Organizations: The Hong Kong Polytechnic University, Hong Kong SAR, China · University of Electronic Science and Technology of China, Chengdu, SiChuan, China · Southwest Jiaotong University, Chengdu, SiChuan, China · Kuaishou Technology, Beijing, China
Semantic IDs (SIDs) have emerged as a promising approach for discriminative recommendation by encoding continuous item rep- resentations into compact discrete identifiers. However, existing SID-based methods face two fundamental limitations: semantic mis- match between content semantics and collaborative preferences, and objective mismatch between SID construction and downstream recommendation optimization. To address these challenges, we propose SIDRec, an end-to-end recommendation-aware SID learn- ing framework that jointly models content and collaborative in- formation while aligning SID construction with recommendation objectives. Specifically, SIDRec introduces a self-updating fusion mechanism that explicitly integrates pretrained content represen- tations with collaborative embeddings initialized from a trained recommendation model, enabling preference-aware semantic mod- eling. Furthermore, SIDRec employs an MMoE-inspired joint opti- mization mechanism with shared experts and task-specific gates, allowing recommendation supervision to directly guide differen- tiable quantization and produce task-adaptive discrete representa- tions. Extensive experiments on three public benchmark datasets demonstrate that SIDRec consistently outperforms all competing methods across both AUC and GAUC, achieving up to 5.15% relative improvements over the strongest baselines. Further ablation stud- ies validate the effectiveness and complementarity of collaborative semantic modeling and end-to-end SID optimization.
Figures & tables
Figure 1. Semantic and collaborative signals capture distinct relationships. Items with different semantics ( e.g. mice and USB flash drives ) can exhibit similar collaborative patterns.
Figure 2. Comparison of existing paradigm with our SIDRec. (a) Existing SIDs paradigm mainly rely on content semantics and are optimized independently of downstream recommendation objectives, leading to semantic and objective mismatches. (b) Our SIDRec addresses these issues through content-collaborative semantic modeling and end-to-end SID learning.
Figure 3. Overview of the SIDRec framework. It first integrates collaborative representations from a trained ranking model with pretrained multimodal embeddings for SID construction. The framework then adapts a pretrained SID tokenizer through downstream CTR learning. Candidate and history representations built from the learned SIDs are used for click prediction and SID prediction, which are optimized jointly.
Statistic
Electronics
ML-20M
Beauty
Users
192,403
138,287
22,363
Items
63,001
20,720
12,101
Interactions
1,689,188
9,995,410
198,502
Average history
8.78
72.28
8.88
Maximum history
431
3,177
204
Sparsity
99.986%
99.651%
99.927%
Table 1. Statistics of the processed public datasets. History lengths are measured before truncation.
Category
Model
Electronics
MovieLens-20M
Beauty
Rank
AUC
Δ
GAUC
Δ
AUC
Δ
GAUC
Δ
AUC
Δ
GAUC
Δ
Linear
LR
0.75960
+15.79%
0.75912
+15.60%
0.94158
+4.40%
0.94143
+4.09%
0.66963
+23.02%
0.66640
+20.97%
16
FM
0.76155
+15.49%
0.76176
+15.20%
0.92802
+5.93%
0.93990
+4.26%
0.72163
+14.15%
0.70956
+13.61%
11
Interaction
DeepFM
0.76340
+15.21%
0.75985
+15.49%
0.94452
+4.08%
0.94517
+3.67%
0.71900
+14.57%
0.70124
+14.96%
13
DCNv2
0.76428
+15.08%
0.76084
+15.34%
0.94725
+3.78%
0.94884
+3.27%
0.72021
+14.38%
0.70647
+14.11%
8
FinalMLP
0.76283
+15.30%
0.76035
+15.42%
0.94484
+4.04%
0.94480
+3.72%
0.71699
+14.89%
0.70083
+15.03%
14
Table 2. Performance comparison on three public datasets. Each Δ column reports the relative improvement (%) of SIDRec over the corresponding baseline. Darker green cells indicate larger gains within each metric, and all gain values are printed in black. Bold denotes the best result and underlining denotes the strongest baseline. Rank is determined by the mean of the six per-metric ranks. Equal mean ranks share the same rank.
History Length
Users (%)
AUC
GAUC
3–5
11,383 (50.9%)
0.8121
0.7973
6–10
7,433 (33.2%)
0.8213
0.8044
11–20
2,528 (11.3%)
0.8533
0.8281
21–50
875 (3.9%)
0.8849
0.8597
51+
144 (0.6%)
0.9189
0.8846
Overall
22,363 (100%)
0.8238
0.8061
Table 3. Performance of SIDRec-CTR across different user activity levels on the Beauty dataset.
Variant
AUC
Drop
GAUC
Drop
SIDRec
0.87954
–
0.87758
–
w/o Collaborative View
0.87610
0.39% ↓
0.87372
0.44% ↓
w/o End-to-end SID
0.86223
1.97% ↓
0.86040
1.96% ↓
w/o Both
0.81627
7.19% ↓
0.81516
7.11% ↓
Table 4. Component ablation on Electronics.
Figure 4. First-level SID assignments after shuffling collaborative embeddings across items with model parameters fixed.
