推荐系统中测试时训练层的初步评估
信息检索
2025-06-17 v1
摘要
本文探讨了测试时训练（Test-Time Training, TTT）层在提高推荐系统性能方面的应用和有效性。我们开发了模型TTT4Rec，利用TTT-Linear作为特征提取层。在多个数据集上的测试表明，TTT4Rec作为基模型，在类似环境下表现相当乃至优于其他基线模型。
关键词
引用
@article{arxiv.2411.15186,
title = {Preliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)},
author = {Tianyu Zhan and Zheqi Lv and Shengyu Zhang and Jiwei Li},
journal= {arXiv preprint arXiv:2411.15186},
year = {2025}
}
备注
To be published in AAAI-25 Student Abstract and Poster Program