Adobe, Inc.

Cisco Technology, Inc.

Anup Bandigadi Rao

Ryan A Rossi

Tung Mai

Eunyee Koh

Sungchul Kim

Georgios Theocharous

Matvey Kapilevich

Shivakumar Vaithyanathan

Fan Du

Charles Menguy

Shamim Sharifuddin Pirzada

Margarita Savova

Yeuk-Yin Chan

Viswanathan Swaminathan

Michael R Thomas

Saayan Mitra

Nedim Lipka

Michele Saad

Subrata Mitra

Somdeb Sarkhel

James Lewis Fenton

Moumita Sinha

Thomas Greger

Bailey G Szeto

Di Jin

Aldo Gael Carranza

Sanjay Pol

Ashok Ramaswami

John Boaz Tsang Lee

Kirankumar Shiragur

Antonio Cuevas

Kelly Quinn Nicholes

Nathan Ng

David R Oran

Russell Robert Stringham

Gang Wu

Ritwik Sinha

Iftikhar Ahamath Burhanuddin

Nikhil Sheoran

David Arbour

Yasin Abbasi Yadkori

Vibhor Porwal

Harleen S Sahni

Sapthotharan Krishnan Nair

Zhao Song

Vijeth Lomada

Sridhar Mahadevan

Lakshmi Shivalingaiah

Kenneth George Russell

Manas Garg

Thomas W Jacobs

Michael Allen Thomas

Alexandru Ionut Hodorogea

Karan Aggarwal

Anil Malkani

Sameeksha Arora

Sergey N Kazarin

Shaddy Garg

Gautam Pratap Kowshik

Himanshu Panday

Akash Vivek Maharaj

Vaishnavi Muppala

Ishita Dasgupta

Aleksander Pejcic

Alireza Farhadi

Ghetia Siddharth

Jatin Varshney

Vikas Maddukuri

Laxmikant Mishra

Yeshwanth Vijayakumar

Aravind Reddy Talla

Enayat Ullah

Jiong Zhu

Liron Goren Snai

Vidit Bhatia

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

Some aspects relate to technologies for an artificial intelligent (AI) system that, among other things, enhances responses to concepts questions for an application with contextual usage insights. In accordance with some aspects, a user query is determined to comprise a concepts question regarding an application. Responsive to determining the user query comprises the concepts question, documentation regarding the application relevant to the user query is identified. A generative model generates text for a response to the concepts question using the documentation regarding the application. Additionally, a determination is made to add contextual usage insights to the response. Responsive to determining to add contextual usage insights to the response, usage data relevant to the user query and/or the response is retrieved. The generative model generates text for a final response using the response and the usage data, and the final response is provided to a user device for presentation.

Enhancing artificial intelligence responses with contextual usage insights

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 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

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

Techniques are provided for training graph neural networks with heterophily datasets and generating predictions for such datasets with heterophily. A computing device receives a dataset including a graph data structure and processes the dataset using a graph neural network. The graph neural network defines prior belief vectors respectively corresponding to nodes of the graph data structure, executes a compatibility-guided propagation from the set of prior belief vectors and using a compatibility matrix. The graph neural network predicts predicting a class label for a node of the graph data structure based on the compatibility-guided propagations and a characteristic of at least one node within a neighborhood of the node. The computing device outputs the graph data structure where it is usable by a software tool for modifying an operation of a computing environment.

Graph neural networks for datasets with heterophily

To retrieve information derived from a plurality of separately stored datasets, join structures are identified within the plurality of separately stored datasets. Join structures can include datasets joined by a central dataset, datasets joined by a single key, and datasets joined across a plurality of keys. Each of the join structures corresponds to a query processing schema that defines a sampling technique. When a join query is received as a SQL query, the join query identifies a portion of the plurality of separately stored datasets, from which a join structure is selected and a corresponding query processing schema is identified. The join query is reconstructed to form a reconstructed join query that comprises query processing schema instructions to derive the requested information using the sampling technique defined by the identified query processing schema.

Approximate query processing for join queries

Systems and methods for dynamic user profile projection are provided. One or more aspects of the systems and methods includes computing, by a prediction component, a predicted number of lookups for a future time period based on a lookup history of a user profile using a lookup prediction model; comparing, by the prediction component, the predicted number of lookups to a lookup threshold; and transmitting, by a projection component, the user profile to an edge server based on the comparison.

