Adobe, Inc.

Palo Alto Research Center Inc.

Xerox Corporation

Panasonic Corporation

Palo Alto Research Company Incorporated

Ryan A Rossi

Eunyee Koh

Fan Du

Anup Bandigadi Rao

Sungchul Kim

Tung Mai

Sana Malik Lee

Tak Yeon Lee

Rong Zhou

Shunan Guo

Viswanathan Swaminathan

Jane Elizabeth Hoffswell

Nedim Lipka

Handong Zhao

Iftikhar Ahamath Burhanuddin

Vasanthi Holtcamp

Ajay Raghavan

Saayan Mitra

Georgios Theocharous

Gang Wu

Somdeb Sarkhel

Charles Menguy

Margarita Savova

Nathan Carl Ross

Xin Qian

Yeuk-Yin Chan

Di Jin

John Anderson

Jungho Park

William Brandon George

Shivakumar Vaithyanathan

Niyati Himanshu Chhaya

Vishwa Vinay

Michele Saad

Sumit Shekhar

Ritwik Sinha

Xiang Chen

Matvey Kapilevich

Said Kobeissi

Saurabh Mahapatra

Zhao Song

Thomas Greger

Yikun Xian

Prithvi Bhutani

John Boaz Tsang Lee

Shenyu Xu

Kirankumar Shiragur

Aldo Gael Carranza

Zening Qu

Md Main Uddin Rony

Abhisek Trivedi

Chang Xiao

Nathan Ng

Kelly Quinn Nicholes

Antonio Cuevas

Qisheng Li

Scott David Cohen

Franck Dernoncourt

Wei Zhang

Tetsuyoshi Ogura

Russell Robert Stringham

Chen Chen

Atanu Ranjan Sinha

Stefano Petrangeli

Akira Minegishi

Subrata Mitra

Sonali Surange

Yosuke Tajika

Haoliang Wang

Tong Yu

Tracy Holloway King

Kshitiz Garg

Zhicheng Liu

David Arbour

Hoda M A Eldardiry

Kanak Vivek Mahadik

Ali Aminian

Uttaran Bhattacharya

Yasin Abbasi Yadkori

Moumita Sinha

Nikhil Belsare

Vibhor Porwal

Jordan Walker

Manoj Kilaru

Gautam Choudhary

Guillaume L Escarguel

Han Guo

Charles Li Chen

Duy-Trung Trong Dinh

Alexandru Ionut Hodorogea

Arpit Ajay Narechania

Alireza Farhadi

Seyedsaed Rezayidemne

Camille Harris

Andrew Thomson

Shaurya Goel

Vidit Jain

Pratyush Garg

Harkanwar Singh

Techniques for data question answering with auxiliary recommendations are described to enable efficient querying of data sets for answers to data questions based on a natural language input. In an example, a processing device is operable to receive a natural language input including a query, determine an additional query based on a context of the query, and query a machine-learning model using the query and the additional query. The processing device is further operable to receive, from the machine-learning model, a result including a quantitative answer to the query, an additional answer based on the additional query, and an explanation by the machine-learning model of how the machine-learning model generated the quantitative answer or the additional answer in response to the querying. The processing device is operable to present the result for display in a user interface.

Data question answering with auxiliary recommendations

Embodiments provide systems, methods, and computer storage media for determining string similarity and pattern matching in strings that arrive in a stream. A stream representing string of characters is received and used to compute mapping values that are compared to a mapping value of a query string to identify a match between strings in the stream of characters and the query string. The stream of characters is searched in a single sequential pass to detect a match or the longest matching substring with a query string. An identified match or absence of a match is provided.

System and methods for streaming string similarity and pattern matching

In implementations of systems for generating node embeddings for multiple roles, a computing device implements an embeddings system to cluster nodes of a graph into clusters. An initial role membership vector is computed for each of the nodes based on the clusters. The embeddings system generates a first set of role embeddings for a particular node of the nodes based on the initial role membership vector for the particular node and nodes connected to the particular node in the graph. The embeddings system determines an indication of at least one of a node classification or a link prediction for the graph based on the first set of role embeddings and a second set of role embeddings for an additional node of the nodes.

Generating node embeddings for multiple roles

Systems and methods for training a neural network are described. One or more embodiments of the present disclosure include training a neural network based on a first combined gradient of a loss function at a plurality of sampled elements of a dataset; receiving an insertion request that indicates an insertion element to be added to the dataset, or a deletion request that indicates a deletion element to be removed from the dataset, wherein the deletion element is one of the plurality of sampled elements; computing a second combined gradient of the loss function by adding the insertion element to the dataset or by replacing the deletion element with a replacement element from the dataset; determining whether the first combined gradient and the second combined gradient satisfy a stochastic condition; and retraining the neural network to obtain a modified neural network based on the determination.

