Add breadcrumbs

RSTZZZ · RSTZZZ · commit 9a8acb07dbd3 · 2024-12-24T06:26:11.000Z
diff --git a/_config.yml b/_config.yml
@@ -106,6 +106,7 @@ defaults:
         - no-sidebar
         - wide
       author_profile: false
+
   # _posts/blog
   - scope:
       path: _posts/blog
@@ -119,6 +120,7 @@ defaults:
       related: false
       classes:
         - wide
+
   # _posts/papers
   - scope:
       path: _posts/papers
@@ -129,6 +131,7 @@ defaults:
         - wide
       author_profile: true
       share: true
+
   # _posts/teaching
   - scope:
       path: _posts/teaching
@@ -138,7 +141,8 @@ defaults:
       classes:
         - no-sidebar
       author_profile: false
-      share: true
+
+
   # _projects
   - scope:
       path: ""
@@ -152,6 +156,7 @@ defaults:
 
 
 
+
 category_archive:
   type: liquid
   path: /categories/
diff --git a/_includes/breadcrumbs.html b/_includes/breadcrumbs.html
@@ -1,28 +1,30 @@
 <!-- _includes/breadcrumbs.html -->
-<nav class="breadcrumbs">
-    <ol class="breadcrumb-list" itemscope itemtype="https://schema.org/BreadcrumbList">
-        <!-- Home -->
-        <li class="breadcrumb-item" itemprop="itemListElement" itemscope itemtype="https://schema.org/ListItem">
-            <a href="{{ site.url }}" itemprop="item">
-                <span itemprop="name">Home</span>
-            </a>
-            <meta itemprop="position" content="1" />
-        </li>
+<div class="breadcrumb-wrapper">
+    <nav class="breadcrumbs">
+        <ol class="breadcrumb-list" itemscope itemtype="https://schema.org/BreadcrumbList">
+            <!-- Home -->
+            <li class="breadcrumb-item" itemprop="itemListElement" itemscope itemtype="https://schema.org/ListItem">
+                <a href="{{ site.url }}" itemprop="item"> Home
+                </a>
+                <meta itemprop="position" content="1" />
+            </li>
 
-        <!-- Previous page (if exists) -->
-        {% if page.parent %}
-        <li class="breadcrumb-item" itemprop="itemListElement" itemscope itemtype="https://schema.org/ListItem">
-            <a href="{{ site.url }}/{{ page.parent | slugify }}" itemprop="item">
-                <span itemprop="name">{{ page.parent }}</span>
-            </a>
-            <meta itemprop="position" content="2" />
-        </li>
-        {% endif %}
+            <!-- Previous page (if exists) -->
+            {% if page.parent %}
+            <li class="breadcrumb-item" itemprop="itemListElement" itemscope itemtype="https://schema.org/ListItem">
+                <a href="{{ site.url }}/{{ page.parent | slugify }}" itemprop="item">
+                    {{ page.parent }}
+                </a>
+                <meta itemprop="position" content="2" />
+            </li>
+            {% endif %}
 
-        <!-- Current page -->
-        <li class="breadcrumb-item current" itemprop="itemListElement" itemscope itemtype="https://schema.org/ListItem">
-            <span itemprop="name">{{ page.title }}</span>
-            <meta itemprop="position" content="{% if page.parent %}3{% else %}2{% endif %}" />
-        </li>
-    </ol>
-</nav>
+            <!-- Current page -->
+            <li class="breadcrumb-item current" itemprop="itemListElement" itemscope
+                itemtype="https://schema.org/ListItem">
+                {{ page.title }}
+                <meta itemprop="position" content="{% if page.parent %}3{% else %}2{% endif %}" />
+            </li>
+        </ol>
+    </nav>
+</div>
diff --git a/_research_directions/online-crime.md b/_research_directions/online-crime.md
@@ -11,6 +11,8 @@ one-liner: "How to analyze large online markets and build victim-centered tools
 
 ---
 
+{% include breadcrumbs.html %}
+
 Sex trafficking impacts 4.8 million people globally and is a $99 billion USD industry that often operates undetected, including in Canada. Technology has become a critical tool for traffickers, enabling recruitment and exploitation while making these crimes harder to trace. However, innovative analytics can uncover hidden patterns, identify victims, and provide much-needed support to those impacted. Our interdisciplinary team of AI and criminology experts is dedicated to developing context-aware, human-centered solutions to tackle this issue responsibly. Through advanced techniques like data mining and anomaly detection, we are working to bring a data-driven approach to the fight against human trafficking in Canada.
 
