Learning to Rank for Recommender Systems - ACM RecSys 2013 tutorial
1. 1 RecSys ’13, Hong Kong, China, Oct. 12, 2013 Learning to Rank for Recommender Systems Alexandros Karatzogloua , Linas Baltrunasa, Yue Shib aTelefonica Research, Spain bDelft University of Technology, Netherlands 2. 2 RecSys ’13, Hong Kong, China, Oct. 12, 2013 Who are we? Alexandros, Linas Yue •  Machine Learning •  Recommender Systems •  Data Mining, Social Networks •  Multimedia Indexing & A
Matrix Factorization 㧠Bayesian Personalized Ranking を用ã„㟠implicit feedback ã®æŽ¨å®šã¯ã†ã¾ãã„ã£ãŸ - 糞糞糞ãƒãƒƒãƒˆå¼æ…¶
Factorization Machines 㧠Bayesian Personalized Ranking を用ã„㟠implicit feedback ã®æŽ¨å®šã‚’è¡Œã„ãŸã‹ã£ãŸã‘ã©ã†ã¾ãã„ã‹ãªã‹ã£ãŸ - 糞ãƒãƒƒãƒˆå¼æ…¶ã®ç¶šã． è¦ç´„ Bayesian Personalized Ranking ãŒè«¦ã‚られãªã„ pairwise 㪠loss を考慮ã—㟠Matrix Factorization 㧠MovieLens 100K ã‚’å¦ç¿’・予測ã™ã‚‹ã¨ AUC ㌠0.8 程度を示ã—㟠手法 Matrix Factorization 㯠ユーザ u \in U ã¨ã‚¢ã‚¤ãƒ†ãƒ i \in I を行列 X ã§è¡¨ã—，X ã‚’ 2 ã¤ã®å¯†è¡Œåˆ—ã«åˆ†è§£ X \approx H W^T ã«åˆ†è§£ã™ã‚‹æ‰‹æ³•ï¼Ž 通常ã¯åˆ†è§£å¾Œã®è¡Œåˆ—ã®ç©ã‚’推定値ã¨ã—，観測値ã¨ã®èª¤å·®ã‚’最å°åŒ–ã™ã‚‹ã‚ˆã†ã«åˆ†è§£å¾Œã®è¡Œåˆ—ã®å€¤ã‚’æ›´æ–°ã™ã‚‹ãŒï¼Œä»Šå›žã¯ BPR
1
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
処ç†ã‚’実行ä¸ã§ã™
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
{{#tags}}- {{label}}
{{/tags}}