DropoutNet: Addressing Cold Start in Recommender Systems
著者
Abstract
Latent models have become the default choice for recommender systems due to their performance and scalability. However, research in this area has primarily fo-cused on modeling user-item interactions, and few latent models have been devel-oped for cold start. Deep learning has recently achieved remarkable success show-ing excellent results for diverse input types. Inspired by these results we propose a neural network based latent model called DropoutNet to address the cold start problem in recommender systems. Unlike existing approaches that incorporate ad-ditional content-based objective terms, we instead focus on the optimization and show that neural network models can be explicitly trained for cold start through dropout. Our model can be applied on top of any existing latent model effectively providing cold start capabilities, and full power of deep architectures. Empirically we demonstrate state-of-the-art accuracy on publicly available benchmarks. Code is available at https://github.com/layer6ai-labs/DropoutNet メモ
提案手法
コールドスタート問題をデータの欠損の問題とみなす
モデルに追加の項を入れるのではなく、学習の手続きを修正し、明示的な条件として欠損の入力を行う
主要なアイディアの背後にあるのはドロップアウトを入力のミニバッチに適用することにある
適した量のドロップアウトを選択することでwarm startでstate-of-the-artなDNNベースの潜在変数学習モデルが、、cold startでもパフォーマンスすることを示す
https://gyazo.com/dc6cba37193498937a3673c4f7122559