Abstract: Systems, methods, and computer program products train a residual neural network including a first fully connected layer, a first recurrent neural network layer, and at least one skip connection for anomaly detection. The at least one skip connection directly connects at least one of (i) an output of the first fully connected layer to a first other layer downstream of the first recurrent neural network layer in the residual neural network and (ii) an output of the first recurrent neural network layer to a second other layer downstream of a second recurrent neural network layer in the residual neural network.

Abstract: A method for recurrent neural networks for asynchronous sequences may include receiving first input data associated with a plurality of first data items ordered in a first sequence and second input data associated with a plurality of second data items ordered in a second sequence. Each first data item may be of a first type, and each second data item may be of a second type. Each respective data item of the first and second data items may be inputted with an indicator associated with a respective type of the respective data item to a recurrent unit of a recurrent neural network (RNN). A respective portion of a hidden state may be determined based on the indicator. The respective portion of the hidden state may be updated based on the respective data item and the indicator. A system and computer program product are also disclosed.

Abstract: A method for recurrent neural networks for asynchronous sequences may include receiving first input data associated with a plurality of first data items ordered in a first sequence and second input data associated with a plurality of second data items ordered in a second sequence. Each first data item may be of a first type, and each second data item may be of a second type. Each respective data item of the first and second data items may be inputted with an indicator associated with a respective type of the respective data item to a recurrent unit of a recurrent neural network (RNN). A respective portion of a hidden state may be determined based on the indicator. The respective portion of the hidden state may be updated based on the respective data item and the indicator. A system and computer program product are also disclosed.

Abstract: Provided are systems for generating a machine learning model for classification tasks using unadversarial training that include a processor to perform an unadversarial training procedure to train a machine learning model to provide a trained machine learning model. When performing the unadversarial training procedure, the processor is programmed or configured to receive a training dataset including a plurality of training samples; generate a noise vector for the plurality of training samples based on a uniform distribution; perturb each training sample of the plurality of training samples; obtain a gradient; generate an updated noise vector based on the gradient; perturb each training sample of the plurality of training samples based on the updated noise vector; and update a model weight of the machine learning model based on the second plurality of perturbed training samples to provide the trained machine learning model. Methods and computer program products are also provided.

Abstract: Provided are methods, systems, and computer program products for unsupervised alignment of embedding spaces. A method may include receiving a first embedding matrix and a second embedding matrix. The first embedding matrix may include a plurality of source points and the second embedding matrix may include a plurality of target points. An initial permutation matrix and an initial orthogonal matrix may be initialized. A permutation matrix may be determined based on the initial permutation matrix, the first embedding matrix, and the second embedding matrix. An orthogonal matrix may be determined based on the initial orthogonal matrix, the first embedding matrix, the permutation matrix, and the second embedding matrix. For each step of a target number of steps, the following may be repeated: updating the permutation matrix based on a quantized 2-Wasserstein distance, and updating the orthogonal matrix based on a gradient descent and a Procrustes problem.

Abstract: Provided are systems for generating a machine learning model for classification tasks using unadversarial training that include a processor to perform an unadversarial training procedure to train a machine learning model to provide a trained machine learning model. When performing the unadversarial training procedure, the processor is programmed or configured to receive a training dataset including a plurality of training samples; generate a noise vector for the plurality of training samples based on a uniform distribution; perturb each training sample of the plurality of training samples; obtain a gradient; generate an updated noise vector based on the gradient; perturb each training sample of the plurality of training samples based on the updated noise vector; and update a model weight of the machine learning model based on the second plurality of perturbed training samples to provide the trained machine learning model. Methods and computer program products are also provided.

Abstract: Methods for adversarial training and/or for analyzing the impact of fine-tuning on deep learning models may include receiving a deep learning model comprising a set of parameters and a dataset of samples. A respective noise vector for a respective sample may be generated based on a length of the sample and a radius hyperparameter. For a target number of steps, the following may be repeated: adjusting the noise vector based on a step size hyperparameter, and projecting the respective noise vector to be within a boundary. The parameters of the deep learning model may be adjusted based on a gradient of a loss based on the noise vector. This may be repeated for each sample of the plurality of samples. A system and computer program product are also disclosed.

