Exploiting Preferences in Loss Functions for Sequential Recommendation via Weak Transitivity

TL;DR

This paper introduces a novel loss function for sequential recommendation systems that explicitly models varying preferences among unobserved items, improving recommendation accuracy by leveraging relative orderings.

Contribution

It proposes a new loss function that incorporates preference structures among items, extending traditional binary-labeled objectives in recommender systems.

Findings

Superior performance over baseline objectives

Effective modeling of preference structures

Enhanced recommendation accuracy

Abstract

A choice of optimization objective is immensely pivotal in the design of a recommender system as it affects the general modeling process of a user's intent from previous interactions. Existing approaches mainly adhere to three categories of loss functions: pairwise, pointwise, and setwise loss functions. Despite their effectiveness, a critical and common drawback of such objectives is viewing the next observed item as a unique positive while considering all remaining items equally negative. Such a binary label assignment is generally limited to assuring a higher recommendation score of the positive item, neglecting potential structures induced by varying preferences between other unobserved items. To alleviate this issue, we propose a novel method that extends original objectives to explicitly leverage the different levels of preferences as relative orders between their scores. Finally, we demonstrate the superior performance of our method compared to baseline objectives.