Adobe, Inc.

Sungchul Kim

Eunyee Koh

Ryan A Rossi

Handong Zhao

Anup Bandigadi Rao

Fan Du

Tak Yeon Lee

Sana Malik Lee

Atanu Ranjan Sinha

Branislav Kveton

Tong Yu

Shunan Guo

Vasanthi Holtcamp

Xin Qian

Yikun Xian

Di Jin

Charles Li Chen

Nedim Lipka

Sumit Shekhar

Hung Hai Bui

Subrata Mitra

Nikhil Sheoran

Sheng Li

Deepali Jain

Nikhil Belsare

Deepali Gupta

Ruiyi Zhang

John Boaz Tsang Lee

Zening Qu

Rui Wang

Scott David Cohen

Wei Zhang

William Brandon George

Russell Robert Stringham

Shiv Kumar Saini

Tung Mai

Ritwik Sinha

Zheng Wen

Xiang Chen

David Arbour

Nathan Carl Ross

Jane Elizabeth Hoffswell

Omar Rahman

Said Kobeissi

Thomas M Jacobs

Saurabh Mahapatra

Jordan Walker

Xiaowei Jia

Shashi K Rai

John Anderson

Aldo Gael Carranza

Prithvi Bhutani

Duy-Trung Trong Dinh

Chang Xiao

Abhisek Trivedi

Camille Harris

Andrew Thomson

Caroline Jiwon Kim

Fayokemi Ojo

Sana Lee

Goutham Srivatsav Arra

Jean Bernard Hishamunda

Tyler Rasmussen

Samuel Nephi Grigg

A visualization recommendation system generates recommendation scores for multiple visualizations that combine data attributes of a dataset with visualization configurations. The visualization recommendation system maps meta-features of the dataset to a meta-feature space and configuration attributes of the visualization configurations to a configuration space. The visualization recommendation system generates meta-feature vectors that describe the mapped meta-features, and generates configuration attribute sets that describe the attributes of the visualization configurations. The visualization recommendation system applies multiple scoring models to the meta-feature vectors and configuration attribute sets, including a wide scoring model and a deep scoring model. In some cases, the visualization recommendation system trains the multiple scoring models using the meta-feature vectors and configuration attribute sets.

Machine learning techniques for generating visualization recommendations

Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.

Teaching a machine classifier to recognize a new class

Graphic visualizations, such as charts or graphs conveying data attribute values, can be generated based on natural language queries, i.e., natural language requests. To do so, a natural language request is parsed into n-grams, and from the n-grams, word embeddings are determined using a natural language model. Data attributes for the graphic visualization are discovered in the vector space from the word embeddings. The type of graphic visualization can be determined based on a request intent, which is determined using a trained intent classifier. The graphic visualization is generated to include the data attribute values of the discovered data attributes, and in accordance with the graphic visualization type.

Learning-based method for generating visualizations via natural language

Systems and techniques for multi-task equidistant embedding are described that process categorical feature data to explore feature interactions. A digital analytics system enforces an equidistant relationship among features within a category while extracting high-order feature interactions by punishing both positive correlations and negative correlations among low-dimensional representations of different features. By enforcing an equidistant embedding, information is retained and accuracy is increased while higher order feature interactions are determined. Further, the digital analytics system shares knowledge among different tasks by connecting a shared network representation common to multiple tasks with exclusive network representations specific to particular tasks.

Multi-task equidistant embedding

Various embodiments describe techniques for making inferences from graph-structured data using graph convolutional networks (GCNs). The GCNs use various pre-defined motifs to filter and select adjacent nodes for graph convolution at individual nodes, rather than merely using edge-defined immediate-neighbor adjacency for information integration at each node. In certain embodiments, the graph convolutional networks use attention mechanisms to select a motif from multiple motifs and select a step size for each respective node in a graph, in order to capture information from the most relevant neighborhood of the respective node.

Graph convolutional networks with motif-based attention

The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize a graph neural network to generate data recommendations. The disclosed systems generate a digital graph representation comprising user nodes corresponding to users, data attribute nodes corresponding to data attributes, and edges reflecting historical interactions between the users and the data attributes; Moreover, the disclosed systems generate, utilizing a graph neural network, user embeddings for the user nodes and data attribute embeddings for the data attribute nodes from the digital graph representation. In addition, the disclosed systems generate, utilizing a graph neural network, user embeddings for the user nodes and data attribute embeddings for the data attribute nodes from the digital graph representation. Furthermore, the disclosed systems determine a data recommendation for a target user utilizing the data attribute embeddings and a target user embedding corresponding to the target user from the user embeddings.

Utilizing a graph neural network to generate visualization and attribute recommendations

Systems and methods for lifelong schema matching are described. The systems and methods include receiving data comprising a plurality of information categories, classifying each information category according to a schema comprising a plurality of classes, wherein the classification is performed by a neural network classifier trained based on a lifelong learning technique using a plurality of exemplar training sets, wherein each of the exemplar training sets includes a plurality of examples corresponding to one of the classes, and wherein the examples are selected based on a metric indicating how well each of the examples represents the corresponding class, and adding the data to a database based on the classification, wherein the database is organized according to the schema.

