Abstract | ||
---|---|---|
Many techniques to utilize side information of users and/or items as inputs to recommenders to improve recommendation, especially on cold-start items/users, have been developed over the years. In this work, we test the approach of utilizing item side information, specifically categorical attributes, in the output of recommendation models either through multi-task learning or hierarchical classification. We first demonstrate the efficacy of these approaches for both matrix factorization and neural networks with a medium-size real-word data set. We then show that they improve a neural-network based production model in an industrial-scale recommender system. We demonstrate the robustness of the hierarchical classification approach by introducing noise in building the hierarchy. Lastly, we investigate the generalizability of hierarchical classification on a simulated dataset by building two user models in which we can fully control the generative process of user-item interactions.
|
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3240323.3240367 | RecSys '18: Twelfth ACM Conference on Recommender Systems
Vancouver
British Columbia
Canada
October, 2018 |
Keywords | Field | DocType |
recommender systems, hierarchical softmax, hierarchical classification, multi-task learning | Generalizability theory,Recommender system,Data mining,Multi-task learning,Computer science,Categorical variable,Matrix decomposition,Robustness (computer science),Artificial intelligence,Hierarchy,Artificial neural network,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-4503-5901-6 | 2 | 0.38 |
References | Authors | |
12 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qian Zhao | 1 | 70 | 9.66 |
Jilin Chen | 2 | 1142 | 68.37 |
Minmin Chen | 3 | 613 | 42.83 |
Sagar Jain | 4 | 123 | 5.63 |
Alex Beutel | 5 | 917 | 36.48 |
francois belletti | 6 | 51 | 4.99 |
Ed H. Chi | 7 | 4806 | 371.21 |