Select a calendar:
Filter May Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Student Activity
Events for May
-
PhD Defense- Woojeong Jin
Wed, May 01, 2024 @ 10:00 AM - 11:30 AM
Thomas Lord Department of Computer Science
Student Activity
PhD Defense- Woojeong Jin
Title: Bridging the Visual Knowledge Gaps in Pre-trained Models
Committee: Xiang Ren (chair), Ram Nevatia, Yan Liu, Toby Mintz.
Abstract: Humans acquire knowledge by processing visual information through observation and imagination, which expands our reasoning capability about the physical world we encounter every day. Despite significant progress in solving AI problems, current state-of-the-art models in natural language processing (NLP) and computer vision (CV) have limitations in terms of reasoning and generalization, particularly with complex reasoning on visual information and generalizing to unseen vision-language tasks. In this thesis, we aim to build a reasoner that can do complex reasoning about the physical world and generalization on vision-language tasks. we will present a few lines of work to bridge the visual knowledge gaps in pre-trained models.Location: Henry Salvatori Computer Science Center (SAL) - 322
Audiences: Everyone Is Invited
Contact: Woojeong Jin
-
PhD Dissertation Defense- Basel Shbita
Wed, May 01, 2024 @ 03:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Student Activity
PhD Dissertation Defense- Basel Shbita
Title: Transforming Unstructured Historical and Geographic Data into Spatio-Temporal Knowledge Graphs
Committee: Craig A. Knoblock (chair), Cyrus Shahabi, John P. Wilson; Jay Pujara, Yao-Yi Chiang
Abstract: This dissertation presents a comprehensive approach to the transformation, integration and semantic enrichment of historical spatio-temporal data into knowledge graphs. The dissertation encompasses three core contributions: one, the automated generation of knowledge graphs from digitized historical maps for analyzing geographical changes over time; two, the integration of spatial and semantic context embeddings for accurate geo-entity recognition and semantic typing; and three, the creation of a comprehensive knowledge graph for the analysis of historical data from digitized archived records. I introduce innovative methodologies and practical tools to support researchers from diverse fields, enabling them to derive meaningful insights from historical and geographic data. My approach is demonstrated through various applications, such as analyzing geospatial changes over time in USGS (United States Geological Survey) historical maps of transportation networks and wetlands, automatic semantic typing of unlabeled georeferenced spatial entities, and constructing a spatio-temporal knowledge graph from digitized historical mineral mining data. The dissertation combines semantic web technologies, representation learning, and semantic modeling to build comprehensive knowledge graphs that support geospatial and temporal analyses.Audiences: Everyone Is Invited
Contact: Basel Shbita
Event Link: https://usc.zoom.us/j/97894910088?pwd=ZVQ0VU9lYlJaWTM4V2w5Vk1maEVOQT09
-
PhD Defense- Julie Jiang
Fri, May 03, 2024 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Student Activity
PhD Defense- Julie Jiang
Title: Socially-informed content analysis of online human behavior
Committee: Emilio Ferrara (CS and Communication, tenure, chair), Kristina Lerman (CS), Marlon Twyman II (Communication, external), Pablo Barberá (Poli Sci)
Abstract: The explosive growth of social media has not only revolutionized communication but also brought challenges such as political polarization, misinformation, hate speech, and echo chambers. This dissertation employs computational social science techniques to investigate these issues, understand the social dynamics driving negative online behaviors, and propose data-driven solutions for healthier digital interactions. I begin by introducing a scalable social network representation learning method that integrates user-generated content with social connections to create unified user embeddings, enabling accurate prediction and visualization of user attributes, communities, and behavioral propensities. Using this tool, I explore three interrelated problems: 1) COVID-19 discourse on Twitter, revealing polarization and asymmetric political echo chambers; 2) online hate speech, suggesting the pursuit of social approval motivates toxic behavior; and 3) moral underpinnings of COVID-19 discussions, uncovering patterns of moral homophily and echo chambers, while also indicating moral diversity and plurality can improve message reach and acceptance across ideological divides. These findings contribute to the advancement of computational social science and provide a foundation for understanding human behavior through the lens of social interactions and network homophily.
