From fac51b1abbacd3dc6ebf912e0270a23cef3a2815 Mon Sep 17 00:00:00 2001 From: William L Hamilton Date: Wed, 31 May 2017 08:42:31 +0100 Subject: [PATCH] Update README.md --- README.md | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index a69c71a..c82837c 100644 --- a/README.md +++ b/README.md @@ -32,6 +32,10 @@ As input, at minimum the code requires that a --train_prefix option is specified * -feats.npy --- "A numpy-stored array of node features; ordering given by id_map.json" * -walks.txt --- "A text file specifying random walk co-occurrences (one pair per line)" (*only for unsupervised) +To run the model on a new dataset, you need to make data files in the format described above. +To run random walks for the unsupervised model and to generate the -walks.txt file) +you can use the `run_walks` function in `graphsage.utils`. + #### Model variants 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 @@ -52,9 +56,3 @@ Note that the full log outputs and stored embeddings can be 5-10Gb in size (on t The unsupervised variants of GraphSAGE will output embeddings to the logging directory as described above. These embeddings can then be used in downstream machine learning applications. The `eval_scripts` directory contains examples of feeding the embeddings into simple logistic classifiers. - -#### Running on a new dataset - -To run the model on a new dataset, you need to make data files of the format described above. -To run random walks for the unsupervised model (and to generate the -walks.txt file) -you can use the `run_walks` function in `graphsage.utils`.