change the framing of tdl

Author: mhajij

packs/challenge.html

@@ -371,12 +371,9 @@ <h1>ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain<a cla
 </section>
 <section id="motivation">
 <h1>Motivation<a class="headerlink" href="#motivation" title="Link to this heading">#</a></h1>
-<p>The field of Topological Deep Learning (TDL) aims to extend Graph Neural
-Networks (GNN) by naturally processing relations between more than two
-elements, ubiquitous in any realistic complex system (social connections
+<p> In the field of Topological Deep Learning (TDL), we focus on developing deep learning models for data situated on topological domains such as simplicial complexes, cell complexes, and hypergraphs. These domains encompass diverse structures found in scientific computations . Topological domains naturally model higher-order interactions ubiquitous in any realistic complex system (social connections
 within a community, molecular structures and reactions, n-body
-interactions,…). More specifically, TDL methods allow to go beyond
-graphs’ pairwise connections –and local neighborhoods– by encoding
+interactions,…). More specifically, TDL methods allow encoding
 higher-order relationships through algebraic topology concepts;
 <a class="reference internal" href="#fig-domains"><span class="std std-numref">Fig. 1</span></a> illustrates the standard <em>topological domains</em> used
 to that end.</p>