HKUBS_Standard_Coloured_Shield_Blue_Text_Logo - 380
  • Global Presence
  • About Us
        • About us about us
        • A Premier Business School in Asia with Global Influence
        • Overview
          • Message from the Dean
          • Vision & Mission
          • Milestones
          • Partnerships & Global Network
          • Beta Gamma Sigma HKU Chapter
          • Rankings & Accreditations
          • Corporate Collaboration
        • Leadership
          • Faculty Management
          • International Advisory Council
        • Our Stories
        • Contact Us
        • Staff Portal
        • Campuses
  • Programmes
        • Programmes programmes
        • Diversified Learning Experience Empowers our Students
        • Undergraduate
        • Masters
          • MAA
          • MAcct
          • MCGRM
          • MEcon
          • MFWM
          • MFin
          • MFFinTech
          • MGM
          • MSAF
          • MSc(BA)
          • MScMktg
          • MWM
        • MBAs & EMBAs
          • MBA
          • IMBA
          • HKU EMBA
        • PhD
        • Executive Education
        • DBA
  • People
        • People people
        • International Faculty Body that Offers Quality Education
        • Faculty
        • Post-Doctoral Fellows
        • Demonstrators/ Teaching Assistants
        • Research Postgraduate Students
        • Administration
  • Research
        • Research research
        • Lead the Frontier of Knowledge Creation
        • Thought Leadership
          • Latest Research Publications
          • HKEJ Column
          • FT Chinese Column
          • In the Media
        • Academic Areas
        • Faculty Members
        • Research Grants
        • Seminars & Conferences
          • Edward K Y Chen Distinguished Lecture Series
        • Research Centres & Institutes
        • Hong Kong Macroeconomics Forecast
        • HKU Knowledge Exchange
        • HKU Scholars Hub
        • Shenzhen Research Institutes
  • Events
  • Media
        • Media media
        • Inspire the Society and Community with Rigorous Insights
        • School News
        • In the Media
        • Press Release
  • Career
        • Career career
        • Fostering Strategic Partnerships and Talent Development
        • Recruit our Talents
        • Student Career Development
        • Career Opportunities
          • Faculty Recruitments
          • HKU Career Site
  • 繁
  • 简
Type To Search
HKUBS_Standard_Coloured_Shield_Blue_Text_Logo - 380
Type To Search
  • Global Presence
  • About Us
        • About us about us
        • A Premier Business School in Asia with Global Influence
        • Overview
          • Message from the Dean
          • Vision & Mission
          • Milestones
          • Partnerships & Global Network
          • Beta Gamma Sigma HKU Chapter
          • Rankings & Accreditations
          • Corporate Collaboration
        • Leadership
          • Faculty Management
          • International Advisory Council
        • Our Stories
        • Contact Us
        • Staff Portal
        • Campuses
  • Programmes
        • Programmes programmes
        • Diversified Learning Experience Empowers our Students
        • Undergraduate
        • Masters
          • MAA
          • MAcct
          • MCGRM
          • MEcon
          • MFWM
          • MFin
          • MFFinTech
          • MGM
          • MSAF
          • MSc(BA)
          • MScMktg
          • MWM
        • MBAs & EMBAs
          • MBA
          • IMBA
          • HKU EMBA
        • PhD
        • Executive Education
        • DBA
  • People
        • People people
        • International Faculty Body that Offers Quality Education
        • Faculty
        • Post-Doctoral Fellows
        • Demonstrators/ Teaching Assistants
        • Research Postgraduate Students
        • Administration
  • Research
        • Research research
        • Lead the Frontier of Knowledge Creation
        • Thought Leadership
          • Latest Research Publications
          • HKEJ Column
          • FT Chinese Column
          • In the Media
        • Academic Areas
        • Faculty Members
        • Research Grants
        • Seminars & Conferences
          • Edward K Y Chen Distinguished Lecture Series
        • Research Centres & Institutes
        • Hong Kong Macroeconomics Forecast
        • HKU Knowledge Exchange
        • HKU Scholars Hub
        • Shenzhen Research Institutes
  • Events
  • Media
        • Media media
        • Inspire the Society and Community with Rigorous Insights
        • School News
        • In the Media
        • Press Release
  • Career
        • Career career
        • Fostering Strategic Partnerships and Talent Development
        • Recruit our Talents
        • Student Career Development
        • Career Opportunities
          • Faculty Recruitments
          • HKU Career Site
HKUBS_Standard_Coloured_Shield_Blue_Text_Logo - 380
  • Global Presence
  • About Us
    • Overview
      • Message from the Dean
      • Vision & Mission
      • Milestones
      • Partnerships & Global Network
      • Beta Gamma Sigma HKU Chapter
      • Rankings & Accreditations
      • Corporate Collaboration
    • Leadership
      • Faculty Management
      • International Advisory Council
    • Our Stories
    • Contact Us
    • Staff Portal
    • Campuses
  • Programmes
    • Undergraduate
    • Masters
      • MAA
      • MAcct
      • MCGRM
      • MEcon
      • MFWM
      • MFin
      • MFFinTech
      • MGM
      • MSAF
      • MSc(BA)
      • MScMktg
      • MWM
    • MBAs & EMBAs
      • MBA
      • IMBA
      • HKU EMBA
    • DBA
    • PhD
    • Executive Education
  • People
    • Faculty
    • Post-Doctoral Fellows
    • Demonstrators/ Teaching Assistants
    • Research Postgraduate Students
    • Administration
  • Research
    • Thought Leadership
      • Latest Research Publications
      • HKEJ Column
      • FT Chinese Column
      • In the Media
    • Academic Areas
    • Faculty Members
    • Research Grants
    • Seminars & Conferences
      • Edward K Y Chen Distinguished Lecture Series
    • Research Centres & Institutes
    • Hong Kong Macroeconomics Forecast
    • HKU Knowledge Exchange
    • HKU Scholars Hub
    • Shenzhen Research Institutes
  • Events
  • Media
    • School News
    • In the Media
    • Press Release
  • Career
    • Recruit our Talents
    • Student Career Development
    • Career Opportunities
      • Faculty Recruitments
      • HKU Career Site

