Simultaneous Learning of the Inputs and Parameters in Neural Collaborative Filtering

TL;DR

This paper introduces a method to jointly learn input values and neural network parameters in collaborative filtering, enhancing model flexibility and performance over fixed-input approaches.

Contribution

It proposes a novel approach to learn the non-zero input elements alongside network parameters, improving generalization and recommendation accuracy.

Findings

Outperforms state-of-the-art methods on real-world datasets

Achieves better generalization bounds with input learning

Requires shallower networks with fewer parameters

Abstract

Neural network-based collaborative filtering systems focus on designing network architectures to learn better representations while fixing the input to the user/item interaction vectors and/or ID. In this paper, we first show that the non-zero elements of the inputs are learnable parameters that determine the weights in combining the user/item embeddings, and fixing them limits the power of the models in learning the representations. Then, we propose to learn the value of the non-zero elements of the inputs jointly with the neural network parameters. We analyze the model complexity and the empirical risk of our approach and prove that learning the input leads to a better generalization bound. Our experiments on several real-world datasets show that our method outperforms the state-of-the-art methods, even using shallow network structures with a smaller number of layers and parameters.