 # Selected Publications
diff --git a/_research_directions/online-toxicity.md b/_research_directions/online-toxicity.md
@@ -20,6 +20,8 @@ logos:
     name: Mitacs
 ---
 
+{% include breadcrumbs.html %}
+
 Toxic and harmful speech online is more than just unpleasant; it has widespread social and economic repercussions, particularly as it permeates social media and gaming platforms. In gaming, where toxicity affects 75% of young players, this behavior harms mental health, alienates communities, and even reduces player engagement and spending, which impacts the industry’s bottom line. Beyond financial losses, unchecked toxicity risks fostering real-world violence and inciting harmful social behaviors. Despite advances in detection methods, including AI-driven moderation, the ever-evolving nature of toxic language poses significant challenges to companies and communities alike. Addressing this problem isn’t just about improving user experience — it’s essential for maintaining safe, inclusive, and healthy online spaces.
 
 
diff --git a/_research_directions/poli-sci.md b/_research_directions/poli-sci.md
@@ -11,6 +11,8 @@ one-liner: How can we use AI to understand the exchange of information and ideas
 
 ---
 
+{% include breadcrumbs.html %}
+
 The current digital age fundamentally changes how we as individuals and a society collect and distribute information. With these changes come powerful new approaches to influence the public agenda. However, the quality of shared information varies widely, and can have wide-reaching consequences. As the sophistication and accessibility of AI tools continue to expand, the authenticity of digital content has been increasingly called into question. Our team stands at the forefront of the challenge to safeguard digital space, as we assess the nature of content and how it proliferates online.
 
 # Topics
diff --git a/_research_directions/poli-sci/ideology-and-polarization.md b/_research_directions/poli-sci/ideology-and-polarization.md
@@ -8,8 +8,12 @@ header:
     overlay_image: /assets/images/research_directions/poli-sci/social_media.webp
 one-liner: How can we measure and understand political conflict?
 excerpt:  From echo chamber to public square, online environments are full of political discussion and conflict. We aim to measure and understand the evolving discourse, and ultimately, how it shapes our beliefs.
+parent: Politics & Online Media
+
 ---
 
+{% include breadcrumbs.html %}
+
 Our research on ideology and polarization explores how digital platforms amplify partisan divides and shape political discourse across societal contexts. It focuses on understanding the expression, measurement, and impact of ideological differences in shaping public opinion, both within and across linguistic and cultural boundaries. This area highlights the interplay between technology, political behavior, and societal cohesion in an increasingly interconnected world.
 
 # Selected Publications
diff --git a/_research_directions/poli-sci/information-integrity.md b/_research_directions/poli-sci/information-integrity.md
@@ -17,8 +17,13 @@ projects:
   - title: "Deepfake"
     alt: "Deepfake"
     excerpt: ""
+
+parent: Politics & Online Media
+
 ---
 
+{% include breadcrumbs.html %}
+
 The information integrity project explores methods to enhance the accuracy and reliability of online information within the context of digital platforms and AI technologies. By analyzing how information is created, shared, and verified on social media and other digital ecosystems, we aim to develop tools and frameworks that support the identification of misinformation, reduce its spread, and bolster public trust in verified sources. This project contributes to our broader goal of understanding and mitigating the effects of digital misinformation on political discourse and social cohesion.
 
