Select a calendar:
Filter August Events by Event Type:
SUNMONTUEWEDTHUFRISAT
University Calendar
Events for August
-
PhD Thesis Proposal - Minh Pham
Tue, Aug 03, 2021 @ 12:30 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
Date and Time: 12:30 - 2:00 pm
Tuesday, August, 3rd
Committee: Craig Knoblock, Bistra Dilkina, Muhao Chen, Xiang Ren, Gerard Hoberg
Title: Robust and Proactive Error Detection and Correction in Tables
Abstract:
Web Tables serve as a rich source of knowledge that supports many knowledge-driven intelligent applications. However, similar to other online resources, information in Web tables is prone to errors and noise. To that end, data cleaning is an important step in table preprocessing and any untreated errors in tables can be detrimental for applications in later phases. Existing supervised methods in data cleaning depend on obtaining sufficient training data, which requires extensive human involvement, while unsupervised methods rely on fixed inductive biases to solve the problem, which is often not generalizable. In this proposal, we articulate the challenges posed in traditional table data cleaning studies and propose a unified solution to address these issues. The proposed approach uses open-domain question answering to proactively mine evidence from Web text to verify table semantic content. Also, an active learning model is integrated to leverage weakly supervised detectors/correctors for closed-domain robust syntactic error detection and correction. In combination, the unified framework aims to improve the accuracy and reduce human interaction in data cleaning for both syntactic and semantic errors.WebCast Link: https://usc.zoom.us/j/96447577773
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Defense - Kien Nguyen
Mon, Aug 16, 2021 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
Ph.D. Candidate: Kien Nguyen
Time: August 16, 2021, 10am-12
Title: Privacy-Aware Geo-Marketplaces
Committee: Prof. Cyrus Shahabi (chair), Prof. Peter Kuhn, Prof. Bhaskar Krishnamachari, Dr. John Krumm
Abstract:
The advance of modern mobile communication devices has enabled people to easily create, consume, and share geospatial information about every aspect of their lives. However, the current practice of geospatial data collection and sharing is often that individuals provide their data for free in order to use services. However, information about locations of individuals can have serious privacy implications. While there was some regulation of location data collection and sharing, current practice is far from ideal for individuals to safely share their location information to service providers.
An emerging alternative framework for current practice is to allow individuals to offer their location data through data marketplaces. We called these marketplaces geo-marketplaces. Geo-marketplaces raise a number of interesting issues about data ownership, utility, pricing and privacy. In this thesis, we focus on the interplay between utility, privacy and pricing of geospatial data in various settings of geo-marketplaces. More specifically, two important aspects of geo-marketplaces are at the center of interest: location privacy and pricing for various types of location data. Location privacy is essential for geo-marketplaces due to the sensitivity of location data. Pricing is crucial to make geo-marketplace viable, especially when geospatial data can come in many different forms. Thus, geo-marketplaces require efficient algorithms for selling different types of geospatial data with alternative pricing strategies while protecting sellers' location privacy.
This thesis aims to enable geo-marketplaces with those requirements by investigating different settings of data types and pricing strategies in a geo-marketplace along with privacy considerations. These settings include (a) differentially private data point release with free query where some quantities derived from individuals' data points can be released for free with strong privacy protection, (b) encrypted data point release with fixed-price query where location data points or geo-tagged data objects for a fixed price with their locations advertised in encrypted space, (c) noisy data point release with variable price query where a location data point can be sold at different prices depending on how much noise is added, and (d) degraded trajectory release with variable-price query where a trajectory can be released or sold at different prices depending on how it is degraded. In each setting, we design the marketplace and develop principled methods to price data, protect privacy of owners and maintain utility of data for buyers in order to enable a viable geo-marketplace. In all settings, our proposed design and methods are evaluated by extensive experiments on large real-world datasets to show its practicality.
Zoom info:
https://usc.zoom.us/j/93232846112
WebCast Link: https://usc.zoom.us/j/93232846112
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Thesis Proposal - Karishma Sharma
Tue, Aug 24, 2021 @ 11:30 AM - 01:00 PM
Thomas Lord Department of Computer Science
University Calendar
Committee:
Yan Liu, Emilio Ferrara, Barath Raghavan, Fred Morstatter, Kimon Drakopoulos
Date/time:
Aug 24, Tuesday from 11.30 am to 1 pm.
Zoom link:
https://usc.zoom.us/j/98260098182?pwd=cEl4aWRycnZ5L1dLMUdvTHRwczQ4UT09
Title:
Diffusion Network Inference and Analysis for Disinformation Mitigation
Abstract:
The proliferation of false and misleading information on social media has greatly reduced trust in online systems. Disinformation is largely aimed at influencing public opinion and social outcomes, and has been associated with reduced intent towards pro-social behaviors, denial of science and truth, and increased prejudices. In this thesis proposal, we address challenges in disinformation mitigation leveraging the content propagation or diffusion dynamics of disinformation on social media, through diffusion network analysis and inference techniques.
We propose techniques for early detection of disinformation contents, with a conditional generative model of social media responses to the content, leveraging historical responses to enrich semantic understanding of why content is labeled as disinformation. Secondly, we investigate how disinformation spreads and propose an unsupervised, generative model for detection of ma- licious coordinated efforts in the spread of disinformation, by inferring latent influence between accounts and collective group anomalous behaviors from observed account activities. Besides detection, we address challenges in network interventions to limit disinformation propagation and prevent viral cascades, by inferring diffusion dynamics of disinformation and legitimate contents from observed, unlabeled cascades with a mixture model of diffusion.
In the proposed future work, we focus on characterizing engagement with disinformation and conspiracy groups on social media. In the U.S. Election, we will evaluate whether Twitter's restriction on the QAnon conspiracy group was effective in limiting its activities with a regression discontinuity design for estimating causal effects of Twitter's intervention. In addition, to address the critical challenges in disinformation labeling, we propose to study methods in uncertainty sampling for active label refinement of social media posts, weakly-labeled based on news source credibility, towards building large-scale disinformation datasets, minimizing expensive human fact-checking efforts to collect disinformation labels. The outcome of this thesis proposal is to improve mitigation techniques and characterization of disinformation for timely identification and containment and to inform the need for robust platform measures.WebCast Link: https://usc.zoom.us/j/98260098182?pwd=cEl4aWRycnZ5L1dLMUdvTHRwczQ4UT09
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
