grakel.MultiscaleLaplacian

class grakel.MultiscaleLaplacian(n_jobs=None, normalize=False, verbose=False, random_state=None, L=3, P=10, gamma=0.01, heta=0.01, n_samples=50)

Laplacian Graph Kernel as proposed in [KP16].

Parameters:

random_stateRandomState or int, default=None

A random number generator instance or an int to initialize a RandomState as a seed.

Lint, default=3

The number of neighborhoods.

gammaReal, default=0.01

A smoothing parameter of float value.

hetafloat, default=0.01

A smoothing parameter of float value.

Pint, default=10

Restrict the maximum number of eigenvalues, taken on eigenvalue decomposition.

n_samplesint, default=50

The number of vertex samples.

Attributes:

random_state_RandomState

A RandomState object handling all randomness of the class.

_data_leveldict

A dictionary containing the feature basis information needed for each level calculation on transform.

Methods

diagonal()	Calculate the kernel matrix diagonal of the fit/transformed data.
fit(X[, y])	Fit a dataset, for a transformer.
fit_transform(X[, y])	Fit and transform, on the same dataset.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
initialize()	Initialize all transformer arguments, needing initialization.
pairwise_operation(x, y)	FLG calculation for the fast multiscale laplacian.
parse_input(X)	Fast ML Graph Kernel.
set_output(*[, transform])	Set output container.
set_params(**params)	Call the parent method.
transform(X)	Calculate the kernel matrix, between given and fitted dataset.

Initialise a multiscale_laplacian kernel.

Attributes:

X

Methods

diagonal()	Calculate the kernel matrix diagonal of the fit/transformed data.
fit(X[, y])	Fit a dataset, for a transformer.
fit_transform(X[, y])	Fit and transform, on the same dataset.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
initialize()	Initialize all transformer arguments, needing initialization.
pairwise_operation(x, y)	FLG calculation for the fast multiscale laplacian.
parse_input(X)	Fast ML Graph Kernel.
set_output(*[, transform])	Set output container.
set_params(**params)	Call the parent method.
transform(X)	Calculate the kernel matrix, between given and fitted dataset.

__init__(n_jobs=None, normalize=False, verbose=False, random_state=None, L=3, P=10, gamma=0.01, heta=0.01, n_samples=50)

Initialise a multiscale_laplacian kernel.

Bibliography

[KP16]

Risi Kondor and Horace Pan. The Multiscale Laplacian Graph Kernel. In Advances in Neural Information Processing Systems, 2990–2998. 2016.