Metadata Embeddings for User and Item Cold-start Recommendations

Code

• github.com/lyst/lightfm
  OfficialIn papernone★ 5,068
• github.com/lyst/lightfm-paper
  OfficialIn papernone★ 0
• github.com/doheelab/lightfm_experiment
  none★ 0
• github.com/mfumagalli68/lightFM
  none★ 0

Abstract

I present a hybrid matrix factorisation model representing users and items as linear combinations of their content features' latent factors. The model outperforms both collaborative and content-based models in cold-start or sparse interaction data scenarios (using both user and item metadata), and performs at least as well as a pure collaborative matrix factorisation model where interaction data is abundant. Additionally, feature embeddings produced by the model encode semantic information in a way reminiscent of word embedding approaches, making them useful for a range of related tasks such as tag recommendations.

Tasks

Reproductions