Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval

TL;DR

This paper identifies and addresses the 'Hourglass' phenomenon in residual quantization for generative retrieval, proposing solutions that improve codebook utilization and retrieval performance in e-commerce systems.

Contribution

It analyzes the causes of the 'Hourglass' phenomenon and introduces methods to mitigate it, enhancing the effectiveness of residual quantization in generative retrieval.

Findings

The 'Hourglass' phenomenon hampers codebook utilization in RQ-SID.

Data sparsity and long-tailed distributions are primary causes.

Proposed solutions significantly improve retrieval performance.

Abstract

Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and generalization. Notably, methods like TIGER employing Residual Quantization-based Semantic Identifiers (RQ-SID), have shown significant promise in e-commerce scenarios by effectively managing item IDs. However, a critical issue termed the "\textbf{Hourglass}" phenomenon, occurs in RQ-SID, where intermediate codebook tokens become overly concentrated, hindering the full utilization of generative retrieval methods. This paper analyses and addresses this problem by identifying data sparsity and long-tailed distribution as the primary causes. Through comprehensive experiments and detailed ablation studies, we analyze the impact of these factors on codebook utilization and data distribution. Our findings reveal that the "Hourglass" phenomenon substantially impacts the performance of RQ-SID in generative retrieval. We propose effective solutions to mitigate this issue, thereby significantly enhancing the effectiveness of generative retrieval in real-world E-commerce applications.