USC - Viterbi School of Engineering

Apr
29

PhD Dissertation Defense - Mengxiao Zhang
Mon, Apr 29, 2024 @ 01:30 PM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar

Title: Robust and Adaptive Algorithm Design in Online Learning: Regularization, Exploration, and Aggregation

Abstract: In recent years, online learning is becoming a central component in Artificial Intelligence and has been widely applied in many real applications. In this thesis, we focus on designing algorithms for online learning with the two characteristics: robustness and adaptivity. Motivated by the existence of unpredictable corruptions and noises in real-world applications such as E-commerce recommendation systems, robustness is a desired property. It means that the designed algorithm is guaranteed to perform well even in adversarial environments. In contrast, adaptivity complements robustness by enhancing performance in benign environments.In order to achieve robustness and adaptivity, we utilize the following three methodologies, namely regularization, exploration, and aggregation. Regularization method has been widely used in the field of machine learning to control the dynamic of the decisions, which is especially important when facing a possibly adversarial environment. In online learning problems, very often the learner can only observe partial information of the environment, making an appropriate exploration method crucial. Aggregation, a natural idea to achieve adaptivity, combines multiple algorithms that work well in different environments. Though intuitive, this requires non-trivial algorithm design for different online learning problems.In this thesis, we design algorithms for a wide range of online learning problems. We first consider the problem of multi-armed bandits with feedback graphs. Then, we consider more complex problems including linear bandits and convex bandits, which involve an infinite number of actions. We hope that the techniques and algorithms developed in this thesis can help improve the current online learning algorithms for real-world applications. Committee Members:Haipeng Luo (Chair), Vatsal Sharan, Renyuan Xu
Location: Ronald Tutor Hall of Engineering (RTH) - 114
Audiences: Everyone Is Invited

Contact: Ellecia Williams
Apr
30

PhD Dissertation Defense - Alan Romano
Tue, Apr 30, 2024 @ 09:30 AM - 11:30 AM
Thomas Lord Department of Computer Science
University Calendar

Title: Static Program Analyses for WebAssembly

Committee Members: Weihang Wang (Chair), Chao Wang, and Pierluigi Nuzzo

Date/Time: Tuesday, April 30th, 9:30am - 11:30am

Abstract: WebAssembly is a recent standard for the web that aims to enable high-performance web applications that can run at near-native speeds. The standard has gained attention in both academia and industry for its ability to speed up existing user-facing web applications. Due to its well-defined and sound design, many static program analysis techniques have been developed to accomplish various purposes of WebAssembly analysis. However, we identify gaps in the static program analysis tools of the current WebAssembly ecosystem. We find that current program optimizations applied on WebAssembly modules may lead to diminished performance. We also identify a lack of tools that help developers understand WebAssembly modules through robust binary decompilation. Finally, we find a gap in the ability to analyze cross-language WebAssembly applications across the two languages they are typically implemented in, i.e., WebAssembly and JavaScript.

In this thesis, we present a novel WebAssembly Analysis Framework, or WAF . WAF is a static program analysis framework for WebAssembly modules that consists of multiple intermediate representations. Inspired by frameworks made for Java, the core of our framework lies in our three intermediate representations that each model the WebAssembly module at a different semantic level. This structure enables WAF to serve in multiple use cases, including program optimizations, binary decompilation, cross-language program analysis, and malware detection. We aim to show that our framework can improve static program analysis in the areas that the WebAssembly ecosystem is lacking.
Location: Henry Salvatori Computer Science Center (SAL) - 322
Audiences: Everyone Is Invited

Contact: Alan Romano
Apr
30

PhD Thesis Proposal - Tian Ye
Tue, Apr 30, 2024 @ 03:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar

Title: Enhancing Adversarial Training in Low-Label Regimes

Committee Members: Viktor Prasanna (Chair), Paul Bogdan, Jyotirmoy Deshmukh, Rajgopal Kannan, Cauligi Raghavendra

Data & Time: April 30, 3:00 PM - 4:00 PM Location: EEB 219

Abstract: As machine learning models are increasingly deployed in critical real-world applications, ensuring their robustness against adversarial attacks is essential to prevent potentially severe consequences. Adversarial training, which involves teaching models to recognize and resist adversarial perturbations, is a key strategy for building such robustness. This thesis explores the enhancement of adversarial robustness in scenarios characterized by low-label regimes, where extensive labeled training data are not accessible, by addressing several challenges in existing semi-supervised adversarial training methods. Specifically, the proposed research focuses on: (1) optimizing the generation of adversarial samples to reduce the risk of overfitting, (2) enhancing the reliability of pseudo-labels to mitigate confirmation bias, and (3) simplifying the optimization of training processes to enhance accessibility and efficiency. These improvements will contribute to strengthening the security and functionality of machine learning applications against adversarial threats in a broader range of applications.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 219
Audiences: Everyone Is Invited

Contact: Ellecia Williams
Apr
30

PhD Thesis Proposal - Nan Xu
Tue, Apr 30, 2024 @ 04:30 PM - 06:30 PM
Thomas Lord Department of Computer Science
University Calendar

Committee Members: Xuezhe Ma (chair), Muhao Chen, Jonathan May, Ram Nevatia, Daniel O’Leary

Title: Decoding Recipes for Coherent and Factual Text Generation

Abstract: While Large language models (LLMs) have demonstrated increasing power in generating texts, they have also called upon studies on their degeneration problems such as repetition, incoherence, hallucination, etc. My PhD thesis outlines my research aiming to tackle these challenges from the perspective of decoding, which is train-free and driven by models' own understanding of seen and generated texts. Specifically, I focus on 1) reducing undesired repetitions and off-topic generations by analyzing probability distribution of decoding steps for open-ended text generation and 2) mitigating hallucinations by studying models' uncertainty against user prompts for false-premise question answering. Motivated by the emergent ability of Large Vision Language Models (LVLMs) to perceive and understand visual signals, I will also introduce my proposal to mitigate hallucinations with effective decoding strategies given multimodal inputs.

