Event Archive

Mining Semantic Patterns from Text

Master's Defense
Speaker Name
Xiaoming Liu
Location
Talk will be virtual on Zoom
Date and Time
-

In this project we study the problem of extracting semantic patterns from sentences to assist with several text analysis tasks, such as identifying checkworthy claims from text and parsing such claims into representations amenable to automatic fact-checking. We leverage NLP tools to parse each sentence into a tree presentation, and replace each specific token with appropriate, more general labels useful for identifying their semantic roles. Substructures in this parse tree serve as our patterns of interest.

Evaluating Robustness of Neural Networks

Duke Computer Science Colloquium
Speaker Name
Lily Weng
Location
Talk will be virtual on Zoom
Date and Time
-

Evaluating Robustness of Neural Networks

 

Link to talk video:  https://compsci.capture.duke.edu/Panopto/Pages/Viewer.aspx?id=f8b8abac-e471-4b79-826d-ab9001221efe

Artificial Intelligence for the Understanding of Large Complex Datacenters

Ph. D. Defense
Speaker Name
Pengfei Zheng
Location
Talk will be virtual on Zoom
Date and Time
-

Advances in monitoring, tracing, and profiling large, complex datacenters produce rich datasets and establish a rigorous foundation for understanding datacenter performance. But the sheer volume and complexity of the data challenges existing techniques, which rely heavily on expert knowledge, human intervention, and simple statistics to gain performance insights.

Dynamic Mechanism Design in Complex Environments

Ph. D. Defense
Speaker Name
Yuan Deng
Location
Zoom Link: https://duke.zoom.us/j/409973318
Date and Time
-

Inspired by various applications including ad auctions, matching markets, and voting, mechanism design deals with the problem of designing algorithms that take inputs from strategic agents and return an outcome optimizing a given objective.

Improving System Availability for Better Services

Ph. D. Defense
Speaker Name
Zhenyu Zhou
Location
Talk will be virtual on Zoom
Date and Time
-

Entering the information age, the demands for online services increase dramatically. Such high demands are pushing the network systems to become more complex and making system availability a crucial requirement for both service providers and clients. The service providers are aiming to have an effective, efficient and stable service: the service should be failure resilient, be scalable to support a large group of clients and still keep acceptable performance. Whereas the clients need a “powerful” service – high performance without threats to their privacy or security.

Topological and Geometric Methods for Graph Analysis

Duke Computer Science Colloquium
Speaker Name
Yusu Wang
Location
Talk will be virtual on Zoom
Date and Time
-
In this talk, I will show how topological and geometric ideas can be used to analyze graph data, which occurs ubiquitously across science and engineering. I will particularly focus on the reconstruction of hidden geometric graphs from noisy data, as well as graph matching and classification. I will discuss the motivating applications, algorithm development, and theoretical guarantees for these methods. Through these topics, I aim to illustrate the important role that geometric and topological ideas can play in data analysis.

Cold-Start Universal Information Extraction

Duke Computer Science Colloquium
Speaker Name
Lifu Huang
Location
Talk will be virtual on Zoom
Date and Time
-
In this talk, I will introduce a new information extraction paradigm - Cold-Start Universal Information Extraction, which aims to create the next generation of information access where machines can automatically discover accurate, concise, and trustworthy information embedded in data of any form without requiring any human effort.

Leveraging Cross-Website Coordination to Mitigate Credential Stuffing

Duke Computer Science/Electrical Computer Engineering Colloquium
Speaker Name
Michael Reiter
Location
Talk will be virtual on Zoom
Date and Time
-

Link to talk video:  https://compsci.capture.duke.edu/Panopto/Pages/Viewer.aspx?id=a2282dc2-1e77-44d2-a1c0-ab88012e371e

Towards Structured-Infused and Disentangled Representation Learning

Duke Computer Science Colloquium
Speaker Name
Xuezhe Ma
Location
Talk will be virtual on Zoom
Date and Time
-
In this talk, I will present two of our recent work. First, I will introduce how to encode structured dependencies into learned representations to achieve efficient non-autoregressive machine translation models. Second, I will present our work on learning representations to decouple global and local information from/for image generation. I will conclude by laying out future research directions towards interpretable and controllable representation learning.

Distributive Justice for Machine Learning: An Interdisciplinary Perspective on Defining, Measuring, and Mitigating Algorithmic Unfairness

Duke Computer Science Colloquium
Speaker Name
Hoda Heidari
Location
Talk will be virtual on Zoom
Date and Time
-
In this talk, I will illustrate how we can bring together tools and methods from computer science, economics, and political philosophy to define, measure, and mitigate algorithmic unfairness. In particular, I will address two key questions: Given the decision-making context, how should we define fairness as the equality of some notion of benefit or harm across socially salient groups? How can we measure unfairness (both at the individual and group level) and bound it in a computationally efficient manner?

Programming DNA for Molecular-scale Temporal Barcoding and Enzymatic Computation

Ph. D. Defense
Speaker Name
Shalin Shah
Location
Hudson Hall 132
Date and Time
-

DNA, the blueprint of life, is more than a carrier of genetic information. It offers a highly programmable substrate that can be used for computing, nanorobotics, and advanced imaging techniques. In this work, we use the programmable nature of synthetic DNA to engineer two novel applications. In the first part, DNA is programmed to improve the multiplexing capabilities of a fluorescence microscope while in the second part, we design a novel DNA computing architecture that using a strand displacing polymerase enzyme.

