diff --git a/README.md b/README.md
new file mode 100644
index 0000000..8e7a971
--- /dev/null
+++ b/README.md
@@ -0,0 +1,17 @@
+= decagon-pytorch
+
+== Introduction
+
+[Decagon](https://github.com/mims-harvard/decagon)
+is a method for learning node embeddings in multimodal graphs,
+and is especially useful for link prediction in highly multi-relational
+settings.
+
+Decagon-PyTorch is a PyTorch reimplementation of the algorithm.
+
+== References
+
+1. Zitnik, M., Agrawal, M., & Leskovec, J. (2018).
+[Modeling polypharmacy side effects with graph convolutional networks](https://academic.oup.com/bioinformatics/article/34/13/i457/5045770)
+Bioinformatics, 34(13), i457-i466.
+