Abstract: Embodiments are directed to methods and systems for media classification that may be used to better improve classification models and understand results of such classification. Various embodiments can determine a classification for a media item and can determine a prompt that includes the classification for a media item. Further embodiments can train a machine learning model using media items with known classifications. The results of each training iteration may be used to understand the result and improve the machine learning model.

Abstract: Methods, systems, and computer program products are provided for pretrained dual transformers for bipartite graphs. Graph data of a bipartite graph including first nodes/entities, second nodes/entities, and edges is received. A first entity context of each first entity includes second entities connected thereto by the edge(s). A second entity context of each second entity/node comprises first entities connected thereto the edge(s). First embeddings for each first entity are generated. First encoded representations for each first entity are generated based on the first entity context and a first transformer encoder. Second embeddings for each second entity are generated. Second encoded representations for each second entity are generated based on the second entity context and a second transformer encoder. The first embeddings and the first transformer encoder are adjusted based on a first contrastive loss. The second embeddings and the second transformer encoder are adjusted based on a second contrastive loss.

Abstract: Described are a system, method, and computer program product for debiasing embedding vectors of machine learning models. The method includes receiving embedding vectors and generating two clusters thereof. The method includes determining a first mean vector of the first cluster and a second mean vector of the second cluster. The method includes determining a bias associated with each of a plurality of first candidate vectors and replacing the first mean vector with a first candidate vector based on the bias. The method includes determining a bias associated with each of a plurality of second candidate vectors and replacing the second mean vector with a second candidate vector based on the bias. The method includes repeatedly replacing the first and second mean vectors until an extremum of the bias score is reached, and debiasing the embedding vectors by linear projection using a direction defined by the first and second mean vectors.

Abstract: Methods, systems, and computer program products are provided for analyzing and/or improving transformer models. A method may include receiving a trained transformer model. The trained transformer model may include at least one multi-head self-attention layer including a plurality of attention heads. At least one sample may be received. The sample(s) may be inputted to the trained transformer model to generate at least one layer output of the multi-head self-attention layer(s) and at least one model output of the trained transformer model. Each respective attention head may be pruned, and the sample(s) may be inputted to the trained transformer model with the respective attention head pruned to generate at least one respective pruned layer output and at least one respective pruned model output. At least one importance metric may be determined for each respective attention head based on at least two of the aforementioned outputs.

Abstract: Methods and systems for anonymizing time-series data are disclosed. An anonymizing computer can generate an anonymized sequence of time-series data that can share many useful properties, patterns, or characteristics with a private sequence of time-series data, without revealing sensitive or private information about the private sequence of time-series data. This may enable data researchers and scientists to study the anonymized sequence of time-series data in lieu of the private sequence of time-series data, thereby preserving the privacy of data subjects (e.g., people) corresponding to the private sequence of time-series data. The anonymized sequence of time-series data can be generated using an iterative optimization process that can involve updating the anonymized sequence of time-series data to minimize a loss value. The loss value can correspond to both the utility and privacy of the anonymized sequence of time-series data.

Abstract: The present disclosure relates to an embedded wafer level ball grid array package (eWLB package). The eWLB package comprises a mold enclosing an integrated circuit, a dielectric entity arranged in the mold, and a microstrip line electrically connected with the integrated circuit. In a direction towards a connection side of the eWLB package comprising connection elements, an end part of the microstrip line is arranged below the dielectric entity. The dielectric entity has a dimension perpendicular to the microstrip line equaling a quarter of a wavelength for which the microstrip line is designed. The eWLB package is configured to be connected via the connection elements to a printed circuit board (PCB) with a waveguide in the form of a passageway opening in the PCB, such that the dielectric entity and the end part of the microstrip line are aligned with the waveguide.

Abstract: A monomer capable forming a polymer through ring-opening metathesis polymerization and capable of depolymerization thereafter through ring-closing metathesis, wherein the monomer comprises a cycloalkene having a fused ring attached thereto to form a cycloalkene-fused ring monomer, wherein the fused ring decreases the ring strain energy of the cycloalkene to a lower ring strain energy state of 5.3 kcal/mol or lower as compared to the same cycloalkene without the fused ring having a ring strain energy above 5.3 kcal/mol and wherein the cycloalkene-fused ring monomer is capable of isomerization into a higher ring strain energy state before polymerization and method of synthesizing the monomer. The monomer is further capable of forming chemically recyclable to monomers block copolymers.

Abstract: Systems, methods, and computer program products are provided for machine learning model visualization and optimized deployment. An example system includes at least one processor configured to generate a first set of candidate code objects using a first machine learning model, determine, for each candidate code object of the first set of candidate code objects, at least one value of at least one performance parameter, and deploy a selected code object of the first set of candidate code objects in a production environment based at least partly on the selected code object having an optimized value of the at least one performance parameter.

Abstract: Methods, systems, and computer program products are provided for content-based time series retrieval. An example system includes at least one processor configured to: obtain, from at least one database, a plurality of known time series; for each known time series of the plurality of known time series: compute a pairwise distance matrix between that known time series and each learned template of a plurality of learned templates to generate a plurality of pairwise distance matrices; stack the plurality of pairwise distance matrices together to generate a tensor; and process, with the residual network, the tensor, wherein the residual network receives, as input, the tensor, and provides, as output, a feature vector for that known time series; and provide the feature vector for each known time series of the plurality of known time series.

