arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.04567cs.IRcs.CY
收藏

VK-LSVD:一个大规模工业数据集用于短视频推荐

VK-LSVD: A Large-Scale Industrial Dataset for Short-Video Recommendation

VK AI(VK人工智能);AI Center & IAI MSU(莫斯科国立大学人工智能中心与智能分析研究所);Lomonosov Moscow State University(莫斯科国立大学)

Aleksandr Poslavsky, Alexander D'yakonov, Yuriy Dorn, Andrey Zimovnov

AI总结:

VK-LSVD是一个大规模工业数据集,用于提升短视频推荐系统的研究与应用

摘要:

短视频推荐面临独特挑战,例如从隐式反馈中建模用户兴趣的快速变化,但进展受限于缺乏反映现实平台动态的大规模开放数据集。为弥合这一差距,我们引入了VK大型短视频数据集(VK-LSVD),这是目前公开可用的同类最大工业数据集。VK-LSVD提供了超过4000亿次交互的数据,来自1000万用户和近2000万部视频,持续六个月,同时包含丰富的特征,包括内容嵌入、多样的反馈信号和上下文元数据。我们的分析支持了该数据集的质量和多样性。该数据集的即时影响已通过其在2025年实时VK RecSys挑战中的核心作用得到确认。VK-LSVD提供了一个重要的、开放的数据集,用于构建现实的基准,以加速顺序推荐、冷启动场景和下一代推荐系统的研究。

英文摘要:

Short-video recommendation presents unique challenges, such as modeling rapid user interest shifts from implicit feedback, but progress is constrained by a lack of large-scale open datasets that reflect real-world platform dynamics. To bridge this gap, we introduce the VK Large Short-Video Dataset (VK-LSVD), the largest publicly available industrial dataset of its kind. VK-LSVD offers an unprecedented scale of over 40 billion interactions from 10 million users and almost 20 million videos over six months, alongside rich features including content embeddings, diverse feedback signals, and contextual metadata. Our analysis supports the dataset's quality and diversity. The dataset's immediate impact is confirmed by its central role in the live VK RecSys Challenge 2025. VK-LSVD provides a vital, open dataset to use in building realistic benchmarks to accelerate research in sequential recommendation, cold-start scenarios, and next-generation recommender systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