 # Selected Publications
diff --git a/_research_directions/poli-sci/social-simulations.md b/_research_directions/poli-sci/social-simulations.md
@@ -9,8 +9,12 @@ header:
 one-liner: How can we prototype effective defenses to attacks on information integrity in an ethical and efficient way?
 excerpt: We use and develop state-of-the-art approaches to human social system simulation to simulate attacks on information integrity in critical social phenomena and to prototype effective defenses against them. 
 
+parent: Politics & Online Media
+
 ---
 
+{% include breadcrumbs.html %}
+
 The pernicious effects of digital manipulation campaigns can reverberate through entire societies, but effectively detecting and responding to them is a challenge. Testing solutions in real-world contexts is highly complex and poses ethical barriers. Taking advantage of state-of-the-art approaches to modelling human social systems with face validity, in this project we overcome these barriers using a simulation approach. We have developed a scalable digital social environment simulator that offers fine-grained experimental control through precise and versatile configuration and a suite of evaluation analyses. We are using it to study information integrity in the context of societal events where it plays a central role, such as elections. By simulating real world and future manipulation strategies and analyzing their properties, we are pursuing a quantitative approach to prototyping effective defenses against them.
 
 
diff --git a/_research_directions/temporal-graph-learning.md b/_research_directions/temporal-graph-learning.md
@@ -11,6 +11,8 @@ excerpt: "Our team comprises experts in AI, data mining, social science, and pub
 
 ---
 
+{% include breadcrumbs.html %}
+
 Time-evolving graphs, also known as temporal networks, are a crucial area of study in network science and are ubiquitous in the real world. They represent systems where entities (nodes) and their interactions (edges) change over time. Understanding and predicting the behavior of these dynamic networks are essential for various applications, from tracking disease spread to detecting fraudulent activities and enhancing recommendation systems. However, modeling and analyzing time-evolving graphs presents significant challenges due to their complex and ever-changing nature. Therefore, there is a pressing need to develop advanced machine learning techniques that can effectively handle the unique characteristics of temporal networks.
 
 # Topics
diff --git a/_research_directions/temporal-graph-learning/TGF.md b/_research_directions/temporal-graph-learning/TGF.md
@@ -7,7 +7,7 @@ header:
     overlay_filter: linear-gradient(rgba(255, 255, 255, 0.1), rgba(0, 0, 0, 0.5))
     overlay_image: /assets/images/research_directions/temporal-graph-learning/TGB.webp
 excerpt: ""
-
+parent: Temporal Graph Learning
 
 project_1:
   - title: "Foundation Model"
@@ -29,6 +29,8 @@ project_3:
 
 ---
 
+{% include breadcrumbs.html %}
+
 This research direction focuses on advancing the frontier of temporal graph analysis by integrating Temporal Graph Foundation Models (TGFM), Large Language Models (LLMs), and multi-modal learning. Temporal graphs, which capture the dynamic relationships and evolving structures of real-world networks over time, are crucial for understanding complex, time-sensitive systems. By combining these graphs with foundation models, we can leverage large-scale pre-training to enable transfer learning and scalable solutions across a range of temporal tasks.
 
 The integration of LLMs with temporal graphs enhances reasoning and representation learning, enabling more sophisticated analysis of dynamic networks. This synergy allows for improved predictive capabilities, anomaly detection, and scenario modeling. Furthermore, the incorporation of multi-modal data—such as text, images, and signals into temporal graphs provides a holistic approach to complex tasks like misinformation detection, event prediction, and spatiotemporal analysis. This research aims to push the boundaries of temporal network analysis by combining the power of temporal graph models with cutting-edge AI techniques, unlocking new opportunities for real-world applications.
diff --git a/_research_directions/temporal-graph-learning/tga.md b/_research_directions/temporal-graph-learning/tga.md
@@ -8,9 +8,12 @@ header:
     overlay_image: /assets/images/research_directions/temporal-graph-learning/TGA.jpg
 one-liner: How to deploy TGL methods for applications such as disease modeling, anomaly detection and forecasting?
 excerpt: Explore the cutting-edge applications of temporal graph learning, from real-time fraud detection to advanced disease modeling. Discover how dynamic network analysis enhances accuracy and efficiency in various domains.
+parent: Temporal Graph Learning
 
