A Correlation Maximization Approach for Cross Domain Co-Embeddings
This addresses the cold-start problem in recommendation systems, providing a practical solution for new user sign-ups, though it appears incremental as it builds on existing embedding and correlation techniques.
The paper tackles the cold-start problem in recommendation systems for new users by introducing ImplicitCE, an algorithm that transforms implicit feedback from auxiliary domains into target domain embeddings, and shows it outperforms state-of-the-art methods on Twitter and DBLP datasets.
Although modern recommendation systems can exploit the structure in users' item feedback, most are powerless in the face of new users who provide no structure for them to exploit. In this paper we introduce ImplicitCE, an algorithm for recommending items to new users during their sign-up flow. ImplicitCE works by transforming users' implicit feedback towards auxiliary domain items into an embedding in the target domain item embedding space. ImplicitCE learns these embedding spaces and transformation function in an end-to-end fashion and can co-embed users and items with any differentiable similarity function. To train ImplicitCE we explore methods for maximizing the correlations between model predictions and users' affinities and introduce Sample Correlation Update, a novel and extremely simple training strategy. Finally, we show that ImplicitCE trained with Sample Correlation Update outperforms a variety of state of the art algorithms and loss functions on both a large scale Twitter dataset and the DBLP dataset.