Dynamic user profile projection

A single unified machine learning model (e.g., a neural network) is trained to perform both supervised event predictions and unsupervised time-varying clustering for a sequence of events (e.g., a sequence representing a user behavior) using sequences of events for multiple users using a combined loss function. The unified model can then be used for, given a sequence of events as input, predict a next event to occur after the last event in the sequence and generate a clustering result by performing a clustering operation on the sequence of events. As part of predicting the next event, the unified model is trained to predict an event type for the next event and a time of occurrence for the next event. In certain embodiments, the unified model is a neural network comprising a recurrent neural network (RNN) such as an Long Short Term Memory (LSTM) network.

Unified framework for dynamic clustering and discrete time event prediction

Techniques are provided for analyzing user actions that have occurred over a time period. The user actions can be, for example, with respect to the user's navigation of content or interaction with an application. Such user data is provided in an action string, which is converted into a highly searchable format. As such, the presence and frequency of particular user actions and patterns of user actions within an action string of a particular user, as well as among multiple action strings of multiple users, are determinable. Subsequences of one or more action strings are identified and both the number of action strings that include a particular subsequence and the frequency that a particular subsequence is present in a given action string are determinable. The conversion involves breaking that string into a sorted list of locations for the actions within that string. Queries can be readily applied against the sorted list.

Determining patterns within a string sequence of user actions

Multi-modal machine-learning model training techniques for search are described that overcome conventional challenges and inefficiencies to support real time output, which is not possible in conventional training techniques. In one example, a search system is configured to support multi-modal machine-learning model training. This includes use of a preview mode and an expanded mode. In the preview mode, a preview segment is generated as part of real time training of a machine learning model. In the expanded mode, the preview segment is persisted as an expanded segment that is used to train and utilize an expanded machine-learning model as part of search.

Multi-modal machine-learning model training for search

A cluster generation system identifies data elements, from a first binary record, that each have a particular value and correspond to respective binary traits. A candidate description function describing the binary traits is generated, the candidate description function including a model factor that describes the data elements. Responsive to determining that a second record has additional data elements having the particular value and corresponding to the respective binary traits, the candidate description function is modified to indicate that the model factor describes the additional elements. The candidate description function is also modified to include a correction factor describing an additional binary trait excluded from the respective binary traits. Based on the modified candidate description function, the cluster generation system generates a data summary cluster, which includes a compact representation of the binary traits of the data elements and additional data elements.

Trait expansion techniques in binary matrix datasets

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

In implementations of item transfer control systems, a computing device implements a transfer system to receive input data describing types of requested items and corresponding quantities of the types of requested items to receive at each of a plurality of destination sites and types of available items and corresponding quantities of the types of available items that are available at each of a plurality of source sites. The transfer system constructs a flow network having a source node for each of the plurality of the source sites and a destination node for each of the plurality of the destination sites. An integral approximate solution is generated that transfers the corresponding quantities of the types of requested items to each of the plurality of the destination sites using a maximum flow solver and the flow network. The transfer system causes transferences of the corresponding quantities of the types of requested items to each of the plurality of the destination sites based on the integral approximate solution.

Item transfer control systems

The present disclosure relates to systems, methods, and non-transitory computer-readable media that estimate the overlap between sets of data samples. In particular, in one or more embodiments, the disclosed systems utilize a sketch-based sampling routine and a flexible, accurate estimator to determine the overlap (e.g., the intersection) between sets of data samples. For example, in some implementations, the disclosed systems generate a sketch vector&#x2014;such as a one permutation hashing vector&#x2014;for each set of data samples. The disclosed systems further compare the sketch vectors to determine an equal bin similarity estimator, a lesser bin similarity estimator, and a greater bin similarity estimator. The disclosed systems utilize one or more of the determined similarity estimators in generating an overlap estimation for the sets of data samples.

Generating overlap estimations between high-volume digital data sets based on multiple sketch vector similarity estimators

Growing community of inventors

San Jose, CA, United States of America

Anup Bandigadi Rao