huihun/graphsage-tf
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
William L Hamilton 2017-06-07 13:56:17 +01:00 committed by GitHub
parent 177da64846
commit eb05f6e6c5
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -24,6 +24,8 @@ The example_unsupervised.sh and example_supervised.sh files contain example usag
Note that example_unsupervised.sh sets a very small max iteration number, which can be increased to improve performance. Note that example_unsupervised.sh sets a very small max iteration number, which can be increased to improve performance.
We generally found that performance continued to improve even after the loss was very near convergence (i.e., even when the loss was decreasing at a very slow rate). We generally found that performance continued to improve even after the loss was very near convergence (i.e., even when the loss was decreasing at a very slow rate).
*Note:* For the PPI data, and any other multi-ouput dataset that allows individual nodes to belong to multiple classes, it is necessary to set the `--sigmoid` flag during supervised training. By default the model assumes that the dataset is in the "one-hot" categorical setting.
#### Input format #### Input format
As input, at minimum the code requires that a --train_prefix option is specified which specifies the following data files: As input, at minimum the code requires that a --train_prefix option is specified which specifies the following data files:
@ -37,6 +39,8 @@ To run the model on a new dataset, you need to make data files in the format des
To run random walks for the unsupervised model and to generate the <prefix>-walks.txt file) To run random walks for the unsupervised model and to generate the <prefix>-walks.txt file)
you can use the `run_walks` function in `graphsage.utils`. you can use the `run_walks` function in `graphsage.utils`.
#### Model variants #### Model variants
The user must also specify a --model, the variants of which are described in detail in the paper: The user must also specify a --model, the variants of which are described in detail in the paper:
* graphsage_mean -- GraphSAGE with mean-based aggregator * graphsage_mean -- GraphSAGE with mean-based aggregator