Preliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)

Tianyu Zhan; Zheqi Lv; Shengyu Zhang; Jiwei Li

doi:10.1609/aaai.v39i28.35323

Preliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)

Information Retrieval 2025-06-17 v1

Authors: Tianyu Zhan , Zheqi Lv , Shengyu Zhang , Jiwei Li

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

This paper explores the application and effectiveness of Test-Time Training (TTT) layers in improving the performance of recommendation systems. We developed a model, TTT4Rec, utilizing TTT-Linear as the feature extraction layer. Our tests across multiple datasets indicate that TTT4Rec, as a base model, performs comparably or even surpasses other baseline models in similar environments.

Keywords

test-time training recommendation systems feature extraction model evaluation TTT-Linear

Cite

@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}
}

Comments

To be published in AAAI-25 Student Abstract and Poster Program

Related papers

View all related →