Venue: RTH 306 and Zoom https://usc.zoom.us/j/97468606369?pwd=a2ovTlYweE1neGpTMHFtUlNrcVVnQT09

Date: 04/30/2024, 4:30-6:30PM
Location: Ronald Tutor Hall of Engineering (RTH) - 306
Audiences: Everyone Is Invited

Contact: Ellecia Williams
May
01

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
May
01

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
May
01

PhD Thesis Proposal - Ta-Yang Wang
Wed, May 01, 2024 @ 03:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar

Title: Training Heterogeneous Graph Neural Networks using Bandit Sampling

Presenter: Ta-Yang Wang

Time: May 1st, 3:00 PM - 4:00 PM

Location: EEB 219

Committee members: Viktor Prasanna (chair), Jyotirmoy Deshmukh, Rajgopal Kannan, Aiichiro Nakano, and Cauligi Raghavendra

Abstract: Graph neural networks (GNNs) have gained significant attention across diverse areas due to their superior performance in learning graph representations. While GNNs exhibit superior performance compared to other methods, they are primarily designed for homogeneous graphs, where all nodes and edges are of the same type. Training a GNN model for large-scale graphs incurs high computation and storage costs, especially when considering the heterogeneous structural information of each node. To address the demand for efficient GNN training, various sampling methods have been proposed. In this proposal, we hypothesize that one can improve the training efficiency via bandit sampling, an online learning algorithm with provable convergence under weak assumptions on the learning objective. The main idea is to prioritize node types with more informative connections with respect to the learning objective. Additionally, we analyze the limitations of the framework, thus advancing its applicability in large-scale graph learning tasks.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 219
Audiences: Everyone Is Invited

Contact: Ellecia Williams
May
02

Machine Learning Center Seminar
Thu, May 02, 2024 @ 12:00 PM - 01:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars

Speaker: Pengtao Xie , Assistant Professor, Department of Electrical and Computer Engineering - University of California, San Diego

Talk Title: Foundation Models and Generative AI for Medical Imaging Segmentation in Ultra-Low Data Regimes

Abstract: Semantic segmentation of medical images is pivotal in disease diagnosis and treatment planning. While deep learning has excelled in automating this task, a major hurdle is the need for numerous annotated masks, which are resource-intensive to produce due to the required expertise and time. This scenario often leads to ultra-low data regimes where annotated images are scarce, challenging the generalization of deep learning models on test images. To address this, we introduce two complementary approaches. One involves developing foundation models. The other involves generating high-fidelity training data consisting of paired segmentation masks and medical images. In the former, our bi-level optimization based method can effectively adapt the general-domain Segment Anything Model (SAM) to the medical domain with just a few medical images. In the latter, our multi-level optimization based method can perform end-to-end generation of high-quality training data from a minimal number of real images. On eight segmentation tasks involving various diseases, organs, and imaging modalities, our methods demonstrate strong generalization performance in both in-domain and out-of-domain settings. Our methods require 8-12 times less training data than baselines to achieve comparable performance.

Biography: Pengtao Xie is an assistant professor in the Department of Electrical and Computer Engineering at the University of California San Diego. His research interest lies in machine learning for healthcare. His PhD thesis was selected as a top-5 finalist for the Doctoral Dissertation Award of the American Medical Informatics Association (AMIA). He was recognized as Global Top-100 Chinese Young Scholars in Artificial Intelligence by Baidu, Tencent AI-Lab Faculty Award, Innovator Award by the Pittsburgh Business Times, Amazon AWS Machine Learning Research Award, among others. He serves as an associate editor for the ACM Transactions on Computing for Healthcare, senior area chair for AAAI, area chairs for ICML and NeurIPS, etc.

Host: Machine Learning Center

Location: Ronald Tutor Hall of Engineering (RTH) - 211
Audiences: Everyone Is Invited

Contact: Thomas Lord Department of Computer Science
May
02

PhD Thesis Defense - Matthew Ferland
Thu, May 02, 2024 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar

PhD Thesis Defense: Matthew Ferland

Committee: Shanghua Teng (Chair), David Kempe, Jiapeng Zhang, Larry Goldstein (Math)

Title: Exploring the Computational Frontier of Combinatorial Games

Abstract: People have been playing games since before written history, and many of the earliest games were combinatorial games, that is to say, games of perfect information and no chance. This type of game is still widely played today, and many popular games of this type, such as Chess and Go, are some of the most studied games of all time. This proposed work resolves around a game-independent systemic study of these games. More specifically, computational properties involving evaluating mathematical analysis tools for combinatorial games, such as Grundy values and confusion intervals, as well as identifying what can be determined about these games using simple oracle models.
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited

Contact: CS Events
May
03

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

Events Calendar

Select a calendar:

Filter April Events by Event Type:

Events for the 5th week of April

Events for the 5^th week of April