-
31.发明授权公开(公告)号：US11475360B2
公开(公告)日：2022-10-18
申请号：US16593065
申请日：2019-10-04
发明人： Ryan A. Rossi , Rong Zhou
IPC分类号： G06N20/00 , G06K9/00 , G06N20/10 , G06K9/62 , G06V10/94 , G06V10/426 , G06N20/20 , G06N5/00 , G06N5/02
摘要： System and methods for relational time-series learning are provided. Unlike traditional time series forecasting techniques, which assume either complete time series independence or complete dependence, the disclosed system and method allow time series forecasting that can be performed on multivariate time series represented as vertices in graphs with arbitrary structures and predicting a future classification for data items represented by one of nodes in the graph. The system and methods also utilize non-relational, relational, temporal data for classification, and allow using fast and parallel classification techniques with linear speedups. The system and methods are well-suited for processing data in a streaming or online setting and naturally handle training data with skewed or unbalanced class labels.
-
公开(公告)号：US11030246B2
公开(公告)日：2021-06-08
申请号：US15179724
申请日：2016-06-10
发明人： Ryan A. Rossi , Rong Zhou
IPC分类号： G06F16/90 , G06F16/901 , G06N7/00 , G06N5/02
摘要： Embodiments of the present invention provide a system for fast, accurate, and scalable unbiased graphlet estimation. The system utilizes neighborhood sampling and combinatorial relations to estimate graphlet counts, statistics, and frequency distributions in a small fraction of the computing time of existing systems. The obtained unbiased estimates are highly accurate, and have applications in the analysis, mining, and predictive modeling of massive real-world networks. During operation, the system obtains data indicating vertices and edges of a graph. The system samples a portion of the graph and counts a number of graph features in the sampled portion of the graph. The system then computes an occurrence frequency of a graphlet pattern and a total number of graphlets associated with the graphlet pattern in the graph.
-
33.发明申请公开(公告)号：US20200034744A1
公开(公告)日：2020-01-30
申请号：US16593065
申请日：2019-10-04
发明人： Ryan A. Rossi , Rong Zhou
摘要： System and methods for relational time-series learning are provided. Unlike traditional time series forecasting techniques, which assume either complete time series independence or complete dependence, the disclosed system and method allow time series forecasting that can be performed on multivariate time series represented as vertices in graphs with arbitrary structures and predicting a future classification for data items represented by one of nodes in the graph. The system and methods also utilize non-relational, relational, temporal data for classification, and allow using fast and parallel classification techniques with linear speedups. The system and methods are well-suited for processing data in a streaming or online setting and naturally handle training data with skewed or unbalanced class labels.
-
公开(公告)号：US10482375B2
公开(公告)日：2019-11-19
申请号：US15802302
申请日：2017-11-02
发明人： Ryan Rossi , Rong Zhou
摘要： A method of deep graph representation learning includes: calculating a plurality of base features from a graph and adding the plurality of base features to a feature matrix. The method further includes generating, by a processing device, a current feature layer from the feature matrix and a set of relational feature operators, wherein the current feature layer corresponds to a set of current features, evaluating feature pairs associated with the current feature layer, and selecting a subset of features from the set of current features based on the evaluated feature pairs. The method further includes adding the subset of features to the feature matrix to generate an updated feature matrix.
-
公开(公告)号：US10387495B2
公开(公告)日：2019-08-20
申请号：US15179780
申请日：2016-06-10
发明人： Rong Zhou
IPC分类号： G06F16/903 , G06F16/901
摘要： Embodiments of the present invention provide a time- and space-efficient system for representing and searching a set of intervals to find all the intervals that overlap with a given query interval or point. A new structure called an interval hash table is introduced to significantly reduce the average search time, thereby improving computing and search technology. During operation, the system obtains data indicating a set of intervals to be hashed. The system divides a respective interval into a set of sub-intervals based on a locality-preserving hashing. The system then obtains a hash code associated with a respective sub-interval, and inserts the respective sub-interval into an interval hash table at a location corresponding to the hash code. The system may further search the interval hash table.
