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

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.

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

References in corpus (12)

• Session-based Recommendations with Recurrent Neural Networks
• Intent Contrastive Learning for Sequential Recommendation
• Mining Latent Structures for Multimedia Recommendation
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
• Intelligent Model Update Strategy for Sequential Recommendation
• Controllable Multi-Interest Framework for Recommendation
• Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendation
• PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation
• Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation
• Semantic Codebook Learning for Dynamic Recommendation Models
• Mining Stable Preferences: Adaptive Modality Decorrelation for Multimedia Recommendation
• Efficient Inference for Large Language Model-based Generative Recommendation