Exploring Applications of State Space Models and Advanced Training Techniques in Sequential Recommendations: A Comparative Study on Efficiency and Perfomance

Nikolay Kutuzov, Alexander Gasnikov, Makar Baderko, Mark Obozov, Kulibaba Stepan

Keywords: Machine learning, Large Language Models, Recommender Systems, State Space Models

Abstract: Recommender systems aim to estimate the dynamically changing user preferences and sequential dependencies between historical user behaviour and metadata. Although transformer-based models have proven to be effective in sequential recommendations, their state growth is proportional to the length of the sequence that is being processed, which makes them expensive in terms of memory and inference costs. Our research focused on three promising directions in sequential recommendations: enhancing speed through the use of State Space Models (SSM), as they can achieve SOTA results in the sequential recommendations domain with lower latency, memory, and inference costs, as proposed by Chengkai Liu et al. (2024); improving the quality of recommendations with Large Language Mod- els (LLMs) via Monolithic Preference Optimization without Reference Model (ORPO); and implementing adaptive batch- and step-size algorithms to reduce costs and accelerate training processes.

Submission Number: 54