In large-scale Point-of-Interest (POI) recommendation, the conflict between accuracy and computational efficiency intensifies as POI catalogs grow. Traditional deep models struggle to balance quality with efficiency. To address this challenge, we propose a knowledge-distilled product quantization framework EffiPOI for efficient POI recommendation. EffiPOI jointly optimizes accuracy and efficiency by integrating product quantization with multi-modal knowledge distillation. Specifically, we first construct service-oriented multi-modal POI representations, which comprehensively capture each POI’s spatial coverage, temporal activity patterns, and semantic attributes. Based on these representations, we design a teacher-student distillation paradigm. The teacher model adopts a Mixture-of-Experts architecture to generate discriminative and semantically expressive POI representations, which serve as high-quality supervision signals for guiding the student model through knowledge distillation. The student model leverages product quantization to encode POIs into compact and computation-friendly representations, achieving a favorable tradeoff between representational compactness and predictive accuracy. To alleviate the performance degradation due to quantization, we develop a hybrid knowledge distillation strategy that transfers both response-aware and feature-aware knowledge from the teacher model to the student model. Experimental results on three real-world datasets show that the proposed method achieves 4.6%–12.1% improvements in accuracy and over 10× speedup in inference efficiency, outperforming existing POI recommendation models. Code is available at: https://github.com/pcm1217/EffiPOI .

Recent studies tend to employ Contrastive Learning (CL) methods to facilitate model training by extracting self-supervised signals to mitigate data sparsity . However, existing CL-based recommendation methods have not fully exploited the rich semantic information present in multi-modal data. To address these limitations, we propose a new CL-based recommendation framework named Multi-level Cross-modal Contrastive Learning (MCCL), which aims to construct multi-level contrastive learning to fully exploit the intra- and inter-modal semantic information in a self-supervised manner. Specifically, we innovatively consider user interaction and semantic review as two distinct semantic modalities, and devise two modal-specific contrastive learning strategies to enhance intra-modal learning. Furthermore, we leverage the semantic consistency between modalities to construct a multi-level cross-modal contrastive learning framework. Finally, a multi-task learning method is employed for collaborative optimization across multiple tasks. We verify the efficacy of MCCL via comprehensive experiments on three real-world datasets. MCCL achieves a significant performance improvement over the state-of-the-art baseline models .