Metric
Electronics
ML-20M
Beauty
Representation Stability
Latent Cosine (Changed) ↑
0.985
0.954
0.989
Latent Cosine (Unchanged) ↑
0.990
0.979
0.993
Structural Consistency
Codebook Cosine (Random) ↑
0.84 (0.67)
0.87 (0.80)
0.89 (0.69)
Token Cosine (Random) ↑
0.34 (0.00)
0.25 (0.08)
0.26 (0.02)
Table 5. Semantic consistency of SID assignments under collaborative perturbation.
Figure 5. SID assignment dynamics during training across three datasets.
Domain
Task
Δ AUC
Δ UAUC
Δ WUAUC
Domain 1
Show
+0.50
+0.62
+1.13
CTR
+0.36
+1.15
+1.05
CVR
+1.08
+2.57
+2.48
Domain 2
Show
+0.42
+0.60
+1.11
CTR
+0.08
+0.06
+0.06
CVR
+0.00
+1.97
+2.08
Table 6. Offline gains over industrial baselines in percentage points. Darker green indicates larger gains within each metric. The largest gain within each domain and metric is bold.
Conventional Sequential Recommender Systems (SRS) typically assign unique hash IDs (HID) to construct item embeddings, which mainly capture collaborative signals from historical user-item interactions. However, such embeddings are vulnerable in long-tail scenarios where most items are rarely consumed. Recent methods that incorporate auxiliary information often face noisy collaborative sharing from co-occurrence signals or semantic homogeneity caused by flat dense embeddings. In contrast, Semantic IDs (SID), with their support for code sharing and multi-granular semantic modeling, offer a promising alternative. Nevertheless, SID-based methods are hindered by a collaborative overwhelming phenomenon: commonly adopted quantization mechanisms compromise the identifier uniqueness needed to model head items, resulting in a performance trade-off between head and tail items. To address this challenge, we propose H2Rec, a novel framework that harmonizes SID and HID. We design a dual-branch modeling architecture that simultaneously captures the multi-granular semantics of SID while preserving the unique collaborative identity provided by HID. Moreover, we introduce a dual-level alignment strategy to bridge the two representations, enabling effective knowledge transfer and robust preference modeling. Extensive offline experiments on three public benchmarks and online experiments on a large-scale commercial platform demonstrate that H2Rec achieves a better balance between head and tail recommendation quality and consistently outperforms existing baselines.
Ziwei Liu, Yejing Wang, Wanyu Wang +6
City University of Hong Kong Hong Kong, China · Tongji University Shanghai, China · Xi’an Jiaotong University Xi’an, China +3
Semantic IDs (SIDs) are compact discrete representations derived from multimodal item features, serving as a unified abstraction for ID-based and generative recommendation. However, learning high-quality SIDs remains challenging due to two issues. (1) Collision problem: the quantized token space is prone to collisions, in which semantically distinct items are assigned identical or overly similar SID compositions, resulting in semantic entanglement. (2) Collision-signal heterogeneity: collisions are not uniformly harmful. Some reflect genuine conflicts between semantically unrelated items, while others stem from benign redundancy or systematic data effects. To address these challenges, we propose Qualification-Aware Semantic ID Learning (QuaSID), an end-to-end framework that learns collision-qualified SIDs by selectively repelling qualified conflict pairs and scaling the repulsion strength by collision severity. QuaSID consists of two mechanisms: Hamming-guided Margin Repulsion, which translates low-Hamming SID overlaps into explicit, severity-scaled geometric constraints on the encoder space; and Conflict-Aware Valid Pair Masking, which masks protocol-induced benign overlaps to denoise repulsion supervision. In addition, QuaSID incorporates a dual-tower contrastive objective to inject collaborative signals into tokenization. Experiments on public benchmarks and industrial data validate QuaSID. On public datasets, QuaSID consistently outperforms strong baselines, improving top-K ranking quality by 5.9% over the best baseline while increasing SID composition diversity. In an online A/B test on Kuaishou e-commerce with a 5% traffic split, QuaSID increases ranking GMV-S2 by 2.38% and improves completed orders on cold-start retrieval by up to 6.42%. Finally, we show that the proposed repulsion loss is plug-and-play and enhances a range of SID learning frameworks across datasets.
Zheng Hu, Yuxin Chen, Yongsen Pan +13
University of Electronic Science and Technology of China, Chengdu, China · Kuaishou Technology, Beijing, China
Existing work on Semantic IDs (SIDs) for generative recommendation treats SID construction as a representation learning problem: encode items into a quantised latent space and read off codes. We argue this view is incidental. SID construction is, at heart, a recursive clustering problem, and once stated this way the natural object to cluster is a graph whose nodes carry semantic content and whose edges carry collaborative signal; SID assignment becomes a hierarchical graph partition. This reframing yields a unified framework, Graph-Informed Semantic IDs (GrIS), that subsumes prior approaches rather than displacing them. RQ-VAE and RQ-KMeans are recovered as the special case where the graph is empty, exposing content-only quantisation as one corner of a larger design space along two so-far-collapsed axes: graph construction and recursive partition algorithm. We explore two contrasting instantiations: RecDMoN, which performs hierarchical assignment via differentiable graph pooling, and RQ-GAE, which extends RQ-VAE with graph-aware item representations and a graph reconstruction objective. On multiple real-world datasets, GrIS consistently improves over CF-aware SOTA, with gains of up to +52% Hit@10. Because graph construction and partition are explicit, separately configurable components, improvements on either axis can be combined and evaluated systematically.
Aleksei Medvedev, Alejandro Ariza-Casabona, Steven Derby +3