cleora

cleora copied to clipboard

Calculating embeddings for new nodes after training

2

I am trying to run Cleora on a simple dataset. My TSV file is simple and follows the format of "leads attributes" l1 a1 l2 a1 l1 a2 l3 a2...

judas123

[paper] definition of M vs Fig. 2.

1

Hi! Apologies if this is not the best place to ask this but. I've been reading Your paper and I hope You could clarify this little thing which is confusing...

olszewskip

edges with weight

3

hi I am not able to find two things: 1. How to give data where edges are present with some weight?? So that edge weights are taken into embedding calculation....

saustar

directed graph

1

How can I force it to learn the embedding of a directed graph?

sademakn

graph partitioning

2

There's an option named 'num_partitions' in [pytorch-biggraph](https://github.com/facebookresearch/PyTorch-BigGraph) that can reduce the peak memory usage, Can Cleora provide that option too? is it possible in the future? my situation: 40M nodes...

sademakn

Initialize with node features

2

Is it possible to leverage the information of the node features, e.g. initialize the embeddings?

kmichael08

* Added an installation of requirements with pinned version * Got rid of warnings about deprecated `log_loss` and `np.int`

nemusa

stomfaig

Pyo3 python bindings, support for parquets output and s3 input/output

1

The implementation of: #69 issue. Pull requests which adds: 1) pyo3 integration 2) support for parquet output 3) support for s3 inputs/outputs

qooba

I'd like to add a few features. 1) Integration with pyo3 bindings which will enable to publish library as a python package and use without using subprocess 2) Support for...

qooba