A

Disentangling ID and Modality Effects for Session-based Recommendation

International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 1883–1892

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. DIMO aims to disentangle these causes at both item and session levels. At the item level, we introduce a co-occurrence representation schema to explicitly incorporate co-occurrence 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.

Authors 6

  1. Xiaokun Zhang Aachen

    Leiden University · Pennsylvania State University · Dalian University of Technology

    Affiliation as printed

    Dalian University of Technology, Dalian, China

    Leiden University

    Pennsylvania State University

  2. Bo Xu Aachen

    Leiden University · Pennsylvania State University · Dalian University of Technology

    Affiliation as printed

    Dalian University of Technology, Dalian, China

    Leiden University

    Pennsylvania State University

  3. Zhaochun Ren Aachen

    Leiden University · Pennsylvania State University · Dalian University of Technology

    Affiliation as printed

    Leiden University, Leiden, Netherlands

    Dalian University of Technology

    Pennsylvania State University

  4. Xiaochen Wang Aachen

    Leiden University · Pennsylvania State University · Dalian University of Technology

    Affiliation as printed

    Pennsylvania State University, State College, PA, USA

    Dalian University of Technology

    Leiden University

  5. Hongfei Lin Aachen

    Leiden University · Pennsylvania State University · Dalian University of Technology

    Affiliation as printed

    Dalian University of Technology, Dalian, China

    Leiden University

    Pennsylvania State University

  6. Fenglong Ma Aachen

    Leiden University · Pennsylvania State University · Dalian University of Technology

    Affiliation as printed

    Pennsylvania State University, University Park, PA, USA

    Dalian University of Technology

    Leiden University

Cited by 31 stored of 32

No patents citing this paper on Lens.org (checked 2026-10-11).

References 35