RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems

Runpeng Cui; Zhipeng Sun; Chi Lu; Peng Jiang

cs.IRFeb 26, 2026

RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems

Authors: Runpeng Cui, Zhipeng Sun, Chi Lu, Peng Jiang

Organizations: Kuaishou Technology Beijing, China · Beijing, China

Abstract

Predicting continuous values such as watch-time and gross merchandise value (GMV) is a core problem in industrial recommendation systems. Its inherent difficulty stems from the highly complex and long-tailed distributions of the target signals, which are hard to model accurately. Existing regression methods typically rely on fixed parametric assumptions on the target distribution: overly simple assumptions underfit real-world data, whereas more intricate ones tend to sacrifice scalability and generalization. To address these limitations, we propose a sequence modeling framework based on residual quantization (RQ), in which the target continuous value is decomposed into a sequence of quantization codes that represent progressively finer approximations. The model autoregressively predicts these codes from coarse to fine granularity, with each step refining the residual error left by the previous one. To further improve the quality of the learned representations, we introduce an ordinal-aware representation learning objective that aligns the RQ code embedding space with the ordinal structure of target values, thereby yielding continuous representations of quantization codes and more accurate predictions. We conduct comprehensive experiments on public benchmarks for watch-time and lifetime value (LTV) prediction, together with a large-scale online A/B test for GMV prediction on an industrial short-video recommendation platform. Across all settings, the proposed method shows competitive performance among existing state-of-the-art approaches and generalizes well across diverse continuous value prediction scenarios.

Figures & tables

Figure 1. GMV distribution in a large-scale online short-video commercial scenario. From top to bottom, each subfigure shows the GMV frequency distribution over the value ranges 10–20, 20–30, 30–40, and 40–50.

Figure 2. Architecture of the proposed RQ-Reg method.

Method	KuaiRec		CIKM16
Method	MAE ↓	XAUC ↑	MAE ↓	XAUC ↑
WLR ( Covington et al., 2016 )	6.047	0.525	0.998	0.672
D2Q ( Zhan et al., 2022 )	5.426	0.565	0.899	0.661
TPM ( Lin et al., 2023 )	4.741	0.599	0.884	0.676
CREAD ( Sun et al., 2024 )	3.215	0.601	0.865	0.678
SWaT ( Yang et al., 2025 )	3.363	0.609	0.847	0.683

Table 1. Performance comparison on watch-time prediction datasets

Dataset	Method	MAE ↓	Gini (+) ↑	SRCC (+) ↑	Gini ↑	SRCC ↑
Criteo-SSC	Two-stage ( Drachen et al., 2018 )	21.719	0.2204	0.2565	0.5278	0.2386
	MTL-MSE ( Ma et al., 2018 )	21.190	0.4340	0.3663	0.6330	0.2478
	ZILN ( Wang et al., 2019 )	20.880	0.4426	0.3874	0.6338	0.2434
	MDME ( Li et al., 2022 )	16.598	0.2297	0.2952	0.4383	0.2269
	MDAN ( Liu et al., 2024 )	20.030	0.4128	0.3521	0.6209	0.2470
	OptDist ( Weng et al., 2024 )	15.784	0.4428	0.3903	0.6437	0.2505

Table 2. Performance comparison on LTV prediction datasets

Method	KuaiRec		CIKM16
Method	MAE ↓	XAUC ↑	MAE ↓	XAUC ↑
RQ-Reg	3.189	0.616	0.811	0.695
w/o $\mathcal{L}_{\text{gen}}$	3.199	0.613	0.821	0.691
w/o $\mathcal{L}_{\text{rnc}}$	3.195	0.614	0.819	0.692
w/o $f_{\text{err}}$	3.191	0.614	0.813	0.694
w/o $f_{\text{reg}}$ + $f_{\text{err}}$	3.200	0.613	0.815	0.694

Table 3. Ablation study on watch-time prediction datasets

Method	KuaiRec		CIKM16
Method	MAE ↓	XAUC ↑	MAE ↓	XAUC ↑
RNN	3.210	0.613	0.815	0.694
LSTM	3.189	0.616	0.811	0.695
Transformer	3.204	0.614	0.829	0.694

Table 4. Comparison of different model backbones on watch-time prediction datasets

Method	KuaiRec		CIKM16
Method	MAE ↓	XAUC ↑	MAE ↓	XAUC ↑
K-means	3.196	0.611	0.823	0.692
RQ K-means	3.189	0.616	0.811	0.695
Dynamic quantile ( Ma et al., 2024 )	3.242	0.611	0.819	0.693

Table 5. Comparison of different quantization methods on watch-time prediction datasets

Method	Reconst. error	Code length
K-means	$7.51\times 10^{-2}$	1
RQ K-means	$\mathbf{1.33\times 10^{-3}}$	3
Dynamic quantile ( Ma et al., 2024 )	$3.28\times 10^{-3}$	3.21 (on avg.)

