Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Gemfile.lock
100755 → 100644
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ GEM
jekyll (~> 4.0)
jekyll-watch (2.2.1)
listen (~> 3.0)
kramdown (2.2.1)
kramdown (2.3.1)
rexml
kramdown-parser-gfm (1.1.0)
kramdown (~> 2.0)
Expand Down
Binary file modified assets/sgf_cv.pdf
Binary file not shown.
4 changes: 2 additions & 2 deletions index.html
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@
<br><br>
In addition to my research, I am involved in the Hydrocephalus community by way of <a href="http://teamhydro.org">Team Hydro</a>, a non-profit organization that my family and I started to raise money and awareness for the condition in honor of my sister, <a href="http://teamhydro.org/kate-finlayson/">Kate</a>. I also do consulting work as a data scientist and deep learning engineer, with clients including tech, biotech, and pharmaceutical companies.
<br><br>
For a more formal account of my academic work, see my <a href=../assets/sgf_cv.pdf"> Curriculum Vitae</a> or <a href="https://scholar.google.com/citations?user=7__yMlEAAAAJ&hl=en">Google Scholar</a>.
For a more formal account of my academic work, see my <a href="../assets/sgf_cv.pdf"> Curriculum Vitae</a> or <a href="https://scholar.google.com/citations?user=7__yMlEAAAAJ&hl=en">Google Scholar</a>.
</p>
</div><!-- table container -->

Expand Down Expand Up @@ -140,7 +140,7 @@ <h3>Subgraph Neural Networks</h3>
<i>In Submission, 2020<br>
<i>*Co-first, listed alphabetically<br>
[<a class="showSingle", target="27">Abstract</a>]
[<a href="">Paper</a>]
[<a href="https://arxiv.org/abs/2006.10538">Paper</a>]
</p>
<div id="div27" class="abstract">
Deep learning methods for graphs achieve remarkable performance on many node-level and graph-level prediction tasks. However, despite the proliferation of the methods and their success, prevailing Graph Neural Networks (GNNs) neglect subgraphs, rendering subgraph prediction tasks challenging to tackle in many impactful applications. Further, subgraph prediction tasks present several unique challenges: subgraphs can have non-trivial internal topology, but also carry a notion of position and external connectivity information relative to the underlying graph in which they exist.
Expand Down