CSE 291: Trends in Recommender Systems and Human Behavioral Modeling

Instructor: Julian McAuley (jmcauley@eng.ucsd.edu), CSE 4102

Autumn 2017, Monday/Wednesday 9:30-10:50, CSE 4140

CSE 291 is a graduate course devoted to current trends for recommender systems and models of human behavior. This course covers material similar to CSE 258, though is more focused on research papers and student-led presentations. It is suggested (but not required) that you have already taken CSE 258 or are taking it concurrently, though the first 1-2 lectures will be spent on revision.

The course meets twice a week on Monday/Wednesday mornings, starting October 2. Meetings are in CSE 4140. Attendance is expected, as grades are primarily based on participation.

Office hours: I'll hold office hours on Tuesdays 9:00-13:00 in CSE 4102.


piazza page
assignment spec (50% of grade)
in-class presentations (50% of grade)example disscussion questions
1

Background

Monday October 2: Matrix Factorization
Wednesday October 4: Item-to-Item Recommendation
Suggested reading:
course outline slides
2

Ranking, Retrieval, & Sequential Recommendation

Monday October 9: Markov-Chains
Wednesday October 11: More Markov Chains, and Metric Learning
Suggested reading:
assignment slidesdiscussion qs
3

Temporal Dynamics

Monday, October 16:
Wednesday, October 18:
Suggested reading:
sign-up sheetslide deckdiscussion qs
4

Deep and Content-Aware

Monday, October 23:
Wednesday, October 25:
Suggested reading:
sign-up sheetslide deckdiscussion qs
5

Text and Question-Answering Systems

Suggested reading:
sign-up sheetslide deckdiscussion qs
6

Project Proposals

7

Novel Tasks & Domains

Suggested reading:
8

Socially & Geographically Aware Models

Suggested reading:
9

Human-subject experiments, evaluation, and deployment

Suggested reading:
10

Project Presentations (if there's time...)