deepwalk
deepwalk copied to clipboard
DeepWalk - Deep Learning for Graphs
When I set --max-memory-data-size 0, it throws following errors: Number of nodes: 6301 Number of walks: 63010 Data size (walks*length): 2520400 Data size 2520400 is larger than limit (max-memory-data-size: 0)....
Traceback (most recent call last): File "./deepwalk", line 11, in load_entry_point('deepwalk==1.0.3', 'console_scripts', 'deepwalk')() File "/usr/local/python36/lib/python3.6/site-packages/deepwalk-1.0.3-py3.6.egg/deepwalk/__main__.py", line 162, in main process(args) File "/usr/local/python36/lib/python3.6/site-packages/deepwalk-1.0.3-py3.6.egg/deepwalk/__main__.py", line 83, in process num_workers=args.workers) File "/usr/local/python36/lib/python3.6/site-packages/deepwalk-1.0.3-py3.6.egg/deepwalk/walks.py", line...
I notice that this module use ```concurrent.futures.ProcessPoolExecutor``` instead of ```joblib``` when generating random walk , according to [https://joblib.readthedocs.io/en/latest/auto_examples/parallel_random_state.html#sphx-glr-download-auto-examples-parallel-random-state-py](https://joblib.readthedocs.io/en/latest/auto_examples/parallel_random_state.html#sphx-glr-download-auto-examples-parallel-random-state-py) and [https://stackoverflow.com/questions/49847794/child-processes-generating-same-random-numbers-as-parent-process](https://stackoverflow.com/questions/49847794/child-processes-generating-same-random-numbers-as-parent-process) , I'm not sure whether ```concurrent.futures.ProcessPoolExecutor``` may lead to wrong...
Thank you for the great code. I have a question about the way you generate the random walks. It seems that the weights of the edges do not have any...
Could you please add documentation on how to use the API ? Thanks
Cannot run when the node sequence number is 0
Hi, I try to figure out the role of vocabulary_counts in skipgram.py, but it seems that the variable self.vocabulary_counts does not have any effect on the codes. In the Word2Vec...
As per #107, this PR implements an extra parameter, `--pretrained`, that can be used to specify pre-trained embeddings that will be used as the initializers for the node embeddings. The...
I don't know if this feature is available yet, but I needed to initialize the node embeddings with some pre-trained vectors and I wasn't able to (and I believe [the...