Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2604.11440 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917462887366656 |
|---|---|
| author | Wan, Qiang Yang, Ze Yang, Dawei Fan, Ying Yan, Xin Liu, Siyang Liu, Yicong Zhang, Chenwei Xu, Wei Qin, Jiahao Wang, Ke |
| author_facet | Wan, Qiang Yang, Ze Yang, Dawei Fan, Ying Yan, Xin Liu, Siyang Liu, Yicong Zhang, Chenwei Xu, Wei Qin, Jiahao Wang, Ke |
| contents | Generative Recommendation (GR) has gained traction for its merits of superior performance and cold-start capability. As the vital role in GR, Semantic Identifiers (SIDs) represent item semantics through discrete tokens. However, current techniques for SID generation based on vector quantization face two main challenges: (i) training instability, stemming from insufficient gradient propagation through the straight-through estimator and sensitivity to initialization; and (ii) inefficient SID quality assessment, where industrial practice still depends on costly GR training and A/B testing. To address these challenges, we propose Reference Vector-Guided Rating Residual Quantization VAE (R3-VAE). This framework incorporates three key innovations: (i) a reference vector that functions as a semantic anchor for the initial features, thereby mitigating sensitivity to initialization; (ii) a dot product-based rating mechanism designed to stabilize the training process and prevent codebook collapse; and (iii) two SID evaluation metrics, Semantic Cohesion and Preference Discrimination, serving as regularization terms during training. Empirical results on six benchmarks demonstrate that R3-VAE outperforms state-of-the-art methods, achieving an average improvement of 14.5% in Recall@10 and 15.5% in NDCG@10 across three public datasets (Beauty, Sports, and Toys). Furthermore, we perform GR training and online A/B tests on Toutiao. Our method achieves a 1.62% improvement in MRR and a 0.83% gain in StayTime/U versus baselines. Additionally, we employ R3-VAE to replace the item ID of CTR model, resulting in significant improvements in content cold start by 15.36%, corroborating the strong applicability and business value in industry-scale recommendation scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11440 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | R3-VAE: Reference Vector-Guided Rating Residual Quantization VAE for Generative Recommendation Wan, Qiang Yang, Ze Yang, Dawei Fan, Ying Yan, Xin Liu, Siyang Liu, Yicong Zhang, Chenwei Xu, Wei Qin, Jiahao Wang, Ke Information Retrieval Generative Recommendation (GR) has gained traction for its merits of superior performance and cold-start capability. As the vital role in GR, Semantic Identifiers (SIDs) represent item semantics through discrete tokens. However, current techniques for SID generation based on vector quantization face two main challenges: (i) training instability, stemming from insufficient gradient propagation through the straight-through estimator and sensitivity to initialization; and (ii) inefficient SID quality assessment, where industrial practice still depends on costly GR training and A/B testing. To address these challenges, we propose Reference Vector-Guided Rating Residual Quantization VAE (R3-VAE). This framework incorporates three key innovations: (i) a reference vector that functions as a semantic anchor for the initial features, thereby mitigating sensitivity to initialization; (ii) a dot product-based rating mechanism designed to stabilize the training process and prevent codebook collapse; and (iii) two SID evaluation metrics, Semantic Cohesion and Preference Discrimination, serving as regularization terms during training. Empirical results on six benchmarks demonstrate that R3-VAE outperforms state-of-the-art methods, achieving an average improvement of 14.5% in Recall@10 and 15.5% in NDCG@10 across three public datasets (Beauty, Sports, and Toys). Furthermore, we perform GR training and online A/B tests on Toutiao. Our method achieves a 1.62% improvement in MRR and a 0.83% gain in StayTime/U versus baselines. Additionally, we employ R3-VAE to replace the item ID of CTR model, resulting in significant improvements in content cold start by 15.36%, corroborating the strong applicability and business value in industry-scale recommendation scenarios. |
| title | R3-VAE: Reference Vector-Guided Rating Residual Quantization VAE for Generative Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.11440 |