Abstract | ||
---|---|---|
Matrix factorization (MF) is one of the most popular techniques for product recommendation, but is known to suffer from serious cold-start problems. Item cold-start problems are particularly acute in settings such as Tweet recommendation where new items arrive continuously. In this paper, we present a meta-learning strategy to address item cold-start when new items arrive continuously. We propose two deep neural network architectures that implement our meta-learning strategy. The first architecture learns a linear classifier whose weights are determined by the item history while the second architecture learns a neural network whose biases are instead adjusted. We evaluate our techniques on the real-world problem of Tweet recommendation. On production data at Twitter, we demonstrate that our proposed techniques significantly beat the MF baseline and also outperform production models for Tweet recommendation. |
Year | Venue | Field |
---|---|---|
2017 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017) | Architecture,Learning theory,Computer science,Matrix decomposition,Artificial intelligence,Linear classifier,Artificial neural network,Cold start (automotive),Machine learning |
DocType | Volume | ISSN |
Conference | 30 | 1049-5258 |
Citations | PageRank | References |
9 | 0.53 | 20 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Manasi Vartak | 1 | 139 | 11.02 |
Thiagarajan, Arvind | 2 | 9 | 0.53 |
Miranda, Conrado | 3 | 9 | 0.53 |
Bratman, Jeshua | 4 | 9 | 0.53 |
Hugo Larochelle | 5 | 7692 | 488.99 |