Disentangling ID and Modality Effects for Session-based Recommendation

TL;DR

This paper introduces DIMO, a novel framework that disentangles ID and modality effects in session-based recommendation to improve accuracy and explainability, using causal inference and self-supervised learning.

Contribution

DIMO explicitly separates ID and modality effects at item and session levels, enabling more accurate and explainable recommendations without supervised signals.

Findings

DIMO outperforms existing methods on multiple datasets.

DIMO effectively generates explanations for recommendations.

Disentanglement improves recommendation accuracy and interpretability.

Abstract

Session-based recommendation aims to predict intents of anonymous users based on their limited behaviors. Modeling user behaviors involves two distinct rationales: co-occurrence patterns reflected by item IDs, and fine-grained preferences represented by item modalities (e.g., text and images). However, existing methods typically entangle these causes, leading to their failure in achieving accurate and explainable recommendations. To this end, we propose a novel framework DIMO to disentangle the effects of ID and modality in the task. At the item level, we introduce a co-occurrence representation schema to explicitly incorporate cooccurrence patterns into ID representations. Simultaneously, DIMO aligns different modalities into a unified semantic space to represent them uniformly. At the session level, we present a multi-view self-supervised disentanglement, including proxy mechanism and counterfactual inference, to disentangle ID and modality effects without supervised signals. Leveraging these disentangled causes, DIMO provides recommendations via causal inference and further creates two templates for generating explanations. Extensive experiments on multiple real-world datasets demonstrate the consistent superiority of DIMO over existing methods. Further analysis also confirms DIMO's effectiveness in generating explanations.