The Data Science Lab
since 2005
  • Home
  • Research
      • Research grants
      • Research interests
      • Research leadership
      • Student theses
      • Humanoid Ameca
      • AI Server
        • GPU
        • Request
        • Allocation
  • Consultancy
      • Consulting projects
      • Cooperate training
      • Enterprise innovation
      • Impact cases
      • Our clients
      • Partnership
  • People
      • Awards and honors
      • Staff
      • Team members
  • Activities
      • Events and services
      • Talks
      • Tutorials
      • Workshops
  • Publications
  • Communities
      • ACM ANZKDD Chapter
      • Big data summit
      • Data Analytics book series
      • DSAA conferences
      • IEEE TF-DSAA
      • IEEE TF-BESC
      • JDSA Springer
      • DataSciences.Info
      • MQ's DSAI
  • Resources
      • Actionable knowledge discovery
      • Agent mining
      • AI: Artificial-intelligence
      • AI4Tech: AI enabling technologies
      • AI4Finance: AI for FinTech
      • AI robots & humanoid AI
      • Algorithmic trading
      • Banking analytics
      • Behavior analytics, computing, informatics
      • Coupling and interaction learning
      • COVID-19 global research and modeling
      • Data science knowledge map
      • Data science dictionary
      • Data science terms
      • Data science tools
      • Data science thinking
      • Domain driven data mining
      • Educational data mining
      • Large-scale statistical learning
      • Metasynthetic engineering
      • Market surveillance
      • Negative Sequence Analysis
      • Non-IID Learning
      • Pattern relation analysis
      • Recommender systems
      • Smart beach analytics
      • Social security analytics
      • Tax analytics
  • About us
Qi Zhang won the first place of School’s research showcase

Our PhD student Qi Zhang won the first place in the School of Computer Science’s HDR student showcase. His poster title is Context-aware Convolutional Recommendation Network for Modeling Preference Dynamics and Explicit Feature Relations. In this poster, he reported his research on the proposed Context-aware cOnvolutional Recommendation Network (CORN) to model user preference and its dynamics and considering contextual factors simultaneously for precise recommendation. The model captures (1) feature relation-based user’s preference by latent interaction layers, and (2) user’s preference dynamics within a context by convolutional layers. He will represent the School to attend the Faculty’s HDR student showcases.

About us
School of Computing, Faculty of Science and Engineering, Macquarie University, Australia
Level 3, 4 Research Park Drive, Macquarie University, NSW 2109, Australia
Tel: +61-2-9850 9583
Staff: firstname.surname(a)mq.edu.au
Students: firstname.surname(a)student.mq.edu.au
Contacts@datasciences.org