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.