Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911097513050112 |
|---|---|
| author | Yang, Weiqin Chen, Jiawei Zhang, Shengjia Wu, Peng Sun, Yuegang Feng, Yan Chen, Chun Wang, Can |
| author_facet | Yang, Weiqin Chen, Jiawei Zhang, Shengjia Wu, Peng Sun, Yuegang Feng, Yan Chen, Chun Wang, Can |
| contents | In the realm of recommender systems (RS), Top-$K$ ranking metrics such as NDCG@$K$ are the gold standard for evaluating recommendation performance. However, during the training of recommendation models, optimizing NDCG@$K$ poses significant challenges due to its inherent discontinuous nature and the intricate Top-$K$ truncation. Recent efforts to optimize NDCG@$K$ have either overlooked the Top-$K$ truncation or suffered from high computational costs and training instability. To overcome these limitations, we propose SoftmaxLoss@$K$ (SL@$K$), a novel recommendation loss tailored for NDCG@$K$ optimization. Specifically, we integrate the quantile technique to handle Top-$K$ truncation and derive a smooth upper bound for optimizing NDCG@$K$ to address discontinuity. The resulting SL@$K$ loss has several desirable properties, including theoretical guarantees, ease of implementation, computational efficiency, gradient stability, and noise robustness. Extensive experiments on four real-world datasets and three recommendation backbones demonstrate that SL@$K$ outperforms existing losses with a notable average improvement of 6.03%. The code is available at https://github.com/Tiny-Snow/IR-Benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05673 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems Yang, Weiqin Chen, Jiawei Zhang, Shengjia Wu, Peng Sun, Yuegang Feng, Yan Chen, Chun Wang, Can Information Retrieval Artificial Intelligence Machine Learning In the realm of recommender systems (RS), Top-$K$ ranking metrics such as NDCG@$K$ are the gold standard for evaluating recommendation performance. However, during the training of recommendation models, optimizing NDCG@$K$ poses significant challenges due to its inherent discontinuous nature and the intricate Top-$K$ truncation. Recent efforts to optimize NDCG@$K$ have either overlooked the Top-$K$ truncation or suffered from high computational costs and training instability. To overcome these limitations, we propose SoftmaxLoss@$K$ (SL@$K$), a novel recommendation loss tailored for NDCG@$K$ optimization. Specifically, we integrate the quantile technique to handle Top-$K$ truncation and derive a smooth upper bound for optimizing NDCG@$K$ to address discontinuity. The resulting SL@$K$ loss has several desirable properties, including theoretical guarantees, ease of implementation, computational efficiency, gradient stability, and noise robustness. Extensive experiments on four real-world datasets and three recommendation backbones demonstrate that SL@$K$ outperforms existing losses with a notable average improvement of 6.03%. The code is available at https://github.com/Tiny-Snow/IR-Benchmark. |
| title | Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2508.05673 |