# TransNets: Learning to Transform for Recommendation

## TL;DR

TransNets is a deep learning model that improves recommendation accuracy by effectively utilizing review text, even when the target user's review for the item is unavailable, by learning a latent representation of user-item pairs.

## Contribution

The paper introduces TransNets, a novel neural network architecture that extends DeepCoNN to better leverage review data and handle missing user reviews in recommendation tasks.

## Key findings

- TransNets outperform DeepCoNN and other baselines.
- Regularizing the user-item pair representation improves recommendation accuracy.
- The model effectively predicts preferences without requiring the target user's review at test time.

## Abstract

Recently, deep learning methods have been shown to improve the performance of recommender systems over traditional methods, especially when review text is available. For example, a recent model, DeepCoNN, uses neural nets to learn one latent representation for the text of all reviews written by a target user, and a second latent representation for the text of all reviews for a target item, and then combines these latent representations to obtain state-of-the-art performance on recommendation tasks. We show that (unsurprisingly) much of the predictive value of review text comes from reviews of the target user for the target item. We then introduce a way in which this information can be used in recommendation, even when the target user's review for the target item is not available. Our model, called TransNets, extends the DeepCoNN model by introducing an additional latent layer representing the target user-target item pair. We then regularize this layer, at training time, to be similar to another latent representation of the target user's review of the target item. We show that TransNets and extensions of it improve substantially over the previous state-of-the-art.