Machine unlearning and retraining of a machine learning model based on a modified training dataset

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

Methods and systems are provided for using reinforcement learning to recommend data visualizations. In embodiments described herein, statistical features for each sample of corresponding samples of a dataset are determined by applying each sample of the dataset to a data visualization recommendation model. The computational cost of each of the statistical features for each of the samples is determined based via a regression model. Recommended statistical features are determined by sequentially applying each sample to a reinforcement learning model with a computational budget and with the corresponding computational costs of the statistical features of each sample. A data visualization is then displayed that is generated by applying the dataset and the recommended statistical features to the data visualization recommendation model.

Using reinforcement learning to recommend data visualizations

Embodiments of the present invention provide systems, methods, and computer storage media for generating and recommending responsive visualizations. In an example embodiment, a design specification of a source visualization and an author's preferences are used to identify and rank compatible sets of candidate responsive transformations (e.g., using answer set programming). Each set is evaluated and ranked according to one or more cost metrics that quantify changes in information density, messaging, or popularity. Some embodiments generate a transformation specification in a declarative grammar that represent the sets of candidate responsive transformations independent of the structure of the source visualization specifications, compile each declarative transformation specification into a rendering grammar specification, and generate a responsive visualization by compiling the rendering grammar specification using a rendering grammar compiler. In some embodiments, the highest ranked responsive visualizations are presented as authoring recommendations and/or the highest ranked responsive visualization is automatically selected and applied.

Recommender for responsive visualization transformations

Systems and methods for dynamic user profile management are provided. One aspect of the systems and methods includes receiving, by a lookup component, a request for a user profile; computing, by a profile component, a time-to-live (TTL) refresh value for the user profile based on a lookup history of the user profile; updating, by the profile component, a TTL value of the user profile based on the request and the TTL refresh value; storing, by the profile component, the user profile and the updated TTL value in the edge database; and removing, by the edge database, the user profile from the edge database based on the updated TTL value.

Dynamic user profile management

Embodiments provide systems, methods, and computer storage media for management, assessment, navigation, and/or discovery of data based on data quality, consumption, and/or utility metrics. Data may be assessed using attribute-level and/or record-level metrics that quantify data: 'quality'—the condition of data (e.g., presence of incorrect or incomplete values), its “consumption”—the tracked usage of data in downstream applications (e.g., utilization of attributes in dashboard widgets or customer segmentation rules), and/or its “utility”—a quantifiable impact resulting from the consumption of data (e.g., revenue or number of visits resulting from marketing campaigns that use particular datasets, storage costs of data). This data assessment may be performed at different stages of a data intake, preparation, and/or modeling lifecycle. For example, an interactive tree view may visually represent a nested attribute schema and attribute quality or consumption metrics to facilitate discovery of bad data before ingesting into a data lake.

Interactive tree representing attribute quality or consumption metrics for data ingestion and other applications

Embodiments provide systems, methods, and computer storage media for a Nonsymmetric Determinantal Point Process (NDPPs) for compatible set recommendations in a setting where data representing entities (e.g., items) arrives in a stream. A stream representing compatible sets of entities is received and used to update a latent representation of the entities and a compatibility distribution indicating likelihood of compatibility of subsets of the entities. The probability distribution is accessed in a single sequential pass to predict a compatible complete set of entities that completes an incomplete set of entities. The predicted complete compatible set is provided a recommendation for entities that complete the incomplete set of entities.

Online inference and learning for nonsymmetric determinantal point processes

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

Embodiments described herein provide methods and systems for facilitating actively-learned context modeling. In one embodiment, a subset of data is selected from a training dataset corresponding with an image to be compressed, the subset of data corresponding with a subset of data of pixels of the image. A context model is generated using the selected subset of data. The context model is generally in the form of a decision tree having a set of leaf nodes. Entropy values corresponding with each leaf node of the set of leaf nodes are determined. Each entropy value indicates an extent of diversity of context associated with the corresponding leaf node. Additional data from the training dataset is selected based on the entropy values corresponding with the leaf nodes. The updated subset of data is used to generate an updated context model for use in performing compression of the image.

Actively-learned context modeling for image compression

Systems and methods for data analysis are described. Embodiments of the present disclosure data analysis include displaying, via a data analysis interface, a data visualization in a first region of the data analysis interface; and displaying, via the data analysis interface, an analysis thread visualization in a second region of the data analysis interface. The analysis thread visualization depicts an analysis thread graph including a first node corresponding to the data visualization and an edge corresponding to an analysis path between the first node and a second node.

Generating data insights

Methods, computer systems, computer-storage media, and graphical user interfaces are provided for facilitating generation and presentation of insights. In one implementation, a set of data is used to generate a data visualization. A candidate insight associated with the data visualization is generated, the candidate insight being generated in text form based on a text template and comprising a descriptive insight, a predictive insight, an investigative, or a prescriptive insight. A set of natural language insights is generated, via a machine learning model. The natural language insights represent the candidate insight in a text style that is different from the text template. A natural language insight having the text style corresponding with a desired text style is selected for presenting the candidate insight and, thereafter, the selected natural language insight and data visualization are providing for display via a graphical user interface.

Facilitating generation and presentation of advanced insights

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

Growing community of inventors

San Jose, CA, United States of America

Ryan A Rossi