-
公开(公告)号:US20200233864A1
公开(公告)日:2020-07-23
申请号:US16252169
申请日:2019-01-18
申请人: ADOBE INC.
发明人: Di Jin , Ryan A. Rossi , Eunyee Koh , Sungchul Kim , Anup Rao
IPC分类号: G06F16/2458 , G06F16/901 , G06F16/28 , G06F16/26 , G06F16/215
摘要: 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
申请人: Adobe Inc.
发明人: Ryan A. Rossi , Eunyee Koh , Sungchul Kim , Anup Bandigadi Rao
IPC分类号: H04L12/24 , G06F16/901 , G06N20/00
摘要: 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.
-
43.
公开(公告)号:US20240311623A1
公开(公告)日:2024-09-19
申请号:US18183387
申请日:2023-03-14
申请人: Adobe Inc.
发明人: Ryan Rossi , Eunyee Koh , Jane Hoffswell , Nedim Lipka , Shunan Guo , Sudhanshu Chanpuriya , Sungchul Kim , Tong Yu
IPC分类号: G06N3/049
CPC分类号: G06N3/049
摘要: 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.
-
44.
公开(公告)号:US12093322B2
公开(公告)日:2024-09-17
申请号:US17654933
申请日:2022-03-15
申请人: Adobe Inc.
发明人: Fayokemi Ojo , Ryan Rossi , Jane Hoffswell , Shunan Guo , Fan Du , Sungchul Kim , Chang Xiao , Eunyee Koh
IPC分类号: G06F16/904 , G06N3/02
CPC分类号: G06F16/904 , G06N3/02
摘要: 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.
-
公开(公告)号:US11995403B2
公开(公告)日:2024-05-28
申请号:US17524282
申请日:2021-11-11
申请人: ADOBE INC.
发明人: Sungchul Kim , Subrata Mitra , Ruiyi Zhang , Rui Wang , Handong Zhao , Tong Yu
IPC分类号: G06F40/295 , G06N20/00
CPC分类号: G06F40/295 , G06N20/00
摘要: 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:US11995048B2
公开(公告)日:2024-05-28
申请号:US17036453
申请日:2020-09-29
申请人: ADOBE INC.
发明人: 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分类号: G06F16/00 , G06F16/21 , G06F18/2115 , G06F18/214 , G06F18/2431 , G06N3/08 , G06V30/262
CPC分类号: G06F16/213 , G06F18/2115 , G06F18/2148 , G06F18/2431 , G06N3/08 , G06V30/274
摘要: 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:US20240160890A1
公开(公告)日:2024-05-16
申请号:US18052463
申请日:2022-11-03
申请人: ADOBE INC.
发明人: Namyong Park , Ryan A. Rossi , Eunyee Koh , Iftikhar Ahamath Burhanuddin , Sungchul Kim , Fan Du
摘要: Systems and methods for contrastive graphing are provided. One aspect of the systems and methods includes receiving a graph including a node; generating a node embedding for the node based on the graph using a graph neural network (GNN); computing a contrastive learning loss based on the node embedding; and updating parameters of the GNN based on the contrastive learning loss.
-
公开(公告)号:US20240152769A1
公开(公告)日:2024-05-09
申请号:US18050607
申请日:2022-10-28
申请人: ADOBE INC.
发明人: Ryan A. Rossi , Kanak Mahadik , Mustafa Abdallah ElHosiny Abdallah , Sungchul Kim , Handong Zhao
IPC分类号: G06N3/0985 , G06Q10/04
CPC分类号: G06N3/0985 , G06Q10/04
摘要: Systems and methods for automatic forecasting are described. Embodiments of the present disclosure receive a time-series dataset; compute a time-series meta-feature vector based on the time-series dataset; generate a performance score for a forecasting model using a meta-learner machine learning model that takes the time-series meta-feature vector as input; select the forecasting model from a plurality of forecasting models based on the performance score; and generate predicted time-series data based on the time-series dataset using the selected forecasting model.
-
公开(公告)号:US11782576B2
公开(公告)日:2023-10-10
申请号:US17161770
申请日:2021-01-29
申请人: Adobe Inc.
发明人: Camille Harris , Zening Qu , Sana Lee , Ryan Rossi , Fan Du , Eunyee Koh , Tak Yeon Lee , Sungchul Kim , Handong Zhao , Sumit Shekhar
IPC分类号: G06F3/0482 , G06F17/15 , G06F3/04845
CPC分类号: G06F3/0482 , G06F3/04845 , G06F17/15
摘要: 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.
-
50.
公开(公告)号:US20230244926A1
公开(公告)日:2023-08-03
申请号:US17592186
申请日:2022-02-03
申请人: ADOBE INC.
发明人: Sungchul Kim , Sejoon Oh , Ryan A. Rossi
IPC分类号: G06N3/08
CPC分类号: G06N3/08
摘要: A data augmentation framework enhances the prediction accuracy of tensor completion methods. An array having a set of cells associated with a set of entities is received. Influence metrics of cells from the array are determined based on an influence of the cells on minimizing loss while training a machine learning model. An entity-importance metric is generated for each entity of the set of entities based on the influence metrics. A cell from the array for which to augment the array with a predicted value is identified. The cell is identified based on a sampling of the set of entities that is weighted by the entity-importance metric for each entity of the set of entities.
-
-
-
-
-
-
-
-
-