DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendation

2025-06-18

AI Summary

Generative recommender systems face two key challenges: (i) token-item granularity mismatch—uniform token-level modeling overlooks item-level collaborative signals; and (ii) semantic-collaborative signal coupling—heterogeneous semantic and collaborative distributions share a single embedding space, causing optimization conflicts. To address these, we propose DiscRec, a decoupled framework with three core contributions: (i) the first item-level positional encoding to explicitly align representations at the item granularity; (ii) a dual-branch Transformer architecture that separately models semantic and collaborative signals, augmented with localized collaborative attention to enhance intra-sequence item interactions; and (iii) an adaptive gating mechanism for flexible fusion of semantic and collaborative representations. Extensive experiments on four real-world datasets demonstrate that DiscRec significantly outperforms state-of-the-art methods, validating both the effectiveness and generalizability of signal decoupling for generative recommendation.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Resolves token-item misalignment in generative recommendation models
• Addresses semantic-collaborative signal entanglement in recommendation systems
• Improves item prediction accuracy via disentangled signal modeling

Innovation

• Item-level position embeddings for structure modeling
• Dual-branch module for signal disentanglement
• Gating mechanism for flexible signal fusion