Autoregressive Generation Strategies for Top-K Sequential Recommendations

TL;DR

This paper investigates autoregressive generation methods for Top-K sequential recommendations using transformer models, proposing new strategies that outperform traditional methods especially over longer time horizons.

Contribution

It introduces novel Reciprocal Rank Aggregation and Relevance Aggregation strategies for improved multi-sequence generation in recommender systems.

Findings

Proposed methods outperform traditional Top-K prediction in long-term recommendations.

Temperature sampling-based strategies improve diversity and relevance.

New strategies show significant gains on diverse datasets.

Abstract

The goal of modern sequential recommender systems is often formulated in terms of next-item prediction. In this paper, we explore the applicability of generative transformer-based models for the Top-K sequential recommendation task, where the goal is to predict items a user is likely to interact with in the "near future". We explore commonly used autoregressive generation strategies, including greedy decoding, beam search, and temperature sampling, to evaluate their performance for the Top-K sequential recommendation task. In addition, we propose novel Reciprocal Rank Aggregation (RRA) and Relevance Aggregation (RA) generation strategies based on multi-sequence generation with temperature sampling and subsequent aggregation. Experiments on diverse datasets give valuable insights regarding commonly used strategies' applicability and show that suggested approaches improve performance on longer time horizons compared to widely-used Top-K prediction approach and single-sequence autoregressive generation strategies.