jajupmochi
|
ed78e65dd8
|
[Features] Add model seletion methods with validation set: KFoldWithValid, RepeatedKFoldWithValid, BaseCrossValidatorWithValid. Required version of scikit-learn is upgraded to 1.1.0, to support the input_name argument of sklearn.utils.check_array used in gklearn.model_selection._split.py.
|
3 years ago |
jajupmochi
|
b36eaae177
|
[Features] Add model seletion methods with validation set: KFoldWithValid, RepeatedKFoldWithValid, BaseCrossValidatorWithValid. Required version of scikit-learn is upgraded to 1.1.0, to support the input_name argument of sklearn.utils.check_array used in gklearn.model_selection._split.py.
|
3 years ago |
jajupmochi
|
5eb90655a4
|
[Features] Add model seletion methods with validation set: , , . Required version of scikit-learn is upgraded to 1.1.0, to support the argument of used in .
|
3 years ago |
jajupmochi
|
a76335ed16
|
[Features][API Changes] Update kernel classes.
|
3 years ago |
jajupmochi
|
5e37d4447f
|
[Major Features] Add GEDModel which is compatibale with .
|
3 years ago |
jajupmochi
|
a7e189134d
|
[Fix] Change the output directory name.
|
3 years ago |
jajupmochi
|
1946d46964
|
[Feature] Allow to permutate nodes in graphs when using bipartite to estimate GED. This feature is implementated in the method in Python, which invokes GEDLIB in C++ by Cython.
|
3 years ago |
jajupmochi
|
42acfd0236
|
[Fix] Fix laplacian_kernel and cosine_kernel between pairs of numpy vectors.
|
3 years ago |
jajupmochi
|
dd58f602ec
|
[Feature] Add kronecker_delta_kernel function between a pair of numpy vectors.
|
3 years ago |
jajupmochi
|
7d3e929b36
|
[Feature] Add several new kernels between vectors.
|
3 years ago |
jajupmochi
|
310b01c347
|
[Major Feature] WLSubtree kernel can now deal with symbolic edge labels (for Gram matrix computation without parallelization). Meanwhile, the dummy labels are no longer added a priori.
|
4 years ago |
jajupmochi
|
bd8bf2b234
|
[Enhancement] Add more verbose for the WL kernel.
|
4 years ago |
jajupmochi
|
609c8c1518
|
[Enhancement] Allow deciding whether or not to make a copy of input graphs in GraphKernel class.
|
4 years ago |
jajupmochi
|
785a5c1926
|
[To finish] Remove dummy labels in treelet kernel (for the contest.)
|
4 years ago |
jajupmochi
|
231c050f88
|
[To finish] Remove dummy labels in treelet kernel (for the contest.)
|
4 years ago |
jajupmochi
|
23a938482a
|
[[Enhancement] gklearn.utils.normalize_gram_matrix function now raises…
|
4 years ago |
jajupmochi
|
4fd314d374
|
[Fix] Fixed the bug that gklearn.utils.kernels.gaussiankernel can not handle lists as inputs.
|
4 years ago |
jajupmochi
|
1800923c45
|
[API change] gklearn.utils.kernels.gaussiankernel function no longer transforms inputs to numpy.array of float values. This may be faster, but may cause some errors to the previous codes.
|
4 years ago |
jajupmochi
|
70a11dfd1b
|
[Enhancement] gklearn.utils.normalize_gram_matrix function now raises an excepetion if the diagonal includes negative values.\n[Enhancement] gklearn.utils.get_graph_kernel_by_name function now accepts strings of kernel names the same as the keys of gklearn.kernels.GRAPH_KERNELS and supports more graph kernels.
|
4 years ago |
jajupmochi
|
b843707e9c
|
[Enhancement] gklearn.dataset.Dataset class can now automatically get the task type of the given dataset (regression or classification).
|
4 years ago |
jajupmochi
|
325f51cb6f
|
[Feature] Add the gklearn.model_learning.dichotomous_permutation function.
|
4 years ago |
jajupmochi
|
ed17010535
|
[Major Feature][Todo] Add model_learning module, including a new NestedCV class and a Workflow class for graph kernel computation.
|
4 years ago |
jajupmochi
|
bb36d0f507
|
[Major Feature] Graph kernel classes now can compute kernel matrix between two different list of graphs using fit/transform methods which uses the same scheme as the scikit-learn library!
|
4 years ago |
jajupmochi
|
d08eddc69c
|
[Enhancement] The global variable now uses kernel classes as values.
|
4 years ago |
jajupmochi
|
679953200c
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
81a881bd79
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
14bd9db5a7
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
29bcfe4dab
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
13c0fb37c1
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
6e898240e3
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
27de2454a9
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
25e10c8d49
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
cba8047279
|
[Exp] Update computation of ged stability.
|
4 years ago |
jajupmochi
|
59687d1e87
|
[Exp] Add taskhub to run exps all in once.
|
4 years ago |
jajupmochi
|
74bab60deb
|
[Exp] Add taskhub to run exps all in once.
|
4 years ago |
jajupmochi
|
13ac6d9153
|
[Exp] Add taskhub to run exps all in once.
|
4 years ago |
jajupmochi
|
756371aaf1
|
[Exp] Add taskhub to run exps all in once.
|
4 years ago |
jajupmochi
|
ac78c8517a
|
[Exp] Add taskhub to run exps all in once.
|
4 years ago |
jajupmochi
|
07478a5717
|
[Exp] Add taskhub to run exps all in once.
|
4 years ago |
jajupmochi
|
e991f59742
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
71df9f591f
|
[Update] Move the import of control out of the __init__().
|
4 years ago |
jajupmochi
|
47951de049
|
[Update] Move the import of control into the __init__().
|
4 years ago |
jajupmochi
|
684d26bf7e
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
bfe64a1f66
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
6332e5684d
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
4bfde8d881
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
59a36aa0a0
|
[Exp] Update exceptions in fcsp exps.
|
4 years ago |
jajupmochi
|
a638bfa45a
|
[Exp] FCSP: 1. Use no more than 10 tlong tasks. 2. use ljia instead of explicit name. 3. My first SCI journal paper is accepted!
|
4 years ago |
jajupmochi
|
8c6168b8f8
|
[Exp] Update special tasks.
|
4 years ago |
jajupmochi
|
e5b977734c
|
[Fix bugs] length in get_iters in compute_geds().
|
4 years ago |