Comparative Deep Learning of Hybrid Representations for Image Recommendations

TL;DR

This paper introduces a dual-net deep learning model with a comparative training method for improved image recommendation systems, effectively capturing user preferences and image features in a shared semantic space.

Contribution

It proposes a novel dual-net deep network combined with a comparative deep learning approach for hybrid image and user preference representation in recommendations.

Findings

Outperforms existing state-of-the-art image recommendation methods.

Uses more training data effectively without increasing network complexity.

Achieves superior accuracy in real-world image recommendation datasets.

Abstract

In many image-related tasks, learning expressive and discriminative representations of images is essential, and deep learning has been studied for automating the learning of such representations. Some user-centric tasks, such as image recommendations, call for effective representations of not only images but also preferences and intents of users over images. Such representations are termed \emph{hybrid} and addressed via a deep learning approach in this paper. We design a dual-net deep network, in which the two sub-networks map input images and preferences of users into a same latent semantic space, and then the distances between images and users in the latent space are calculated to make decisions. We further propose a comparative deep learning (CDL) method to train the deep network, using a pair of images compared against one user to learn the pattern of their relative distances. The CDL embraces much more training data than naive deep learning, and thus achieves superior performance than the latter, with no cost of increasing network complexity. Experimental results with real-world data sets for image recommendations have shown the proposed dual-net network and CDL greatly outperform other state-of-the-art image recommendation solutions.