End-to-End Semantic ID Generation for Generative Advertisement Recommendation

TL;DR

UniSID introduces an end-to-end framework for semantic ID generation in generative ad recommendation, improving semantic fidelity and recommendation accuracy over traditional two-stage methods.

Contribution

The paper proposes UniSID, a unified end-to-end SID generation model that jointly optimizes embeddings and SIDs, incorporating multi-granularity contrastive learning and ad reconstruction.

Findings

Achieves up to 4.62% improvement in Hit Rate metrics.

Outperforms state-of-the-art SID generation methods.

Addresses semantic degradation and error accumulation issues.

Abstract

Generative Recommendation (GR) has excelled by framing recommendation as next-token prediction. This paradigm relies on Semantic IDs (SIDs) to tokenize large-scale items into discrete sequences. Existing GR approaches predominantly generate SIDs via Residual Quantization (RQ), where items are encoded into embeddings and then quantized to discrete SIDs. However, this paradigm suffers from inherent limitations: 1) Objective misalignment and semantic degradation stemming from the two-stage compression; 2) Error accumulation inherent in the structure of RQ. To address these limitations, we propose UniSID, a Unified SID generation framework for generative advertisement recommendation. Specifically, we jointly optimize embeddings and SIDs in an end-to-end manner from raw advertising data, enabling semantic information to flow directly into the SID space and thus addressing the inherent limitations of the two-stage cascading compression paradigm. To capture fine-grained semantics, a multi-granularity contrastive learning strategy is introduced to align distinct items across SID levels. Finally, a summary-based ad reconstruction mechanism is proposed to encourage SIDs to capture high-level semantic information that is not explicitly present in advertising contexts. Experiments demonstrate that UniSID consistently outperforms state-of-the-art SID generation methods, yielding up to a 4.62% improvement in Hit Rate metrics across downstream advertising scenarios compared to the strongest baseline.