Connecting Blockchains to the Real World

Duke Computer Science/Electrical Computer Engineering Colloquium
Speaker Name
Fan Zhang
Location
Talk will be virtual on Zoom
Date and Time
-
My research is in applied cryptography and system security. In this talk, I’ll start with my work on data oracles that enable the faithful representation of real-world states on blockchains. Then I’ll present Ekiden, a system that endows smart contracts with privacy by storing secrets and performing computation in off-chain committees. Finally, I’ll discuss future plans for leveraging systems I developed to enable secure systems that empower and protect their users from insecure and centralized infrastructure.

Reuse-Centric Programming System Support of Machine Learning

Duke Computer Science Colloquium
Speaker Name
Hui Guan
Location
Talk will be virtual at https://duke.zoom.us/j/847552551
Date and Time
-

Modern machine learning, especially deep learning, faces a fundamental question: how to create models that efficiently deliver reliable predictions to meet the requirements of diverse applications running on various systems. This talk will introduce reuse-centric optimization, a novel direction for addressing the fundamental question. Reuse-centric optimization centers around harnessing reuse opportunities for enhancing computing efficiency. It generalizes the principle to a higher level and a larger scope through a synergy between programming systems and machine learning algorithms.

Causal Inference & Graphical Models: From Missing Data to the Future of Artificial Intelligence

Duke Computer Science Colloquium
Speaker Name
Karthika Mohan
Location
LSRC D106
Date and Time
-
The remarkable progress in AI and machine learning owe much to the availability of massive amounts of data, and where there is data, there is missingness. I address these deficiencies by using a graphical representation called "Missingness Graph" which portrays the causal mechanisms responsible for missingness. Viewing the missing data problem from a causal perspective has ushered in several notable surprises.

Improving Network Security with Low-Cost and Easy-to-Adopt Solutions

Ph. D. Defense
Speaker Name
Shengbao Zheng
Location
North 311
Date and Time
-

According to statistics, there are over 80,000 cyberattacks per day or over 30 million attacks per year. To make the Internet safe, both the industry and academia propose many solutions. However, these security solutions mainly concentrate on being effective, and ignore the other two features: deployment cost and usability. Therefore, though many works have been proposed to improve security, attacks still happen frequently.

Enabling Future-Proof Telemetry for Networked Systems

Duke Electrical Computer Engineering Colloquium
Speaker Name
Alan (Zaoxing) Liu
Location
Gross Hall 318
Date and Time
-
In this talk, I will present my research that focuses on building telemetry systems that are future-proof for current and new telemetry tasks, diverse workloads, and heterogeneous platforms. I will discuss the efficient algorithms and implementations that realize this future-proof vision in network monitoring for hardware and software platforms.

Towards Language Technology for Everyone

Duke Computer Science Colloquium
Speaker Name
Antonios Anastasopoulos
Location
LSRC D106
Date and Time
-
In this talk, I will focus on a sample of research threads towards the goal of building NLP that serves everyone. First, I'll describe work that is tailored to creating NLP tools for endangered language documentation, with neural models that take advantage of additional signals (in this case translations) in multi-source and multi-task settings. Second, I'll show how similarities across languages can be leveraged for building more accurate morphological inflection systems in numerous under-resourced languages, along with data augmentation through hallucination. Last, I will suggest several directions for future research.

Two Research Stories

Triangle Computer Science Distinguished Lecturer Series
Speaker Name
Martin Rinard
Location
LSRC D106
Date and Time
-

Martin Rinard will present the stories of two research projects. The failure-oblivious computing project developed techniques for keeping systems running and delivering useful results to their users in the face of otherwise fatal errors or security vulnerabilities. The loop perforation project developed techniques for improving performance at the cost of small accuracy losses. Both projects provided new insights into the fundamental empirical resilience of existing software systems.

Gromov-Wasserstein Learning: A New Machine Learning Framework for Structured Data Analysis

Duke Computer Science/Biostatistics & Bioinformatics Colloquium
Speaker Name
Hongteng Xu
Location
LSRC D106
Date and Time
-
In this talk, I will introduce a novel machine learning framework called Gromov-Wasserstein Learning (GWL) — a new systematic solution I proposed for structured data analysis. First, I will introduce the theoretical fundamentals of GWL and link it to learning tasks from structured data. Next, I will describe the optimization algorithms in the GWL, analyzing their convergence, computational complexity, and scalability in detail. Finally, I will show that the GWL unifies graph matching, partitioning, and representation into the same algorithmic framework, which outperforms existing methods on PPI network analysis and molecule clustering and classification.

Cross-Layering in Future Wireless Networks: From Compact Full-duplex Radios to City-Scale Experimentation

Duke Electrical Computer Engineering Colloquium
Speaker Name
Tingjun Chen
Location
Hudson Hall 208
Date and Time
-
In this talk, I will first describe our design and optimization of compact single-antenna full-duplex radios which are suitable for hand-held devices. I will then present a novel approach to enable full-duplex operation in multi-antenna systems by repurposing beamforming degrees of freedom to achieve both wideband self-interference cancellation and improved data rate gain.