Abstract: The disclosure herein describes providing item selection recommendations using prediction scores based on a user's selection cycle of an item. A set of filter weights is generated using a trained hypernetwork. The set of filter weights is specific to a user and an item. Each filter weight is indicative of a probability that the user will select the item at the associated time period. A prediction score is generated for the item using the set of filter weights and item selection history data of the user, including a time period at which the user last selected the item. A selection recommendation is then provided to the user based at least in part on the generated prediction score during a current time period. The disclosure uses filter weights associated with explicit time periods to capture selection cycles of items for the user to improve the accuracy of provided selection recommendations.

Abstract: A diagnostic tool for deep learning similarity models and image classifiers provides valuable insight into neural network decision-making. A disclosed solution generates a saliency map by: receiving a test image; determining, with an image classifier, an image classification of the test image; determining, for the test image, a first activation map for at least one model layer using the determined image classification; determining, for the test image, a first gradient map for the at least one model layer using the determined image classification; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map.

Abstract: Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.

Abstract: The disclosure herein describes a system for interpreting text-based similarity between a seed item and a recommended item selected by a pre-trained language model from a plurality of candidate items based on semantic similarities between the seed item and the recommended item. The system analyzes similarity scores and contextual paragraph representations representing text-based descriptions of the seed item and recommended item to generate gradient maps and word scores representing the text-based descriptions. A model for interpreting text-based similarity utilizes the calculated gradients and word scores to match words from the seed item description with words in the recommended item description having similar semantic meaning. The word-pairs having the highest weight are identified by the system as the word-pairs having the greatest influence over the selection of the recommended item from the candidate items by the original pre-trained language model.

Abstract: Embodiments are described for automatically generating threshold values based on a target metric value that specifies a desired precision or recall performance of an ML model. For instance, a trained ML model is executed against a data set using possible threshold values. Accuracy metric(s) of the ML model is determined based on the execution. Using the accuracy metric(s), evaluation metrics are modeled. A probability that a first modeled evaluation metric value has a relationship with a target metric value is determined. A determination is made that the probability has a relationship with a confidence level. Responsive to determining that the probability has the relationship with the confidence level, the threshold value is added to a set of candidate threshold values. The threshold value from among the set of candidate threshold values is selected by selecting the candidate threshold value associated with the largest second modeled evaluation metric value.

Abstract: Semantic search techniques via focused summarizations are described. For example, a search query is received for a text-based content item in a data set comprising a plurality of text-based content items. A first feature vector representative of the search query is obtained. A respective semantic similarity score is determined between the first feature vector and each of a plurality of second feature vectors. Each of the second feature vectors is representative of a machine-generated summarization of a respective text-based content item. The machine-generated summarization comprises a plurality of multi-word fragments that are selected from the respective text-based content item via a transformer-based machine learning model. A search result is provided responsive to the search query.

Abstract: A comparison engine performs item similarity comparisons. A source item and one or more candidate items are input into a triplet-trained machine learning model trained using training data including triplets of anchor elements, positive elements, and negative elements. Each triplet corresponds to an item included in the training data. The anchor elements and the positive elements are included in the corresponding item. The negative element is included in a different item in the training data. A similarity score between the source item and each of the one or more candidate items is generated from the triplet-trained machine learning model.

Abstract: Solutions for visual search and discovery include performing unsupervised training of a generative adversarial network that has a generator and an assessor. Training the generative adversarial network involves alternating training the assessor with the generator and a plurality of catalog images with training the generator with the assessor. The catalog images are inverted into catalog vectors by leveraging the trained generator. A query image is inverted into a query vector, and image similarity is determined by calculating a distance between the query vector and a catalog vector. In some examples, inversion is performed by training an encoder with the trained generator and inverting the catalog images with the encoder. In some examples, the trained generator is used to perform a search in a vector space. A weighting vector may be used to weight elements of the vectors, effectively prioritizing image features for image similarity determination.

Abstract: Machine learning multiple features of an item depicted in images. Upon accessing multiple images that depict the item, a neural network is used to machine train on the plurality of images to generate embedding vectors for each of multiple features of the item. For each of multiple features of the item depicted in the images, in each iteration of the machine learning, the embedding vector is converted into a probability vector that represents probabilities that the feature has respective values. That probability vector is then compared with a value vector representing the actual value of that feature in the depicted item, and an error between the two vectors is determined. That error is used to adjust parameters of the neural network used to generate the embedding vector, allowing for the next iteration in the generation of the embedding vectors. These iterative changes continue thereby training the neural network.

Abstract: A diagnostic tool for deep learning similarity models and image classifiers provides valuable insight into neural network decision-making. A disclosed solution generates a saliency map by: receiving a baseline image and a test image; determining, with a convolutional neural network (CNN), a first similarity between the baseline image and the test image; based on at least determining the first similarity, determining, for the test image, a first activation map for at least one CNN layer; based on at least determining the first similarity, determining, for the test image, a first gradient map for the at least one CNN layer; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map. Some examples further determine a region of interest (ROI) in the first saliency map, cropping the test image to an area corresponding to the ROI, and determine a refined similarity score.

