Implicit ZCA Whitening Effects of Linear Autoencoders for Recommendation
This work addresses improving item similarity estimation in recommendation systems, but it appears incremental as it builds on existing linear models and whitening techniques.
The paper connects linear autoencoders to ZCA whitening for recommendation systems, showing that the dual solution applies whitening to item features, and validates this with preliminary experiments on low-dimensional embeddings.
Recently, in the field of recommendation systems, linear regression (autoencoder) models have been investigated as a way to learn item similarity. In this paper, we show a connection between a linear autoencoder model and ZCA whitening for recommendation data. In particular, we show that the dual form solution of a linear autoencoder model actually has ZCA whitening effects on feature vectors of items, while items are considered as input features in the primal problem of the autoencoder/regression model. We also show the correctness of applying a linear autoencoder to low-dimensional item vectors obtained using embedding methods such as Item2vec to estimate item-item similarities. Our experiments provide preliminary results indicating the effectiveness of whitening low-dimensional item embeddings.