Techniques to embed a data object into a multidimensional frame
Various embodiments are generally directed to techniques for embedding a data object into a multidimensional frame, such as for training an autoencoder to generate latent space representations of the data object based on the multidimensional frame, for instance. Additionally, in one or more embodiments latent space representations of data objects may be classified, such as with a machine learning algorithm. Some embodiments are particularly directed to embedding a data object comprising a plurality of object entries into a three-dimensional (3D) frame.
1 . An apparatus, comprising:
a processor; and
memory comprising instructions that, when executed by the processor, cause the processor to:
access a data object comprising a set of object entries, wherein each object entry in the set of object entries comprises a row value, a column value, and at least one cell contents entry, wherein the object entry corresponds to a data table entry, and wherein the row value and the column value indicate a location of the data table entry in a data table;
generate a multidimensional frame based on the data object, the multidimensional frame comprising a row dimension, a column dimension, and a content dimension, wherein at least one row value is mapped onto the row dimension, at least one column value is mapped onto the column dimension, and the at least one cell contents entry is mapped along the contents dimension to generate the multidimensional frame; and
utilize a trained encoder to embed the multidimensional frame into a latent space representation of the multidimensional frame.
2 . The apparatus of claim 1 , the instructions, when executed by the processor, to cause the processor to provide the latent space representation to a classifier to compute a correlation score for the latent space representation.
3 . The apparatus of claim 2 , the correlation score configured to indicate a correlation of the latent space representation to one or more latent space representations in a latent space representation library.
4 . The apparatus of claim 3 , the one or more latent space representations in the latent space representation library corresponding to one or more training frames used to train the trained encoder.
5 . The apparatus of claim 2 , the instructions, when executed by the processor, to cause the processor to compute, via the classifier, a set of correlation scores for the latent space representation, wherein each correlation score in the set of correlation scores corresponds to a different latent space representation of a different multidimensional frame generated based on a different data object.
6 . The apparatus of claim 5 , the instructions, when executed by the processor, to cause the processor to compare the set of correlation scores to a correlation threshold to identify a set of correlated latent space representations, identify a set of correlated data objects based on the set of correlated latent space representations, and provide the set of correlated data objects as output.
7 . A method comprising:
accessing a data object comprising a set of object entries, wherein each object entry in the set of object entries comprises a row value, a column value, and at least one cell contents entry wherein the object entry corresponds to a data table entry, and wherein the row value and the column value indicate a location of the data table entry in a data table;
generating a multidimensional frame based on the data object, the multidimensional frame comprising a row dimension, a column dimension, and a content dimension, wherein at least one row value is mapped onto the row dimension, at least one column value is mapped onto the column dimension, and the at least one cell contents entry is mapped along the contents dimension to generate the multidimensional frame; and
utilizing a trained encoder to embed the multidimensional frame into a latent space representation of the multidimensional frame.
8 . The method of claim 7 , including providing the latent space representation to a classifier to compute a correlation score for the latent space representation.
9 . The method of claim 8 , wherein the correlation score is configured to indicate a correlation of the latent space representation to one or more latent space representations in a latent space representation library.
10 . The method of claim 9 , the one or more latent space representations in the latent space representation library corresponding to one or more training frames used to train the trained encoder.
11 . The method of claim 8 , further comprising computing, via the classifier, a set of correlation scores for the latent space representation, wherein each correlation score in the set of correlation scores corresponds to a different latent space representation of a different multidimensional frame generated based on a different data object.
12 . The method of claim 11 , further comprising comparing the set of correlation scores to a correlation threshold to identify a set of correlated latent space representations, identify a set of correlated data objects based on the set of correlated latent space representations, and provide the set of correlated data objects as output.
13 . The method of claim 7 , wherein the trained encoder comprises a neural network trained on a set of training multidimensional frames.
14 . A non-transitory computer-readable storage medium having executable instructions stored thereon, which when executed by a processing circuit, cause the processing circuit to:
access a data object comprising a set of object entries, wherein each object entry in the set of object entries comprises a row value, a column value, and at least one cell contents entry wherein the object entry corresponds to a data table entry, and wherein the row value and the column value indicate a location of the data table entry in a data table;
generate a multidimensional frame based on the data object, the multidimensional frame comprising a row dimension, a column dimension, and a content dimension, wherein at least one row value is mapped onto the row dimension, at least one column value is mapped onto the column dimension, and the at least one cell contents entry is mapped along the contents dimension to generate the multidimensional frame; and
utilize a trained encoder to embed the multidimensional frame into a latent space representation of the multidimensional frame.
15 . The non-transitory computer-readable storage medium of claim 14 , the instructions, when executed by the processing circuit, cause the processing circuit to provide the latent space representation to a classifier to compute a correlation score for the latent space representation.
16 . The non-transitory computer-readable storage medium of claim 15 , the correlation score configured to indicate a correlation of the latent space representation to one or more latent space representations in a latent space representation library.
17 . The non-transitory computer-readable storage medium of claim 16 , the one or more latent space representations in the latent space representation library corresponding to one or more training frames used to train the trained encoder.
18 . The non-transitory computer-readable storage medium of claim 15 , the instructions, when executed by the processing circuit, cause the processing circuit to compute, via the classifier, a set of correlation scores for the latent space representation, wherein each correlation score in the set of correlation scores corresponds to a different latent space representation of a different multidimensional frame generated based on a different data object.
19 . The non-transitory computer-readable storage medium of claim 18 , the instructions, when executed by the processing circuit, cause the processing circuit to compare the set of correlation scores to a correlation threshold to identify a set of correlated latent space representations, identify a set of correlated data objects based on the set of correlated latent space representations, and provide the set of correlated data objects as output.