Abstract: Machine learning multiple features of an item depicted in images. Upon accessing multiple images that depict the item, a neural network is used to machine train on the plurality of images to generate embedding vectors for each of multiple features of the item. For each of multiple features of the item depicted in the images, in each iteration of the machine learning, the embedding vector is converted into a probability vector that represents probabilities that the feature has respective values. That probability vector is then compared with a value vector representing the actual value of that feature in the depicted item, and an error between the two vectors is determined. That error is used to adjust parameters of the neural network used to generate the embedding vector, allowing for the next iteration in the generation of the embedding vectors. These iterative changes continue thereby training the neural network.

Abstract: A method of training a machine learning model is provided. The method includes receiving labeled training data in the machine learning model, the received labeled training data including content data for items accessible to a user and input usage data representing recorded interaction between the user and the items, wherein the received content data for each item includes data representing intrinsic attributes of the item. The method further includes selecting a set of the input usage data that excludes input usage data for a proper subset of the items and training the machine learning model based on both the content data and the selected set of input usage data of the received labeled training data for the items.

Abstract: A relational similarity determination engine receives as input a dataset including a set of entities and co-occurrence data that defines co-occurrence relations for pairs of the entities. The relational similarity determination engine also receives as input side information defining explicit relations between the entities. The relational similarity determination engine jointly models the co-occurrence relations and the explicit relations for the entities to compute a similarity metric for each different pair of entities within the dataset. Based on the computed similarity metrics, the relational similarity determination engine identifies a most similar replacement entity from the dataset for each of the entities within the dataset. For a select entity received as an input, the relational similarity determination engine outputs the identified most similar replacement entity.

Abstract: A computing system scores importance of a number of tokens in an input token sequence to one or more prediction scores computed by a neural network model on the input token sequence. The neural network model includes multiple encoding layers. Self-attention matrices of the neural network model are received into an importance evaluator. The self-attention matrices are generated by the neural network model while computing the one or more prediction scores based on the input token sequence. Each self-attention matrix corresponds to one of the multiple encoding layers. The importance evaluator generates an importance score for one or more of the tokens in the input token sequence. Each importance score is based on a summation as a function of the self-attention matrices, the summation being computed across the tokens in the input token sequence, across the self-attention matrices, and across the multiple encoding layers in the neural network model.

Abstract: A method of generating an aggregate saliency map using a convolutional neural network. Convolutional activation maps of the convolutional neural network model are received into a saliency map generator, the convolutional activation maps being generated by the neural network model while computing the one or more prediction scores based on unlabeled input data. Each convolutional activation map corresponds to one of the multiple encoding layers. The saliency map generator generates a layer-dependent saliency map for each encoding layer of the unlabeled input data, each layer-dependent saliency map being based on a summation of element-wise products of the convolutional activation maps and their corresponding gradients. The layer-dependent saliency maps are combined into the aggregate saliency map indicating the relative contributions of individual components of the unlabeled input data to the one or more prediction scores computed by the convolutional neural network model on the unlabeled input data.

Abstract: An anchor-based collaborative filtering system receives a training dataset including user-item interactions each identifying a user and an item that the user has positively interacted with. The system defines a vector space and distributes the items of the training dataset within the vector based on a determined similarity of the items. The system further defines a set of taste anchors that are each associated in memory with a subgroup of the items in a same neighborhood of the vector space. To make a recommendation to an individual user, the system identifies an anchor-based representation for the individual user that includes a subset of the defined taste anchors that best represents the types of items that the user has favorably interacted with in the past. The taste anchors included in the identified anchor-based representation for the individual user are used to make recommendations to the user in the future.

Abstract: Solutions for localizing relevant objects in multi-object images include receiving a multi-object image; detecting a plurality of detected objects within the multi-object image; generating a primary heatmap for the multi-object image, the primary heatmap having at least one region of interest; determining a relevant detected object corresponding to a region of interest in the primary heatmap; determining an irrelevant detected object not corresponding to a region of interest in the primary heatmap; and indicating the relevant detected object as an output result but not indicating the irrelevant detected object as an output result. Some examples identify a plurality of objects that are visually similar to the relevant object and displaying the visually similar objects to a user, for example as recommendations of alternative catalog items on an e-commerce website. Some examples are able to identify a plurality of relevant objects and display multiple sets of visually similar objects.

Abstract: Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.

Abstract: A diagnostic tool for deep learning similarity models and image classifiers provides valuable insight into neural network decision-making. A disclosed solution generates a saliency map by: receiving a baseline image and a test image; determining, with a convolutional neural network (CNN), a first similarity between the baseline image and the test image; based on at least determining the first similarity, determining, for the test image, a first activation map for at least one CNN layer; based on at least determining the first similarity, determining, for the test image, a first gradient map for the at least one CNN layer; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map. Some examples further determine a region of interest (ROI) in the first saliency map, cropping the test image to an area corresponding to the ROI, and determine a refined similarity score.

Abstract: Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.