-
公开(公告)号：US10332229B2
公开(公告)日：2019-06-25
申请号：US14275347
申请日：2014-05-12
发明人： Rong Zhou
IPC分类号： G06F16/00 , G06T1/20 , G06F16/245 , G06F16/28
摘要： Provided is a high-performance implementation of the k-means clustering algorithm on a graphics processing unit (GPU), which leverages a set of GPU kernels with complimentary strengths for datasets of various dimensions and for different numbers of clusters. The concepts of non-dominated GPU kernels and efficient strategies to select high-throughput kernels that match the arguments of the clustering problem with the underlying GPU hardware for maximum speedup are provided.
-
37.发明授权公开(公告)号：US10235182B2
公开(公告)日：2019-03-19
申请号：US15628153
申请日：2017-06-20
发明人： Ryan A. Rossi , Rong Zhou
摘要： Embodiments described herein provide a system for facilitating hybrid task management across a central processing unit (CPU) and a graphics processing unit (GPU) of a computer. During operation, the system determines a set of tasks for performing data mining on a data set and storing the set of tasks in a data structure in an ascending order of uniformity associated with a respective task. The uniformity of a task indicates how uneven and skewed the task is compared to other tasks in the set of tasks. The system then allocates a subset of tasks to a core of the CPU from a front of the data structure and a subset of tasks to a core of the GPU from a back of the data structure.
-
公开(公告)号：US10217241B2
公开(公告)日：2019-02-26
申请号：US15183561
申请日：2016-06-15
发明人： Ryan A. Rossi , Rong Zhou
摘要： Embodiments of the present invention provide a system for fast parallel graph compression based on identifying a set of large cliques, which is used to encode the graph. The system provides both permanently-stored and in-memory graph encoding and reduces the space needed to represent and store a graph, the I/O traffic to use the graph, and the computation needed to perform algorithms involving the graph. The system thereby improves computing technology and graph computation. During operation, the system obtains data indicating vertices and edges of a graph. The system executes a clique-finding method to identify a maximum clique in the graph. The system then removes the clique from the graph, adds the clique to a set of found cliques, and generates a compressed representation of the graph based on the set of found cliques.
-
公开(公告)号：US10073815B2
公开(公告)日：2018-09-11
申请号：US15169422
申请日：2016-05-31
发明人： Rong Zhou
IPC分类号： G06F17/16
CPC分类号： G06F17/16
摘要： A method and system for performing general matrix-matrix multiplication (GEMM) operations on a graphics processor unit (GPU) using Smart kernels. During operation, the system may generate a set of kernels that includes at least one of a variable-dimension variable-K GEMM kernel, a variable-dimension constant-K GEMM kernel, or a combination thereof. A constant-K GEMM kernel performs computations for matrices with a specific value of K (e.g., the number of columns in a first matrix and the number of rows in a second matrix). Variable-dimension GEMM kernels allow for flexibility in the number of rows and columns used by a thread block to perform matrix multiplication for a sub-matrix. The system may generate rules to select the best (e.g., fastest) kernel for performing computations according to the particular parameter combination of the matrices being multiplied.
-
40.发明授权公开(公告)号：US09672557B2
公开(公告)日：2017-06-06
申请号：US14052584
申请日：2013-10-11
发明人： Rong Zhou , Daniel Davies
CPC分类号： G06Q30/0631 , G06Q30/0282
摘要： One embodiment of the present invention provides a system for dynamically assigning vertices to processors to generate a recommendation for a customer. During operation, the system receives graph data with customer and product vertices and purchase edges. The system traverses the graph from a customer vertex to a set of product vertices. The system divides the set of product vertices among a set of processors. Subsequently, the system determines a set of product frontier vertices for each processor. The system traverses the graph from the set of product frontier vertices to a set of customer vertices. The system divides the set of customer vertices among a set of processors. Then, the system determines a set of customer frontier vertices for each processor. The system traverses the graph from the set of customer frontier vertices to a set of recommendable product vertices. The system generates one or more product recommendations for the customer.
-
-
-
-
-
-
-
-
-
搜索结果
55 条记录 (耗时 0.061 秒)