arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2508.06970cs.IR
收藏

融合序列嵌入、图与工程化特征:RecSys Challenge 2025第四名解决方案

Blending Sequential Embeddings, Graphs, and Engineered Features: 4th Place Solution in RecSys Challenge 2025

Sergei Makeev, Alexandr Andreev, Vladimir Baikalov, Vladislav Tytskiy, Aleksei Krasilnikov, Kirill Khrylchenko

AI总结:

本文提出RecSys Challenge 2025第四名方案,通过融合序列编码器、图神经网络、深度交叉网络与特征工程生成通用用户嵌入,在六项下游任务中取得优异表现。

摘要:

本文介绍了团队ambitious在由Synerise和ACM RecSys组织、聚焦通用行为建模的RecSys Challenge 2025中获第四名的解决方案。挑战目标为生成在六项不同下游任务中均有效的用户嵌入。我们的方案整合了:(1)序列编码器以捕捉用户兴趣的时序演变,(2)图神经网络以增强泛化能力,(3)深度交叉网络以建模高阶特征交互,以及(4)对性能至关重要的特征工程。

英文摘要:

This paper describes the 4th-place solution by team ambitious for the RecSys Challenge 2025, organized by Synerise and ACM RecSys, which focused on universal behavioral modeling. The challenge objective was to generate user embeddings effective across six diverse downstream tasks. Our solution integrates (1) a sequential encoder to capture the temporal evolution of user interests, (2) a graph neural network to enhance generalization, (3) a deep cross network to model high-order feature interactions, and (4) performance-critical feature engineering.

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。

↑