Lifelong schema matching

Disclosed systems and methods predict and visualize outcomes based on past events. For example, an analysis application encodes a sequence of events into a feature vector that includes, for each event, a numerical representation of a respective category and a respective timestamp. The application applies a time-aware recurrent neural network to the feature vector, resulting in one or more of (i) a set of future events in which each event is associated with a probability and a predicted duration and (ii) a sequence embedding that contains information about predicted outcomes and temporal patterns observed in the sequence of events. The application applies a support vector model classifier to the sequence embedding. The support vector model classifier computes a likelihood of a categorical outcome for each of the events in the probability distribution. The application modifies interactive content according to the categorical outcomes and probability distribution.

Predicting and visualizing outcomes using a time-aware recurrent neural network

Methods and systems disclosed herein relate generally to systems and methods for using a machine-learning model to predict user-engagement levels of users in response to presentation of future interactive content. A content provider system accesses a machine-learning model, which was trained using a training dataset including previous user-device actions performed by a plurality of users in response to previous interactive content. The content provider system receives user-activity data of a particular user and applies the machine-learning model to the user-activity data, in which the user-activity data includes user-device actions performed by the particular user in response to interactive content. The machine-learning model generates an output including a categorical value that represents a predicted user-engagement level of the particular user in response to a presentation of the future interactive content.

Provisioning interactive content based on predicted user-engagement levels

Embodiments of the present invention provide systems, methods, and computer storage media for latent summarization of a graph. Structural features can be captured from feature vectors associated with each node of the graph by applying base functions on the feature vectors and iteratively applying relational operators to successive feature matrices to derive deeper inductive relational functions that capture higher-order structural information in different subgraphs of increasing size (node separations). Heterogeneity can be summarized by performing capturing features in appropriate subgraphs (e.g., node-centric neighborhoods associated with each node type, edge direction, and/or edge type). Binning and/or dimensionality reduction can be applied to the resulting feature matrices. The resulting set of relational functions and multi-level feature matrices can form a latent summary that can be used to perform a variety of graph-based tasks, including node classification, node clustering, link prediction, entity resolution, anomaly and event detection, and inductive learning tasks.

Latent network summarization

Methods, computer systems, computer-storage media, and graphical user interfaces are provided for facilitating data visualization generation. In one implementation, dataset intent data, visual design intent data, and insight intent data determined from a user input natural language query are obtained. A set of candidate intent recommendations is generated using various combinations of the dataset intent data, visual design intent data, and insight intent data. Each of the candidate intent recommendations is incorporated into a set of visualization templates to determine eligibility of the candidate intent recommendations. For eligible candidate intent recommendations, a score associated with a corresponding visualization template is determined. Based on the scores, a candidate intent recommendation and corresponding visualizations template is selected to use as a visual recommendation for presenting a data visualization.

Facilitating generation of data visualizations via natural language processing

In some embodiments, a data visualization system detects insights from a dataset and computes insight scores for respective insights. The data visualization system further computes insight type scores, from the insight scores, for insight types in the detected insights. The data visualization system determines a selected insight type for the dataset having a higher insight type score than unselected insight types and determines, for the selected insight type, a set of selected insights that have higher insight scores than unselected insights. The data visualization system determines insight visualizations for the set of selected insights and generates, for inclusion in a user interface of the data visualization system, selectable interface elements configured for invoking an editing tool for updating the determined insight visualizations from the dataset. The selectable interface elements are arranged in the user interface according to the insight scores of the set of selected insights.

Configuration of user interface for intuitive selection of insight visualizations

Systems and methods for personalized visualization recommendation are described. Embodiments of the described systems and methods are configured to identify a first matrix representing user interactions with a plurality of data attributes corresponding to a plurality of datasets, a second matrix representing user interactions with a plurality of visualizations, and a third matrix representing a plurality of meta-features for each of the data attributes; compute low-dimensional embeddings representing user characteristics, the data attributes, visualization configurations, and the meta-features using joint factorization of the first matrix, the second matrix and the third matrix; generate a model for predicting visualization preference weights based on the low-dimensional embeddings; predict the visualization preference weights for a user corresponding to a plurality of candidate visualizations of dataset using the model; and generate a personalized visualization of the dataset for the user based on the predicted visualization preference weights.

Personalized visualization recommendation system

Systems, methods, and non-transitory computer-readable media are disclosed for generating generate explanatory paths for column annotations determined using a knowledge graph and a deep representation learning model. For instance, the disclosed systems can utilize a knowledge graph to generate an explanatory path for a column label determination from a deep representation learning model. For example, the disclosed systems can identify a column and determine a label for the column using a knowledge graph (e.g., a representation of a knowledge graph) that includes encodings of columns, column features, relational edges, and candidate labels. Then, the disclosed systems can determine a set of candidate paths between the column and the determined label for the column within the knowledge graph. Moreover, the disclosed systems can generate an explanatory path by ranking and selecting paths from the set of candidate paths using a greedy ranking and/or diversified ranking approach.

Generating explanatory paths for predicted column annotations

Growing community of inventors

San Jose, CA, United States of America

Sungchul Kim