Abstract: A method for detecting collusive transaction fraud includes: generating a merchant baseline including a transaction data baseline and a time series baseline; extracting time series data of the first merchant system; generating a first score and second score with a deep learning model; generating a first merchant risk score of the first merchant system based on the first and second scores; in response to determining that the first merchant risk score satisfies the threshold, determining a plurality of related entities related to the first merchant system; and classifying the first merchant system and at least one related entity of the plurality of related entities in a first group risk class based on at least one risk score of the at least one related entity.

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: A method of producing a vitrimer includes reacting an epoxide group containing compound with a carboxylic acid group containing compound, where one or more of the epoxide group containing compound and the carboxylic acid group containing compound is a polycarbonate-based material. The vitrimer includes a ?-hydroxy ester group where the epoxide group reacts with the carboxylic acid group. A composition includes a vitrimer which is a reaction product of an epoxide group containing compound and a carboxylic acid group containing compound, where one or more of the epoxide group containing compound and the carboxylic acid group containing compound is a polycarbonate-based material.

Abstract: Methods, systems, and computer program products for traffic flow forecasting: obtain a graph representing a traffic network; obtain historical time-series traffic data associated with historical traffic conditions at a number of historical time steps in the traffic network; process, with each spatial-temporal graph sandwich transformer of at least one spatial-temporal graph sandwich transformer, the graph and the historical time-series traffic data to generate a sandwich transformer output, wherein each spatial-temporal graph sandwich transformer includes a top temporal transformer, a spatial transformer that receives, as an input, an output of the top temporal transformer and the graph, and a bottom temporal transformer that receives, as an input, an output of the spatial transformer; and generate, based on the sandwich transformer output from each spatial-temporal graph sandwich transformer, predicted time-series traffic data associated with predicted traffic conditions at a number of next time steps in the

Abstract: Described are a system, method, and computer program product for debiasing embedding vectors of machine learning models. The method includes receiving embedding vectors and generating two clusters thereof. The method includes determining a first mean vector of the first cluster and a second mean vector of the second cluster. The method includes determining a bias associated with each of a plurality of first candidate vectors and replacing the first mean vector with a first candidate vector based on the bias. The method includes determining a bias associated with each of a plurality of second candidate vectors and replacing the second mean vector with a second candidate vector based on the bias. The method includes repeatedly replacing the first and second mean vectors until an extremum of the bias score is reached, and debiasing the embedding vectors by linear projection using a direction defined by the first and second mean vectors.

Abstract: A method, system, and computer program product is provided for embedding compression and reconstruction. The method includes receiving embedding vector data comprising a plurality of embedding vectors. A beta-variational autoencoder is trained based on the embedding vector data and a loss equation. The method includes determining a respective entropy of a respective mean and a respective variance of each respective dimension of a plurality of dimensions. A first subset of the plurality of dimensions is determined based on the respective entropy of the respective mean and the respective variance for each respective dimension of the plurality of dimensions. A second subset of the plurality of dimensions is discarded based on the respective entropy of the respective mean and the respective variance for each respective dimension of the plurality of dimensions. The method includes generating a compressed representation of the embedding vector data based on the first subset of dimensions.

Abstract: A monomer capable forming a polymer through ring-opening metathesis polymerization and capable of depolymerization thereafter through ring-closing metathesis, wherein the monomer comprises a cycloalkene having a fused ring attached thereto which decreases the ring strain energy to 5.3 kcal/mol or lower as compared to the same cycloalkene without a fused ring having a ring strain energy above 5.3 kcal/mol.

Abstract: Provided are methods for generating a multitask machine learning model based on time series data, that may include receiving input time series data associated with an input time series of data points, calculating a pairwise distance between the input time series and a plurality of time series templates, providing the pairwise distance as a first input to a building block of a residual neural network, where the residual neural network has a plurality of multi-dimensional convolutional layers; generating a first output of the first building block of the residual neural network based on the first input, generating a final output of the residual neural network based on the first output, and generating a first output of a multitask machine learning model using a first output layer and a second output of the multitask machine learning model using a second output layer. Systems and computer program products are also disclosed.

Abstract: A mechanochemical method for recycling polystyrene. The method includes providing polystyrene, grinding the polystyrene to thereby obtain benzene, and wherein the step of grinding the polystyrene further comprises combining AlCl3 with the polystyrene during the grinding. The obtained benzene is then able to be recycled into styrene monomer. The obtained benzene is also able to be upcycled into benzophenone.

Abstract: Systems, methods, and computer program products for multi-head posterior based pre-trained model evaluation are provided. The system includes at least one processor configured to: generate an embedding dataset based on a pre-trained model, the embedding dataset including a plurality of embeddings representing a plurality of entities; cluster each entity of the plurality of entities based on a feature dataset, resulting in a plurality of clusters; and generate a metric for the pre-trained model based on a posterior probability of each entity of the plurality of entities and the plurality of clusters.