Location: Grace Ford Salvatori Hall Of Letters, Arts & Sciences (GFS) - 104
Audiences: Everyone Is Invited
Contact: Julie Jiang
Event Link: https://usc.zoom.us/j/5152754393?pwd=V1pzUnpEc0JtTVZlS0l5R1VMRWlRdz09&omn=91709345144
-
PhD Defense- Yilei Zeng
Tue, May 07, 2024 @ 10:30 AM - 12:00 PM
Thomas Lord Department of Computer Science
Student Activity
PhD Defense- Yilei Zeng
Title: Learning Social Sequential Decision-Making in Online Games
Committee: Emilio Ferrara (chair), Dmitri Williams, Michael Zyda
Abstract:
A paradigm shift towards human-centered intelligent gaming systems is gradually setting in. This dissertation explores the complexities of social sequential decision-making within online gaming environments and presents comprehensive AI solutions to enhance personalized single and multi-agent experiences. The three core contributions of the dissertation are intricately interrelated, creating a cohesive framework for understanding and improving AI in gaming. I begin by delving into the dynamics of gaming sessions and sequential in-game individual and social decision-making, which establishes a baseline of how decisions evolve, providing the necessary context for the subsequent integration of diverse information sources; two, the integration of heterogeneous information and multi-modal trajectories, which enhances decision-making generation models; and three, the creation of a reinforcement learning with human feedback framework to train gaming AIs that effectively align with human preferences and strategies, which enables the system not only learning but also interacting with humans. Collectively, this dissertation combines innovative data-driven, generative AI, representation learning, and human-AI collaboration solutions to help advance both the fields of computational social science and artificial intelligence applications of gaming.
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Yilei Zeng
-
PhD Dissertation Defense - Nicolaas Weideman
Thu, May 16, 2024 @ 09:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Student Activity
PhD Dissertation Defense - Nicolaas Weideman
Title: Improving Binary Program Analysis to Enhance the Security of Modern Software Systems
Committee: Jelena Mirkovic (chair), Chao Wang and Paul Bogdan
Abstract: With the ever-increasing reliance of the modern world on software systems, the frequency and impact of cyberattacks have greatly increased as well. Software must be analyzed thoroughly to evaluate its security, as vulnerabilities in software can have devastating consequences such as compromised privacy of users, shutdown of infrastructure, significant business losses, and even pose threat to human life. Unfortunately, manual analysis of the source code is insufficient to evaluate the security of software. This is firstly due to the quantity and size of modern software making this method impractical and secondly due to low-level vulnerabilities that are invisible in the source code. Conversely, binary program analysis focuses on automatically analyzing the machine code instructions of executables to reason about security-related properties. In this thesis we enhance automatic software security evaluation by leveraging and extending binary program analysis. We develop approaches to 1) automatically discover vulnerabilities and 2) automatically and safely patch vulnerabilities. We improve the reliability of binary data-flow analysis by 3) evaluating three state of the art binary analysis frameworks and 4) improving the state of the art. Each of these directions independently pushes the boundaries of what is possible in defending modern software, leading to a more secure digital environment.
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Nicolaas Weideman
-
PhD Defense- Hongkuan Zhou
Fri, May 17, 2024 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Student Activity
PhD Defense- Hongkuan Zhou
Title: Scaling up Temporal Graph Learning: Powerful Models, Efficient Algorithms, and Optimized Systems
Committee Members: Prof. Keith Michael Chugg, Prof. Rajgopal Kannan, Prof Viktor K. Prasanna (Chair), Prof. Mukund Raghothaman
Abstract: Recently, Temporal Graph Neural Networks (TGNNs) have extended the scope of Graph Representation Learning (GRL) to dynamic graphs. TGNNs generate high-quality and versatile dynamic node embeddings by simultaneously encoding the graph structures, node and edge contexts, and their temporal dependencies. TGNNs are shown to demonstrably outperform traditional dynamic graph analytic algorithms in impactful applications that address critical real-world challenges, such as social network analysis, healthcare applications, and traffic prediction and management. However, due to the challenges of the prevalent noise in real-world data, irregular memory accesses, complex temporal dependencies, and high computation complexity, current TGNNs face the following problems when scaling to large dynamic graphs: (1) Unpowerful models. Current TGNN models struggle to capture high-frequency information and handle the diverse and dynamic noise. (2) Ineffcieint algorithms. Current training algorithms cannot leverage the massive parallel processing architecture of modern hardware, while current inference algorithms cannot meet the requirements in different scenarios. And (3) Unoptimized systems. Current TGNN systems suffer from inefficient designs that hinder overall performance. In this dissertation, we address the above issues via model-algorithm-system co-design. For model improvements, we propose a static node-memory-enhanced TGNN model and a temporal adaptive sampling technique. For algorithm improvements, we propose a scalable distributed training algorithm with heuristic guidelines to achieve the optimal configuration, and a versatile inference algorithm. For system improvements, we propose techniques of dynamic feature caching, simplified temporal attention, etc., to compose optimized training and inference systems. We demonstrate significant improvements in accuracy, training time, inference latency, and throughput compared with state-of-the-art TGNN solutions.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Hongkuan Zhou
