Latent semantic indexing: a probabilistic analysis
PODS '98 Proceedings of the seventeenth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
Analysis of recommendation algorithms for e-commerce
Proceedings of the 2nd ACM conference on Electronic commerce
STOC '01 Proceedings of the thirty-third annual ACM symposium on Theory of computing
Competitive recommendation systems
STOC '02 Proceedings of the thiry-fourth annual ACM symposium on Theory of computing
Eigentaste: A Constant Time Collaborative Filtering Algorithm
Information Retrieval
Convergent algorithms for collaborative filtering
Proceedings of the 4th ACM conference on Electronic commerce
Recommendation Systems: A Probabilistic Analysis
FOCS '98 Proceedings of the 39th Annual Symposium on Foundations of Computer Science
Improved recommendation systems
SODA '05 Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms
Collaborate with strangers to find own preferences
Proceedings of the seventeenth annual ACM symposium on Parallelism in algorithms and architectures
Tell me who I am: an interactive recommendation system
Proceedings of the eighteenth annual ACM symposium on Parallelism in algorithms and architectures
Finding similar users in social networks: extended abstract
Proceedings of the twenty-first annual symposium on Parallelism in algorithms and architectures
Anatomy of the long tail: ordinary people with extraordinary tastes
Proceedings of the third ACM international conference on Web search and data mining
Asynchronous active recommendation systems
OPODIS'07 Proceedings of the 11th international conference on Principles of distributed systems
Collaborative scoring with dishonest participants
Proceedings of the twenty-second annual ACM symposium on Parallelism in algorithms and architectures
Recommender systems with non-binary grades
Proceedings of the twenty-third annual ACM symposium on Parallelism in algorithms and architectures
Hi-index | 0.00 |
We consider the interactive model of collaborative filtering, where each member of a given set of users has a grade for each object in a given set of objects. The users do not know the grades at start, but a user can probe any object, thereby learning her grade for that object directly. We describe reconstruction algorithms which generate good estimates of all user grades ("preference vectors") using only few probes. To this end, the outcomes of probes are posted on some public "billboard", allowing users to adopt results of probes executed by others. We give two new algorithms for this task under very general assumptions on user preferences: both improve the best known query complexity for reconstruction, and one improving resilience in the presence of many users with esoteric taste.