includes generating anomaly scores for each node in the merged single layer graph and determining a set of anomalous users based on the anomaly scores.

A computer-implemented method for providing merchant recommendations comprises receiving, by a processor, raw merchant embeddings and raw user embeddings generated from payment transaction records, wherein the raw merchant embeddings include a plurality of embedded features. A generative adversarial network (GAN) performs a disentanglement process on the raw merchant embeddings to remove an effect of an identified feature by generating modified merchant embeddings that are free of the identified feature and are aligned with other ones of the plurality of features. A list of merchant rankings is automatically generates based on the modified merchant embeddings, past preferences of a target user using the raw merchant embeddings, and a current location in which the merchant recommendations should be made. A list of merchant rankings is then provided to the target user.

Growing community of inventors

Palo Alto, CA, United States of America

Michael Yeh