Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer

TL;DR

This paper introduces the SA^2CRQ framework, which enhances retrieval efficiency and generalization by adaptive quantization and residual knowledge transfer, especially benefiting cold-start and tail items.

Contribution

The paper proposes a novel adaptive quantization method and residual knowledge transfer technique to improve semantic retrieval for head and tail items.

Findings

SA^2CRQ improves retrieval accuracy in industrial and public datasets.

The framework effectively handles cold-start and tail item retrieval scenarios.

Experimental results show consistent performance gains over baselines.

Abstract

While semantic ID-based generative retrieval enables efficient end-to-end modeling in industrial applications, these methods face a persistent trade-off. On one hand, data-rich head items often suffer from ID collisions, which blur their distinct features and degrade downstream tasks. On the other hand, data-sparse tail items especially cold-start items are prone to semantic fragmentation during quantization; they are often mapped as isolated discrete points, which severely hinders their ability to generalize. To address this issue, we propose the Anchored Curriculum with Sequential Adaptive Quantization ($SA^2CRQ$) framework. The framework introduces Sequential Adaptive Residual Quantization (SARQ) to dynamically allocate code lengths based on item path entropy, assigning longer, discriminative IDs to head items and shorter, generalizable IDs to tail items. To mitigate data sparsity, the Anchored Curriculum Residual Quantization (ACRQ) component utilizes a frozen semantic manifold learned from head items to regularize and accelerate the representation learning of tail items. Experimental results from a large-scale industrial search system and multiple public datasets indicate that $SA^2CRQ$ yields consistent improvements over existing baselines, particularly in cold-start retrieval scenarios.