 ---
 
+{% include breadcrumbs.html %}
+
 Temporal graphs provide a robust framework for modeling and analyzing systems that evolve over time, offering unique advantages in addressing dynamic real-world challenges. In anomaly detection, they capture time-varying patterns to identify irregularities across domains such as finance, social networks, and cryptocurrency markets. For example, temporal graphs can highlight fraudulent transactions, uncover outliers in trading patterns, or detect sudden shifts in network behavior. In epidemic modeling, temporal graphs accurately represent evolving human contact networks, enabling more precise predictions of disease spread by accounting for temporal dependencies and behavioral changes, such as social distancing or vaccination. They also enhance forecasting in transportation systems like flight networks, tracking delays, cancellations, and disruptions over time to optimize scheduling and reduce congestion. By incorporating both structural and temporal dynamics, temporal graphs empower more realistic, data-driven approaches to solving complex, time-sensitive problems across diverse fields.
 
 # Selected Publications
diff --git a/_research_directions/temporal-graph-learning/tgb.md b/_research_directions/temporal-graph-learning/tgb.md
@@ -9,10 +9,13 @@ header:
     overlay_size: contain
 one-liner: How to realistically, reproducibly, and robustly evaluate machine learning models on temporal graphs?
 excerpt: ""
-
+parent: Temporal Graph Learning
 
 ---
 
+{% include breadcrumbs.html %}
+
+
 The Temporal Graph Benchmark (TGB) is a comprehensive collection of datasets designed for the realistic, reproducible, and robust evaluation of machine learning models on temporal graphs. These datasets are large-scale, span multiple years, and cover various domains such as social networks, trade networks, transaction networks, and transportation networks. They include both node and edge-level prediction tasks, providing a diverse set of challenges for researchers.
 
 The follow-up work TGB 2.0 is a new benchmarking framework designed to evaluate methods for predicting future links on Temporal Knowledge Graphs (TKGs) and Temporal Heterogeneous Graphs (THGs). This framework extends the original Temporal Graph Benchmark by focusing on large-scale datasets, which are significantly larger than existing datasets in terms of nodes, edges, or timestamps. 
diff --git a/_sass/custom/breadcrumbs.scss b/_sass/custom/breadcrumbs.scss
@@ -1,43 +1,50 @@
 .breadcrumbs {
-    margin: 0 0 1em;
+    margin: 0 0 1em; // Space before paragraph
     padding: 0;
-    font-family: $sans-serif;
-    font-size: $type-size-6;
+    width: 100%;
 
     .breadcrumb-list {
         display: flex;
-        flex-wrap: wrap;
+        align-items: center;
         list-style: none;
         margin: 0;
-        padding: 0;
+        gap: 0.8em; // Slightly increased space between elements
+        font-size: 1.2em; // Increased font size
+        float: left
     }
 
     .breadcrumb-item {
-        display: inline-block;
+        display: flex;
+        align-items: center;
+        color: $link-color; // Default text color
+        line-height: 2em;
 
         a {
-            text-decoration: none;
             color: $link-color;
+            text-decoration: none;
 
             &:hover {
                 text-decoration: underline;
-                color: $link-color-hover;
             }
         }
 
-        // Add separator after each item except the last
         &:not(:last-child) {
             &::after {
                 content: ">";
-                margin: 0 0.5em;
-                color: $text-color;
-                opacity: 0.5;
+                margin-left: 0.5em;
+                color: $link-color; // Same color as links
             }
         }
 
-        // Style for current page
         &.current {
-            color: $text-color;
+            color: $text-color; // Black color for current page
         }
     }
+}
+
+// Container wrapper to ensure alignment with content
+.breadcrumb-wrapper {
+    width: 100%;
+    margin: 0 auto;
+    max-width: $max-width;
 }
