Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model

TL;DR

This paper introduces DDSR, a fuzzy modeling approach for sequential recommendation that captures user behavior randomness using discrete state space diffusion, improving accuracy and efficiency over existing methods.

Contribution

The paper presents a novel diffusion-based fuzzy model for SR that operates in discrete spaces and leverages semantic labels for better performance and cold start handling.

Findings

DDSR outperforms state-of-the-art methods on benchmark datasets.

Using semantic labels enhances efficiency and cold start performance.

The model effectively captures the unpredictability of user behavior.

Abstract

Sequential recommendation (SR) aims to predict items that users may be interested in based on their historical behavior sequences. We revisit SR from a novel information-theoretic perspective and find that conventional sequential modeling methods fail to adequately capture the randomness and unpredictability of user behavior. Inspired by fuzzy information processing theory, this paper introduces the DDSR model, which uses fuzzy sets of interaction sequences to overcome the limitations and better capture the evolution of users' real interests. Formally based on diffusion transition processes in discrete state spaces, which is unlike common diffusion models such as DDPM that operate in continuous domains. It is better suited for discrete data, using structured transitions instead of arbitrary noise introduction to avoid information loss. Additionally, to address the inefficiency of matrix transformations due to the vast discrete space, we use semantic labels derived from quantization or RQ-VAE to replace item IDs, enhancing efficiency and improving cold start issues. Testing on three public benchmark datasets shows that DDSR outperforms existing state-of-the-art methods in various settings, demonstrating its potential and effectiveness in handling SR tasks.