Update README.md

README.md

@@ -1,14 +1,9 @@
 # Keras Graph Attention Network
-This is a Keras implementation of the Graph Attention Network (GAT)
-model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903).
+This is a Keras implementation of the Graph Attention Network (GAT) model by Veličković et al. (2017, [[arXiv link]](https://arxiv.org/abs/1710.10903)).
 
 ## Acknowledgements
-I have no affiliation with the authors of the paper and I am
-implementing this code for non-commercial reasons.  
-The authors published their [reference Tensorflow implementation
-here](https://github.com/PetarV-/GAT), so check it out for something that
-is guaranteed to work as intended. Their implementation is slightly
-different than mine, so that may be something to keep in mind.
+I have no affiliation with the authors of the paper and I am implementing this code for non-commercial reasons.  
+The authors published their [reference Tensorflow implementation here](https://github.com/PetarV-/GAT), so check it out for something that is guaranteed to work as intended. Their implementation is slightly different than mine, so that may be something to keep in mind.
 You should cite the paper if you use any of this code for your research:
 ```
 @article{
@@ -21,25 +16,14 @@ You should cite the paper if you use any of this code for your research:
   note={Accepted as poster},
 }
 ```
-If you would like to give me credit, feel free to link to my
-[Github profile](https://github.com/danielegrattarola),
-[blog](https://danielegrattarola.github.io), or
-[Twitter](https://twitter.com/riceasphait).
+If you would like to give me credit, feel free to link to my [Github profile](https://github.com/danielegrattarola), [blog](https://danielegrattarola.github.io), or [Twitter](https://twitter.com/riceasphait).
 
-I also copied the code in `utils.py` almost verbatim from [this repo by
-Thomas Kipf](https://github.com/tkipf/gcn), who I thank sincerely for
-sharing his work on GCNs and GAEs, and for giving me a few pointers on
-how to split the data into train/test/val sets.
+I also copied the code in `utils.py` almost verbatim from [this repo by Thomas Kipf](https://github.com/tkipf/gcn), who I thank sincerely for sharing his work on GCNs and GAEs, and for giving me a few pointers on how to split the data into train/test/val sets.
 
-Thanks to [matthias-samwald](https://github.com/matthias-samwald),
-[mawright](https://github.com/mawright) (commit f4974ac),
-and [vermaMachineLearning](https://github.com/vermaMachineLearning)
-(commit 7959bd8) for helping me out with early bugs and running
-experiments.
+Thanks to [mawright](https://github.com/mawright), [matthias-samwald](https://github.com/matthias-samwald), and [vermaMachineLearning](https://github.com/vermaMachineLearning) for helping me out with bugs, performance improvements, and running experiments.
 
 ## Disclaimer
-I do not own any rights to the datasets distributed with this code, but
-they are publicly available at the following links:
+I do not own any rights to the datasets distributed with this code, but they are publicly available at the following links:
 
 - CORA: [https://relational.fit.cvut.cz/dataset/CORA](https://relational.fit.cvut.cz/dataset/CORA)
 - PubMed: [https://catalog.data.gov/dataset/pubmed](https://catalog.data.gov/dataset/pubmed)
@@ -55,14 +39,10 @@ $ python
 >>> from keras_gat import GraphAttention
 ```
 
-Or you can just copy and paste `graph_attention_layer.py` into your
-project.
+Or you can just copy and paste `graph_attention_layer.py` into your project.
 
 ## Replicating experiments
-If you wish to replicate the experimental results of the paper, simply
-run:
+To replicate the experimental results of the paper, simply run:
 ```sh
 $ python examples/gat.py
 ```
-
-from the base folder.