FELRec: Efficient Handling of Item Cold-Start With Dynamic Representation Learning in Recommender Systems

TL;DR

FELRec introduces a dynamic, weight-free embedding storage for sequential recommender systems that effectively addresses item cold-start without side information or finetuning, outperforming existing methods significantly.

Contribution

The paper presents FELRec, a novel recursive embedding refinement approach that handles item cold-start efficiently without additional side information or training.

Findings

Outperforms similar methods by 29.50%-47.45% during item cold-start

Generalizes well to unseen datasets in zero-shot settings

Operates with a single forward pass over existing representations

Abstract

Recommender systems suffer from the cold-start problem whenever a new user joins the platform or a new item is added to the catalog. To address item cold-start, we propose to replace the embedding layer in sequential recommenders with a dynamic storage that has no learnable weights and can keep an arbitrary number of representations. In this paper, we present FELRec, a large embedding network that refines the existing representations of users and items in a recursive manner, as new information becomes available. In contrast to similar approaches, our model represents new users and items without side information and time-consuming finetuning, instead it runs a single forward pass over a sequence of existing representations. During item cold-start, our method outperforms similar method by 29.50%-47.45%. Further, our proposed model generalizes well to previously unseen datasets in zero-shot settings. The source code is publicly available at https://github.com/kweimann/FELRec .