Events

Home Events
“Learning from Crowdsourced Multi-Labeling: A Variational Bayesian Approach” by Dr. Junming Yin
21Oct
SOB Seminar Calendar, Information and Innovation Management

“Learning from Crowdsourced Multi-Labeling: A Variational Bayesian Approach” by Dr. Junming Yin

Wednesday, 21 October 2020 | 10:30 a.m. — 12:00 noon
online seminar
Share on TwitterShare on FacebookShare on WhatsappShare on LinkedInShare on Email
Speaker:
  • Dr. Junming Yin
    Assistant Professor
    Department of Management Information Systems
    University of Arizona

     

Introduction :

 

Dr. Yin plans to present two studies :

Learning from Crowdsourced Multi-Labeling: A Variational Bayesian Approach

ABSTRACT

Microtask crowdsourcing has emerged as a cost-effective approach for obtaining large-scale labeled data. Crowdsourcing platforms, such as MTurk, provide an online marketplace where task requesters can submit a batch of microtasks for a crowd of workers to complete for a small monetary compensation. As the information collected from a crowd can be prone to errors, additional algorithmic techniques are needed to infer the ground truth labels from noisy annotations by workers with heterogeneous quality. Moreover, it would be very beneficial to identify and possibly filter out low-quality workers to foster the creation of a healthy and sustainable crowdsourcing ecosystem. Much of the existing literature on crowd labeling has focused on the single-label setting. However, in many application domains, it is common that each item to be annotated can be assigned to multiple categories simultaneously. In this paper, we present a variety of new approaches for modeling label dependency and worker quality in the context of multi-label crowdsourcing. To capture label dependency, we introduce three methods based on a Bayesian mixture of Bernoulli distributions, its Dirichlet process extension, and a multivariate logit-normal distribution. We also propose two distinct generative models for characterizing shared and hierarchical structures of worker quality. Efficient collapsed and Laplace variational inference algorithms are then developed to jointly infer ground truth labels and worker quality. Extensive simulation and MTurk experiments show that the models based on integrating Bernoulli mixtures and shared structure of worker quality achieve a significant improvement over other state-of-the-art methods. Our study clearly highlights that joint and effective modeling of label dependency and worker quality is crucial to the design of a multi-label crowdsourcing system. The proposed framework also has great potential to be extended to a broader range of applications, in which different opinions need to be combined to measure multiple perspectives of an object.

Relaxed Multivariate Bernoulli Distribution and Its Applications to Deep Generative Models

ABSTRACT

Recent advances in variational auto-encoder (VAE) have demonstrated the possibility of approximating the intractable posterior distribution with a variational distribution parameterized by a neural network. To optimize the variational objective of VAE, the reparameterization trick is commonly applied to obtain a low-variance estimator of the gradient. The main idea of the trick is to express the variational distribution as a differentiable function of parameters and a random variable with a fixed distribution. To extend the reparameterization trick to inference involving discrete latent variables, a common approach is to use a continuous relaxation of the categorical distribution as the approximate posterior. However, when applying continuous relaxation to the multivariate cases, multiple variables are typically assumed to be independent, making it suboptimal in applications where modeling dependency is crucial to the overall performance. In this work, we propose a multivariate generalization of the Relaxed Bernoulli distribution, which can be reparameterized and can capture the correlation between variables via a Gaussian copula. We demonstrate its effectiveness in two tasks: density estimation with Bernoulli VAE and semi-supervised multi-label classification.

Promotions at the Top: The Role of Social Class in Chief Executive Selection20 Oct 2020
"Equity Term Structures without Dividend Strips Data" by Dr. Serhiy KozakWednesday, 21 October 2020
Other Events
214th Congregation (Summer Congregation 2025)
7Jul-8Jul
Faculty Level | Event
214th Congregation (Summer Congregation 2025)
Grand Hall, Centennial Campus, HKU
Semiparametric Identification of the Discount Factor and Payoff Function in Dynamic Discrete Choice Models
Semiparametric Identification of the Discount Factor and Payoff Function in Dynamic Discrete Choice Models
Semiparametric Identification of the Discount Factor and Payoff Function in Dynamic Discrete Choice Models
Semiparametric Identification of the Discount Factor and Payoff Function in Dynamic Discrete Choice Models
Semiparametric Identification of the Discount Factor and Payoff Function in Dynamic Discrete Choice Models
18Jun
Economics | Seminar
Semiparametric Identification of the Discount Factor and Payoff Function in Dynamic Discrete Choice Models
18 June 2025 | 2:15 PM - 3:30 PM
KK 910 K. K. Leung Building, HKU
Prof. Katsumi Shimotsu
“Learning from Crowdsourced Multi-Labeling: A Variational Bayesian Approach” by Dr. Junming Yin
Wednesday, 21 October 202010:30 a.m. — 12:00 noon
online seminar
Sign up for upcoming news and events
LinkedIn WeChat Instagram Facebook Weibo Twitter YouTube

©2025, HKU Business School. All Rights Reserved. | Privacy Policy | Web Accessibility Statement