TimeKit: A Time-series Forecasting-based Upgrade Kit for Collaborative Filtering

TL;DR

TimeKit introduces a novel approach to enhance collaborative filtering recommender systems by forecasting user/item embeddings over time using neural controlled differential equations, leading to improved recommendation accuracy.

Contribution

It proposes a time-series forecasting upgrade kit that integrates neural controlled differential equations into collaborative filtering to better handle temporal dynamics.

Findings

Significantly improves existing collaborative filtering algorithms.

Effective in real-world benchmark datasets.

Enhances recommendation accuracy through temporal embedding forecasting.

Abstract

Recommender systems are a long-standing research problem in data mining and machine learning. They are incremental in nature, as new user-item interaction logs arrive. In real-world applications, we need to periodically train a collaborative filtering algorithm to extract user/item embedding vectors and therefore, a time-series of embedding vectors can be naturally defined. We present a time-series forecasting-based upgrade kit (TimeKit), which works in the following way: it i) first decides a base collaborative filtering algorithm, ii) extracts user/item embedding vectors with the base algorithm from user-item interaction logs incrementally, e.g., every month, iii) trains our time-series forecasting model with the extracted time-series of embedding vectors, and then iv) forecasts the future embedding vectors and recommend with their dot-product scores owing to a recent breakthrough in processing complicated time-series data, i.e., neural controlled differential equations (NCDEs). Our experiments with four real-world benchmark datasets show that the proposed time-series forecasting-based upgrade kit can significantly enhance existing popular collaborative filtering algorithms.