General recommender systems deliver personalized services by learning user and item representations, with the central challenge being how to capture latent user preferences. However, representations derived from sparse interactions often fail to comprehensively characterize user behaviors, thereby limiting recommendation effectiveness. Recent studies attempt to enhance user representations through sophisticated modeling strategies ($e.g.,$ intent or language modeling). Nevertheless, most works primarily concentrate on model interpretability instead of representation optimization. This imbalance has led to limited progress, as representation optimization is crucial for recommendation quality by promoting the affinity between users and their interacted items in the feature space, yet remains largely overlooked. To overcome these limitations, we propose DIAURec, a novel representation learning framework that unifies intent and language modeling for recommendation. DIAURec reconstructs representations based on the prototype and distribution intent spaces formed by collaborative and language signals. Furthermore, we design a comprehensive representation optimization strategy. Specifically, we adopts alignment and uniformity as the primary optimization objectives, and incorporates both coarse- and fine-grained matching to achieve effective alignment across different spaces, thereby enhancing representational consistency. Additionally, we further introduce intra-space and interaction regularization to enhance model robustness and prevent representation collapse in reconstructed space representation. Experiments on three public datasets against fifteen baseline methods show that DIAURec consistently outperforms state-of-the-art baselines, fully validating its effectiveness and superiority.

翻译：摘要：通用推荐系统通过学习用户与物品表征提供个性化服务，其核心挑战在于如何捕获用户潜在偏好。然而，基于稀疏交互习得的表征往往难以全面刻画用户行为，从而制约推荐效果。近期研究尝试通过复杂建模策略（如意图建模或语言建模）增强用户表征，但多数工作主要聚焦于模型可解释性而非表征优化。这种失衡导致进展有限——尽管表征优化通过提升特征空间中用户与其交互物品的亲和度对推荐质量至关重要，却长期被忽视。为突破上述局限，我们提出DIAURec——一种融合意图建模与语言建模的新型表征学习框架。该框架基于协同信号与语言信号形成的原型意图空间和分布意图空间重建表征，并设计全面的表征优化策略：具体而言，采用对齐性与一致性作为主要优化目标，引入粗粒度与细粒度匹配以实现跨空间高效对齐，增强表征一致性；同时引入空间内正则化与交互正则化提升模型鲁棒性，防止重建空间表征坍塌。在三个公开数据集上与十五种基线方法的实验表明，DIAURec持续优于现有最先进基线，充分验证了其有效性与优越性。