DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendation

TL;DR

DiscRec introduces a novel framework for generative recommendation that disentangles semantic and collaborative signals, explicitly models item structure, and fuses signals effectively, leading to improved recommendation performance.

Contribution

It proposes a dual-branch model with item-level position embeddings and a gating mechanism for disentangling and fusing semantic and collaborative signals in generative recommendation.

Findings

Outperforms state-of-the-art baselines on four datasets.

Effectively decouples semantic and collaborative signals.

Demonstrates improved recommendation accuracy.

Abstract

Generative recommendation is emerging as a powerful paradigm that directly generates item predictions, moving beyond traditional matching-based approaches. However, current methods face two key challenges: token-item misalignment, where uniform token-level modeling ignores item-level granularity that is critical for collaborative signal learning, and semantic-collaborative signal entanglement, where collaborative and semantic signals exhibit distinct distributions yet are fused in a unified embedding space, leading to conflicting optimization objectives that limit the recommendation performance. To address these issues, we propose DiscRec, a novel framework that enables Disentangled Semantic-Collaborative signal modeling with flexible fusion for generative Recommendation. First, DiscRec introduces item-level position embeddings, assigned based on indices within each semantic ID, enabling explicit modeling of item structure in input token sequences. Second, DiscRec employs a dual-branch module to disentangle the two signals at the embedding layer: a semantic branch encodes semantic signals using original token embeddings, while a collaborative branch applies localized attention restricted to tokens within the same item to effectively capture collaborative signals. A gating mechanism subsequently fuses both branches while preserving the model's ability to model sequential dependencies. Extensive experiments on four real-world datasets demonstrate that DiscRec effectively decouples these signals and consistently outperforms state-of-the-art baselines. Our codes are available on https://github.com/Ten-Mao/DiscRec.