公开(公告)号：US20240273296A1

公开(公告)日：2024-08-15

申请号：US18625884

申请日：2024-04-03

Applicant: Adobe Inc.

Inventor： Sungchul KIM ,  Subrata MITRA ,  Ruiyi Zhang ,  Rui Wang ,  Handong ZHAO ,  Tong YU

IPC: G06F40/295 ,  G06N20/00

CPC classification number: G06F40/295 ,  G06N20/00

Abstract: 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.

公开(公告)号：US20230169140A1

公开(公告)日：2023-06-01

申请号：US18061697

申请日：2022-12-05

Applicant: Adobe Inc.

Inventor： John Boaz Tsang LEE ,  Ryan ROSSI ,  Sungchul KIM ,  Eunyee KOH ,  Anup RAO

IPC: G06F17/10 ,  G06F16/901 ,  G06N3/08 ,  G06F17/16 ,  G06V10/426 ,  G06F18/21 ,  G06F18/24 ,  G06N3/047 ,  G06V10/82

CPC classification number: G06F17/10 ,  G06F16/9024 ,  G06N3/08 ,  G06F17/16 ,  G06V10/426 ,  G06F18/21 ,  G06F18/24 ,  G06N3/047 ,  G06V10/82

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：US20190155863A1

公开(公告)日：2019-05-23

申请号：US16254125

申请日：2019-01-22

Applicant: ADOBE INC.

Inventor： Sungchul KIM ,  Nedim LIPKA ,  Eunyee KOH

IPC: G06F16/9535 ,  G06F16/335

Abstract: A method for clustering geolocations using geo-point density includes receiving a user log of geolocation data extracted from user interactions with at least one electronic device. A density is determined relative to other geo-points for each geo-point in a set of geo-points extracted from the user log. Lower density geo-points in the set are merged into higher density geo-points in the set to result in a merged set of geo-points, and clusters of geo-points are identified from the merged set. Merging the geo-points tends to preserve frequently occurring geo-points while reducing those that constitute noise, which improves the reliability of identifying the clusters. Core geo-points of the user log are selected from the clusters. The core geo-points of the user log can be compared to core geo-points of other use logs to identify associations between the user logs.

公开(公告)号：US20250037006A1

公开(公告)日：2025-01-30

申请号：US18225970

申请日：2023-07-25

Applicant: ADOBE INC.

Inventor： Kanak MAHADIK ,  Sungchul KIM ,  Ryan ROSSI ,  Handong ZHAO ,  Shravika MITTAL

IPC: G06N20/00

Abstract: In various examples, a ranking is generated for a set of computing instances based on predicted metrics associated with computing instances. For example, a prediction model estimates various system performance metrics based on information associated with a workload and configuration information associated with computing instances. The system performance metrics estimated by the prediction model are used to rank the set of computing instances.

公开(公告)号：US20220414468A1

公开(公告)日：2022-12-29

申请号：US17823390

申请日：2022-08-30

Applicant: Adobe Inc.

Inventor： Fan DU ,  Sungchul KIM ,  Shunan GUO ,  Sana LEE ,  Eunyee KOH

IPC: G06N3/08 ,  G06N7/00 ,  G06N20/10 ,  G06N5/02 ,  G06N3/04

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.