graphqembed

graphqembed copied to clipboard

According to my understanding of the GQE model, the relation matrix in the project function of BilinearMetapathDecoder should be transposed before performing the matrix multiplication: https://github.com/williamleif/graphqembed/blob/2775a242cf8a5df520530f2dd08aa8790f109ebf/netquery/decoders.py#L149-L150 But after I change...

cynricfu

Possible evaluation issue

1

According to the paper, queries for the training set are sampled by removing edges from the graph. In `parallel_sample()` if `test` is True, the test edges are loaded: https://github.com/williamleif/graphqembed/blob/2775a242cf8a5df520530f2dd08aa8790f109ebf/netquery/data_utils.py#L77-L86 `test`...

dfdazac

this should fix https://github.com/williamleif/graphqembed/issues/2

pminervini

Updates made to make sure the bio train works with Python3.

nsheils

nsheils

updates for Python 3

1

In order to make this work for python 3, instances of "import cPickle as pickle" need to be changed to "import pickle" Additionally, in data_utils.py the load_graph function must be...

nsheils

Line 2 of train_helpers.py should be "from netquery.utils " rather than "from utils"

nsheils

The correct one is `python -m netquery.bio.train`.

plieblang

The `requirements.txt` file has the line `torch>=3.0` when in fact Pytorch does not have a version >= 3.0. Should it perhaps be `torch>=0.3.0`?

plieblang

Bumps [scikit-learn](https://github.com/scikit-learn/scikit-learn) from 0.18.2 to 1.5.0. Release notes Sourced from scikit-learn's releases. Scikit-learn 1.5.0 We're happy to announce the 1.5.0 release. You can read the release highlights under https://scikit-learn.org/stable/auto_examples/release_highlights/plot_release_highlights_1_5_0.html and...

dependabot[bot]