Updated tutorial ECML 2023 and added presentation

Author: marshka

Gemfile.lock

@@ -1,20 +1,21 @@
 GEM
   remote: https://rubygems.org/
   specs:
-    addressable (2.8.1)
+    addressable (2.8.4)
       public_suffix (>= 2.0.2, < 6.0)
     colorator (1.1.0)
-    concurrent-ruby (1.1.10)
+    concurrent-ruby (1.2.2)
     em-websocket (0.5.3)
       eventmachine (>= 0.12.9)
       http_parser.rb (~> 0)
     eventmachine (1.2.7)
     ffi (1.15.5)
     forwardable-extended (2.6.0)
+    google-protobuf (3.23.2-x86_64-darwin)
     http_parser.rb (0.8.0)
-    i18n (1.12.0)
+    i18n (1.14.1)
       concurrent-ruby (~> 1.0)
-    jekyll (4.3.1)
+    jekyll (4.3.2)
       addressable (~> 2.4)
       colorator (~> 1.0)
       em-websocket (~> 0.5)
@@ -30,10 +31,13 @@ GEM
       safe_yaml (~> 1.0)
       terminal-table (>= 1.8, < 4.0)
       webrick (~> 1.7)
-    jekyll-feed (0.17.0)
+    jekyll-feed (0.15.1)
       jekyll (>= 3.7, < 5.0)
-    jekyll-sass-converter (2.2.0)
-      sassc (> 2.0.1, < 3.0)
+    jekyll-liquify (0.0.2)
+      liquid (>= 2.5, < 5.0)
+      redcarpet (~> 3.1)
+    jekyll-sass-converter (3.0.0)
+      sass-embedded (~> 1.54)
     jekyll-seo-tag (2.8.0)
       jekyll (>= 3.8, < 5.0)
     jekyll-watch (2.2.1)
@@ -42,8 +46,8 @@ GEM
       rexml
     kramdown-parser-gfm (1.1.0)
       kramdown (~> 2.0)
-    liquid (4.0.3)
-    listen (3.7.1)
+    liquid (4.0.4)
+    listen (3.8.0)
       rb-fsevent (~> 0.10, >= 0.10.3)
       rb-inotify (~> 0.9, >= 0.9.10)
     mercenary (0.4.0)
@@ -57,15 +61,16 @@ GEM
     rb-fsevent (0.11.2)
     rb-inotify (0.10.1)
       ffi (~> 1.0)
+    redcarpet (3.6.0)
     rexml (3.2.5)
-    rouge (4.0.1)
+    rouge (4.1.2)
     safe_yaml (1.0.5)
-    sassc (2.4.0)
-      ffi (~> 1.9)
+    sass-embedded (1.62.1-x86_64-darwin)
+      google-protobuf (~> 3.21)
     terminal-table (3.0.2)
       unicode-display_width (>= 1.1.1, < 3)
-    unicode-display_width (2.3.0)
-    webrick (1.7.0)
+    unicode-display_width (2.4.2)
+    webrick (1.8.1)
 
 PLATFORMS
   x86_64-darwin-20
@@ -74,6 +79,7 @@ DEPENDENCIES
   http_parser.rb (~> 0.6.0)
   jekyll (~> 4.3.1)
   jekyll-feed (~> 0.12)
+  jekyll-liquify
   minima (~> 2.5)
   tzinfo (>= 1, < 3)
   tzinfo-data

_tutorials/graph-based-processing/ecml-2023.html

@@ -1,6 +1,6 @@
 ---
 layout: particles_header
-title: Graph-based Processing of Spatiotemporal Time Series
+title: Graph Deep Learning for Spatiotemporal Time Series
 lead: Forecasting, Reconstruction and Analysis
 description: The GMLG tutorial on graph deep learning for time-series processing.
 venue: ECML PKDD 2023
@@ -76,6 +76,20 @@
         </div>
     </div>
 </section>
+<!-- Material section-->
+<section>
+    <div class="container px-4">
+        <div class="row gx-4 justify-content-center">
+            <div class="col-lg-8 text-center">
+                <h1>Material</h1>
+                <p>Download the slides used in our tutorial.</p>
+                <a href="./gdl4sts_handout.pdf">
+                    <img src="{{site.url}}/assets/img/presentation-thumb.png" height="82px" />
+                </a>
+            </div>
+        </div>
+    </div>
+</section>
 <!-- Program section-->
 <section class="bg-light">
     <div class="container px-4">
@@ -85,34 +99,31 @@ <h1 class="text-center">Program</h1>
                 <h5 class="mt-3 mb-2 fw-light"><span class="fw-bold me-2">Part 1</span> Graph-based processing of
                     spatiotemporal time series.</h5>
                 <ol>
-                    <li><strong>Spatiotemporal time series with graph-side information</strong><br>
+                    <li><strong>Spatiotemporal time series</strong><br>
                         Definition of the problem settings. Introduction to common downstream tasks: forecasting and
                         imputation.
                     </li>
                     <li><strong>Spatiotemporal graph neural networks (STGNNs)</strong><br>
                         Presentation of the fundamental components of the general STGNN family of deep learning models
-                        for STS. Recipes and strategies for building effective STGNNs are provided.
+                        for STS. Recipes and strategies for building effective STGNNs, as well as architectures from the
+                        literature, are provided.
                     </li>
-                    <li><strong>Global and local spatiotemporal models</strong><br>
+                    <li><strong>Global and local models</strong><br>
                         Discussion on the problem of local effects in spatiotemporal data. Review of the global and
                         local modeling paradigms with their strengths and practical implications.
                     </li>
-                    <li><strong>Forecasting</strong><br>
-                        Overview of model architectures from the literature.
+                    <li><strong>Model quality assessment</strong><br>
+                        Identification of time-space regions, e.g., specific sensors or periods of time, where
+                        predictions can be improved.
                     </li>
                 </ol>
 
                 <h5 class="mt-3 mb-2 fw-light"><span class="fw-bold me-2">Part 2</span> Challenges and tools.</h5>
                 <ol>
-                    <li><strong>Graph learning</strong><br>
+                    <li><strong>Latent graph learning</strong><br>
                         Why and how to learn a graph structure from data when relational information is unavailable,
                         insufficient or unreliable.
                     </li>
-                    <li><strong>Statistical tools to test the optimality of predictive
-                            models</strong><br>
-                        Identification of time-space regions, e.g., specific sensors or periods of time, where
-                        predictions can be improved.
-                    </li>
                     <li><strong>Learning in non-stationary environments</strong><br>
                         Challenges and methods associated with modeling the evolution of spatiotemporal systems over
                         time.
@@ -125,12 +136,11 @@ <h5 class="mt-3 mb-2 fw-light"><span class="fw-bold me-2">Part 2</span> Challeng
                         multivariate
                         time series imputation.
                     </li>
-                    <li><strong>Software</strong><br>
-                        Overview of open-source Pytorch libraries for graph-based spatiotemporal data processing and
-                        short demo
-                        with Torch Spatiotemporal.
-                    </li>
                 </ol>
+
+                <h5 class="mt-3 mb-2 fw-light"><span class="fw-bold me-2">Demo</span> Coding Spatiotemporal GNNs.</h5>
+                <p>Overview of open-source Pytorch libraries for graph-based spatiotemporal data processing and short demo
+                with Torch Spatiotemporal.</p>
             </div>
         </div>
     </div>