The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation

TL;DR

This paper introduces H2Rec, a framework that combines semantic IDs and hash IDs in sequential recommender systems to improve recommendation accuracy for both popular and long-tail items by balancing their representations.

Contribution

H2Rec is the first to harmonize semantic and hash IDs through dual-branch architecture and alignment strategies, enhancing tail and head item recommendations simultaneously.

Findings

H2Rec outperforms baseline models on three real-world datasets.

The dual-level alignment improves knowledge transfer between ID types.

Balanced recommendation quality for head and tail items is achieved.

Abstract

Conventional Sequential Recommender Systems (SRS) typically assign unique Hash IDs (HID) to construct item embeddings. These HID embeddings effectively learn collaborative information from historical user-item interactions, making them vulnerable to situations where most items are rarely consumed (the long-tail problem). Recent methods that incorporate auxiliary information often suffer from noisy collaborative sharing caused by co-occurrence signals or semantic homogeneity caused by flat dense embeddings. Semantic IDs (SIDs), with their capability of code sharing and multi-granular semantic modeling, provide a promising alternative. However, the collaborative overwhelming phenomenon hinders the further development of SID-based methods. The quantization mechanisms commonly compromise the uniqueness of identifiers required for modeling head items, creating a performance seesaw between head and tail items. To address this dilemma, we propose \textbf{\name}, a novel framework that harmonizes the SID and HID. Specifically, we devise a dual-branch modeling architecture that enables the model to capture both the multi-granular semantics within SID while preserving the unique collaborative identity of HID. Furthermore, we introduce a dual-level alignment strategy that bridges the two representations, facilitating knowledge transfer and supporting robust preference modeling. Extensive experiments on three real-world datasets show that \name~ effectively balances recommendation quality for both head and tail items while surpassing the existing baselines. The implementation code can be found online\footnote{https://github.com/ziwliu8/H2Rec}.