Abstract: Provided are systems for generating a machine learning model for classification tasks using unadversarial training that include a processor to perform an unadversarial training procedure to train a machine learning model to provide a trained machine learning model. When performing the unadversarial training procedure, the processor is programmed or configured to receive a training dataset including a plurality of training samples; generate a noise vector for the plurality of training samples based on a uniform distribution; perturb each training sample of the Generate a noise vector plurality of training samples; obtain a gradient; generate an updated noise vector based on the gradient; perturb each training sample of the plurality of training samples based on the updated noise vector; and update a model weight of the machine learning model based on the second plurality of Obtain a gradient perturbed training samples to provide the trained machine learning model.

Abstract: A method performed by a server computer is disclosed. The method comprises generating a binary compositional code matrix from an input matrix. The binary compositional code matrix is then converted into an integer code matrix. Each row of the integer code matrix is input into a decoder, including plurality of codebooks, to output a summed vector for each row. The method then includes inputting a derivative of each summed vector into a downstream machine learning model to output a prediction.

Abstract: A method performed by a computer is disclosed. The method comprises receiving interaction data between electronic devices of a plurality of entities. The interaction data is used to form an entity interaction vector containing a number of interactions between the electronic devices of a chosen entity and an entity time series containing a plurality of metrics per unit time of the interactions. An interaction encoder of the computer can generate an interaction hidden representation of the entity interaction vector using embeddings of the plurality of entities. A temporal encoder of the computer can generate a temporal hidden representation of the entity time series. The interaction hidden representation and the temporal hidden representation can be used to generate a predicted scale and a shape estimation of a target interaction metric. The computer can then generate an estimated interaction metric of a time period using the predicted scale and the shape estimation.

Abstract: Systems, methods, and computer program products train a residual neural network including a first fully connected layer, a first recurrent neural network layer, and at least one skip connection for anomaly detection. The at least one skip connection directly connects at least one of (i) an output of the first fully connected layer to a first other layer downstream of the first recurrent neural network layer in the residual neural network and (ii) an output of the first recurrent neural network layer to a second other layer downstream of a second recurrent neural network layer in the residual neural network.

Abstract: Methods and systems are described. A method includes accessing transaction data related to restaurants associated with a plurality of geographically separate locations, determining a number of co-visitors shared by each of the restaurants associated with the plurality of geographically separate locations above a predetermined threshold, generating a graphical representation of the plurality of restaurants based on the number of the co-visitors shared by restaurants with the co-visitors above the predetermined threshold and the distance between the restaurants with the co-visitors. The graphical representation is transformed into restaurant embeddings and a neural network model is used to generate restaurant preferences based on the restaurant embeddings.

Abstract: A method for recurrent neural networks for asynchronous sequences may include receiving first input data associated with a plurality of first data items ordered in a first sequence and second input data associated with a plurality of second data items ordered in a second sequence. Each first data item may be of a first type, and each second data item may be of a second type. Each respective data item of the first and second data items may be inputted with an indicator associated with a respective type of the respective data item to a recurrent unit of a recurrent neural network (RNN). A respective portion of a hidden state may be determined based on the indicator. The respective portion of the hidden state may be updated based on the respective data item and the indicator. A system and computer program product are also disclosed.

Abstract: Methods and systems are described. A method includes accessing transaction data related to restaurants associated with a plurality of geographically separate locations, determining a number of co-visitors shared by each of the restaurants associated with the plurality of geographically separate locations above a predetermined threshold, generating a graphical representation of the plurality of restaurants based on the number of the co-visitors shared by restaurants with the co-visitors above the predetermined threshold and the distance between the restaurants with the co-visitors. The graphical representation is transformed into restaurant embeddings and a neural network model is used to generate restaurant preferences based on the restaurant embeddings.

Abstract: Methods and systems are described. A method includes accessing transaction data related to restaurants associated with a plurality of geographically separate locations, determining a number of co-visitors shared by each of the restaurants associated with the plurality of geographically separate locations above a predetermined threshold, generating a graphical representation of the plurality of restaurants based on the number of the co-visitors shared by restaurants with the co-visitors above the predetermined threshold and the distance between the restaurants with the co-visitors. The graphical representation is transformed into restaurant embeddings and a neural network model is used to generate restaurant preferences based on the restaurant embeddings.

Abstract: Methods and systems are described. A method includes accessing transaction data related to restaurants associated with a plurality of geographically separate locations, determining a number of co-visitors shared by each of the restaurants associated with the plurality of geographically separate locations above a predetermined threshold, generating a graphical representation of the plurality of restaurants based on the number of the co-visitors shared by restaurants with the co-visitors above the predetermined threshold and the distance between the restaurants with the co-visitors. The graphical representation is transformed into restaurant embeddings and a neural network model is used to generate restaurant preferences based on the restaurant embeddings.