Lei Tang

Invited Talks

• Beyond Similarities: Lessons Learned from Recommendation at Walmart, UAI Workshop on New Challenges in eCommerce Product Recommendation, 2013.
• Adaptive User Segmentation for Recommendation, GraphLab Workshop on Large Scale Machine Learning, 2013.
• Community Detection for Social Computing, Social Computing Class @ UC Berkeley, September 2011
• Large Scale Community Detection for Social Computing, with Implementations in Hadoop, SDForum Software Architecture and Platform, February 2011 [slides]
• When Social Meets Advertising: Challenges and Findings in Large-Scale Social Targeting, Arizona State University, December 2010

Tutorial

• SocialCom-2009: Tutorial on Community Detection and Behavior Study for Social Computing

Conferences

• ICDM-2009: Uncovering Groups via Heterogeneous Interaction Analysis
• CIKM-2009: Scalable Learning of Collective Behavior based on Sparse Social Dimensions
• KDD-2009: Relational Learning via Latent Social Dimensions
• IJCAI-2009: On Multiple Kernel Learning with Multiple Labels
• WWW-2009: Large Scale Multi-Label Classification via MetaLabeler
• KDD-2008: Community Evolution in Dynamic Multi-Mode Networks
• KDD-2006: Acclimatizing Taxonomic Semantics for Hierarchical Content Categorization
• ICDM-2005: Bias Analysis in Text Classification for Highly Skewed Data

Seminars (Roughly in reverse chronological order)

• Recommendation, Targeting and Advertising
  • Randomized Matrix Factorization
  • Estimating Ad Effectiveness with Biased Observations
  • Large Scale Classification with Millions of Classes
• Collective Behavior:
  • Predictability of Social Networks
• Community Detection:
  • Community Structure in Large Social and Information Networks (slides borrowed from Michael W. Mahoney)
  • Evolutionary Clustering
  • Community Detection in Social Networks
• Optimization:
  • Convergence of Coordinate Block Descent Method (a.k.a., alternating optimization)
  • Minimization Problem with Smooth Components
• Sampling Methods:
  • Basic Sampling Methods
  • MCMC
  • Slice Sampling
  • Gibbs Sampling for LDA
• Multiple Kernel Learning:
  • Introduction to Multiple Kernel Learning
  • Efficient Multiple Kernel Learning
  • Multiclass Multiple Kernel Learning
  • Learning Nonparametric Kernel Matrices from Pairwise Constraints
• Statistical Learning Techniques
  • Kernel Methods
  • Gaussian Process
  • A Short Introduction to Graphical Models
• Transfer Learning, Multi-Task Learning, Sample Selection Bias and Semi-Supervised Learning
  • Sample Selection Bias
  • A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data
  • Overview of Multi-task Learning
  • Integrating Constraints and Metric Learning in Semi-Supervised Clustering
  • Transfer Learning for Text Categorization
  • Nightmare at Test Time: Robust Learning by Feature Deletion
• Co-Clustering
• HITS: part1, part2

Related Group Presentation Links

• Fall, 2009, Spring 2009, 2008, 2007, 2005-2006, 2004-2005.