公开(公告)号：US20220100714A1

公开(公告)日：2022-03-31

申请号：US17036453

申请日：2020-09-29

Applicant: ADOBE INC.

Inventor： Handong Zhao ,  Yikun Xian ,  Sungchul Kim ,  Tak Yeon Lee ,  Nikhil Belsare ,  Shashi Kant Rai ,  Vasanthi Holtcamp ,  Thomas Jacobs ,  Duy-Trung T. Dinh ,  Caroline Jiwon Kim

IPC: G06F16/21 ,  G06K9/62 ,  G06N3/08 ,  G06K9/72

Abstract: 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.

公开(公告)号：US20210264244A1

公开(公告)日：2021-08-26

申请号：US16796681

申请日：2020-02-20

Applicant: Adobe Inc.

Inventor： Yikun Xian ,  Tak Yeon Lee ,  Sungchul Kim ,  Ryan Rossi ,  Handong Zhao

IPC: G06N3/08 ,  G06F16/22 ,  G06F16/901 ,  G06F16/248 ,  G06F16/2457 ,  G06N5/02

Abstract: 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.

公开(公告)号：US20200342305A1

公开(公告)日：2020-10-29

申请号：US16394227

申请日：2019-04-25

Applicant: Adobe Inc.

Inventor： Fan Du ,  Eunyee Koh ,  Sungchul Kim ,  Shunan Guo ,  Sana Malik Lee

IPC: G06N3/08 ,  G06N5/02 ,  G06N20/10 ,  G06N7/00

Abstract: 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.

公开(公告)号：US20200285944A1

公开(公告)日：2020-09-10

申请号：US16297024

申请日：2019-03-08

Applicant: Adobe Inc.

Inventor： John Boaz Tsang Lee ,  Ryan Rossi ,  Sungchul Kim ,  Eunyee Koh ,  Anup Rao

IPC: G06N3/04 ,  G06F16/901 ,  G06N3/08 ,  G06F17/16 ,  G06K9/46 ,  G06K9/62

Abstract: 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.

公开(公告)号：US20200233864A1

公开(公告)日：2020-07-23

申请号：US16252169

申请日：2019-01-18

Applicant: ADOBE INC.

Inventor： Di Jin ,  Ryan A. Rossi ,  Eunyee Koh ,  Sungchul Kim ,  Anup Rao

IPC: G06F16/2458 ,  G06F16/901 ,  G06F16/28 ,  G06F16/26 ,  G06F16/215

Abstract: 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.

公开(公告)号：US20200177466A1

公开(公告)日：2020-06-04

申请号：US16204616

申请日：2018-11-29

Applicant: Adobe Inc.

Inventor： Ryan A. Rossi ,  Eunyee Koh ,  Sungchul Kim ,  Anup Bandigadi Rao

IPC: H04L12/24 ,  G06F16/901 ,  G06N20/00

Abstract: In implementations of higher-order network embedding, a computing device maintains interconnected data in the form of a graph that represents a network, the graph including nodes that each represent entities in the network and node associations that each represent edges between the nodes in the graph. The computing device includes a network embedding module that is implemented to determine a frequency of k-vertex motifs for each of the edges in the graph, and derive motif-based matrices from the frequency of each of the k-vertex motifs in the graph. The network embedding module is also implemented to determine a higher-order network embedding for each of the nodes in the graph from each of the motif-based matrices. The network embedding module can then concatenate the higher-order network embeddings into a matrix representation.

公开(公告)号：US20250061609A1

公开(公告)日：2025-02-20

申请号：US18451201

申请日：2023-08-17

Applicant: ADOBE INC.

Inventor： Junda Wu ,  Haoliang Wang ,  Tong Yu ,  Stefano Petrangeli ,  Gang Wu ,  Viswanathan Swaminathan ,  Sungchul Kim ,  Handong Zhao

IPC: G06T9/40 ,  G06V10/70 ,  G06V10/75

Abstract: One or more aspects of the method, apparatus, and non-transitory computer readable medium include obtaining image data and computing a prediction residue value for a pixel of the image data using a prediction function. An entropy value for the pixel can then be determined based on the prediction residue value using context modeling, and progressive compressed image data for the image data can be generated based on the entropy value. The compressed image data can be used to enable collaborative image editing and other image processing tasks.

公开(公告)号：US20240404243A1

公开(公告)日：2024-12-05

申请号：US18328950

申请日：2023-06-05

Applicant: ADOBE INC.

Inventor： Handong Zhao ,  Yue Bai ,  Zhe Lin ,  Ajinkya Gorakhnath Kale ,  Jiuxiang Gu ,  Tong Yu ,  Sungchul Kim

IPC: G06V10/75 ,  G06F16/332 ,  G06V10/774

Abstract: Systems and methods for multimodal machine learning are provided. According to one aspect, a method for multimodal machine learning includes obtaining a prompt; encoding the prompt using a multimodal encoder to obtain a prompt embedding, wherein the encoding comprises generating a plurality of multi-head attention (MHA) outputs corresponding to a plurality of different scales, respectively, and combining the plurality of MHA outputs using a multi-scale aggregator; and generating a response to the prompt based on the prompt embedding.

公开(公告)号：US20240311623A1

公开(公告)日：2024-09-19

申请号：US18183387

申请日：2023-03-14

Applicant: Adobe Inc.

Inventor： Ryan Rossi ,  Eunyee Koh ,  Jane Hoffswell ,  Nedim Lipka ,  Shunan Guo ,  Sudhanshu Chanpuriya ,  Sungchul Kim ,  Tong Yu

IPC: G06N3/049

CPC classification number: G06N3/049

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for building time-decayed line graphs from temporal graph networks for efficiently and accurately generating time-aware recommendations. For example, the time-decayed line graph system creates a line graph of the temporal graph network by deriving interaction nodes from temporal edges (e.g., timed interactions) and connecting interactions that share an endpoint node. Then, the time-decayed line graph system determines the edge weights in the line graph based on differences in time between interactions, with interactions that occur closer together in time being connected with higher weights. Notably, by using this method, the derived time-decayed line graph directly represents topological proximity and temporal proximity. Upon generating the time-decayed line graphs, the system performs downstream predictive modeling such as predicted edge classifications and/or temporal link predictions.

公开(公告)号：US12093322B2

公开(公告)日：2024-09-17

申请号：US17654933

申请日：2022-03-15

Applicant: Adobe Inc.

Inventor： Fayokemi Ojo ,  Ryan Rossi ,  Jane Hoffswell ,  Shunan Guo ,  Fan Du ,  Sungchul Kim ,  Chang Xiao ,  Eunyee Koh

IPC: G06F16/904 ,  G06N3/02

CPC classification number: G06F16/904 ,  G06N3/02

Abstract: 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.