A method for processing data includes receiving an adjustment request for adjusting a number of consumer instances from a first number to a second number, and determining a migration overhead for adjusting a first distribution of states associated with the first number of consumer instances to a second distribution of the states associated with the second number of consumer instances, wherein the states are intermediate results of processing the data and the migration overhead includes a latency and a bandwidth shortage incurred for migrating the states. Based on the determined migration overhead, the states are migrated between the first number of consumer instances and the second number of consumer instances, and thereafter the data is processed based on the second distribution of the states at the second number of consumer instances.

The description relates the feature matching. Our approach establishes pointwise correspondences between challenging image pairs. It takes off-the-shelf local features as input and uses an attentional graph neural network to solve an assignment optimization problem. The deep middle-end matcher acts as a middle-end and handles partial point visibility and occlusion elegantly, producing a partial assignment matrix.

A processor-implemented method includes acquiring, by a processor, a first undirected graph and a second undirected graph, generating, by the processor, a first lattice for the first undirected graph and a second lattice for the second undirected graph; matching, by the processor, the first lattice and the second lattice based on a first global structure of the first lattice and a second global structure of the second lattice, the first global structure corresponding to nodes of the first undirected graph and the second global structure corresponding to nodes of the second undirected graph, and processing the first undirected graph and the second undirected graph based on a result of the matching of the first lattice and the second lattice.

A method for employing a differentiable ranking based graph sparsification (DRGS) network to use supervision signals from downstream tasks to guide graph sparsification is presented. The method includes, in a training phase, generating node representations by neighborhood aggregation operators, generating sparsified subgraphs by top-k neighbor sampling from a learned neighborhood ranking distribution, feeding the sparsified subgraphs to a task, generating a prediction, and collecting a prediction error to update parameters in the generating and feeding steps to minimize an error, and, in a testing phase, generating node representations by neighborhood aggregation operators related to testing data, generating sparsified subgraphs by top-k neighbor sampling from a learned neighborhood ranking distribution related to the testing data, feeding the sparsified subgraphs related to the testing data to a task, and outputting prediction results to a visualization device.

Embodiments are disclosed for generating tables from charts. The techniques include determining a chart type of a selected chart. The techniques include determining a plurality of chart elements of the selected chart. Further, the techniques include determining a plurality of measurements of a plurality of data representations of the selected chart. Additionally, the techniques include determining a plurality of corresponding numeric values for the measurements based on the chart elements. Also, the techniques include generating a data table comprising the chart elements and the corresponding numeric values.

Various embodiments are generally directed to systems for summarizing data visualizations (i.e., images of data visualizations), such as a graph image, for instance. Some embodiments are particularly directed to a personalized graph summarizer that analyzes a data visualization, or image, to detect pre-defined patterns within the data visualization, and produces a textual summary of the data visualization based on the pre-defined patterns detected within the data visualization. In various embodiments, the personalized graph summarizer may include features to adapt to the preferences of a user for generating an automated, personalized computer-generated narrative. For instance, additional pre-defined patterns may be created for detection and/or the textual summary may be tailored based on user preferences. In some such instances, one or more of the user preferences may be automatically determined by the personalized graph summarizer without requiring the user to explicitly indicate them. Embodiments may integrate machine learning and computer vision concepts.

Various embodiments of the disclosure relate to systems and methods for aligning a sequence read to a graph reference. In one embodiment, the method comprises selecting a first node from a graph reference, the graph reference comprising a plurality of nodes connected by a plurality of directed edges, at least one node of the plurality of nodes having a nucleotide sequence. The method further comprises traversing the graph reference according to a depth-first search, and comparing a sequence read to nucleotide sequences generated from the traversal of the graph reference. The traversal of the graph is then modified in response to a determination that each and every node associated with a given nucleotide sequence was previously evaluated.

A character recognition method, a character recognition apparatus, an electronic device and a computer readable storage medium are disclosed. The character recognition method includes: determining semantic information and first position information of each individual character recognized from an image; constructing a graph network according to the semantic information and the first position information of each individual character; and determining a character recognition result of the image according to a feature of each individual character calculated by the graph network.

An object of the invention is to efficiently create a 3D model of a plant with attributes from a 3D model of a plant with no attributes. In order to solve the above problems, in the invention, a connection information conversion part 5 converts a connection relationship of parts extracted from a 3D model with no attributes 2 into connection information of a system diagram, an extraction information comparing part 6 compares the connection information with the connection relationship extracted from an attribute system diagram to create an conversion correspondence DB 7, and a 3D model with attributes 9 is created based on the conversion correspondence DB from the 3D model with no attributes 2.

A method is provided for determining graph isomorphism. The method includes initializing a hash value for each of a plurality of vertexes in a first labelled graph and a second labelled graph by assigning an integer value as the hash value, to form a first set of hash values for the vertexes in the first graph and a second set of hash values for the vertexes in the second graph. The integer value for a given vertex is assigned based on a label of the given vertex in the graphs. The method includes performing a determination of whether the first and second labelled graphs are isomorphic, by comparing the first and second sets of hash values. The method includes initiating a performance of an action that changes a state of a controlled object to another state, responsive to the determination. Each graph includes a mixture of hard and soft labels.