Table 6. Reconstruction errors (in MAE) of different quantization methods on KuaiRec

Panel of Figure 3 — Figure 3. Results of RQ K-means quantization error (a) and RQ-Reg prediction (b) with different numbers of RQ levels $L$ on KuaiRec.

Panel of Figure 4 — Figure 4. Learned representations of target values from different models on KuaiRec. Point color represents the magnitude of the corresponding target value, from low (cool) to high (warm).

Setting	AUC ↑	ADVV ↑
Overall	+0.12%	+4.19%
Long-tail	+0.23%	+4.76%

Table 7. Performance lift of RQ-Reg over the production baseline in the online short-video advertising scenario

Figure 5. Daily ADVV gains during the online evaluation. The A/B test period spans days 1–7. On day 8 the experimental bucket was switched back to the production baseline, and the subsequent A/A test spans days 9–13.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Configuration	KuaiRec		CIKM16
Configuration	MAE ↓	XAUC ↑	MAE ↓	XAUC ↑
$K=16$	3.195	0.614	0.820	0.692
$K=32$	3.191	0.614	0.818	0.694
$K=48$	3.189	0.616	0.811	0.695
$K=64$	3.194	0.614	-	-

Appendix

Table 8. Performance comparison with different settings of hyperparameter

K

Configuration	KuaiRec		CIKM16
Configuration	MAE ↓	XAUC ↑	MAE ↓	XAUC ↑
$\alpha=0.1$	3.197	0.614	0.816	0.693
$\alpha=0.5$	3.189	0.614	0.812	0.695
$\alpha=1.0$	3.189	0.616	0.811	0.695
$\alpha=2.0$	3.193	0.614	0.814	0.693
$\alpha=5.0$	3.192	0.614	0.819	0.692

Appendix

Table 9. Performance comparison with different settings of hyperparameters

\alpha

and

\beta

Configuration	KuaiRec		CIKM16
Configuration	MAE ↓	XAUC ↑	MAE ↓	XAUC ↑
$k=0.01$	3.193	0.614	0.817	0.693
$k=0.05$	3.191	0.615	0.816	0.694
$k=0.1$	3.189	0.616	0.811	0.695
$k=0.2$	3.188	0.615	0.818	0.692
$k=0.5$	3.193	0.615	0.819	0.692

Appendix

Table 10. Performance comparison with different settings of hyperparameters

k

and

t_{0}

Explore similar work

FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors
May 31, 2026Hongxu Ma, Han Zhou, Chenghou Jin +5Future Video Prediction Short Video Bursts
Fudan University Shanghai, China · Kuaishou Technology Beijing, China · Shanghai University of Finance and Economics Shanghai, China +1
Probabilistic Residual Learning for Online Recommendations
Jul 23, 2026Wenyuan Wang, Yusong Zhao, Zihao Xu +11Real-World Content Recommendation Problem Residual Learning
Rutgers University · Piscataway, New Jersey, United States · Meta +4
RecRec: Recursive Refinement for Sequential Recommendation
Jul 12, 2026Pervez Shaik, Prosenjit Biswas, Abhinav Thorat +2Multimodal Recommendation Model Sequential Recommendation
Sony Research India India

May 31, 2026, cs.AIJ/K move · Enter open · S save

FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors

Hongxu Ma, Han Zhou, Chenghou Jin, Jie Zhang+4

Fudan University Shanghai, China · Kuaishou Technology Beijing, China · Shanghai University of Finance and Economics Shanghai, China+1

Future Video Prediction Short Video Bursts

Open paper AskPDF arXiv

Watch time has emerged as a pivotal metric for optimizing deep user engagement in short-video recommender systems. However, current methods of watch time prediction (WTP) suffer from inherent paradigm-specific limitations. Direct Regression faces mean-collapse due to unimodal Gaussian assumptions, while Ordinal Regression is hampered by quantization errors from rigid discretization. Similarly, Discrete Generative Regression struggles with high inference latency and heuristic vocabulary design. Beyond these specific flaws, a shared deficiency is the inability to capture the intrinsic multimodality and heterogeneity of User-Item Interaction Patterns. To address these challenges, we first revisit the WTP problem from a causal perspective and identify these user-specific patterns as structural confounders that modulate watch time outcomes, where identical interests manifest as distinct watch time outcomes conditioned on diverse user habits. Then, we formally propose a new (or the fourth) paradigm -- Continuous Generative Regression, and introduce FlowTime, a novel method utilizing a One-step Generative Variational Autoencoder. FlowTime effectively circumvents the latency of iterative denoising while maintaining the expressivity of continuous latent spaces. Furthermore, we design a Flow-based Personalized Prior that leverages NFs to warp a standard Gaussian prior into a complex, history-conditioned manifold, thereby enabling the adaptive modeling of multimodal interaction patterns. Finally, we build TimeRec, the first open-source WTP Library, alongside a novel personalization metric to establish a rigorous benchmarking standard. Extensive offline experiments and online A/B tests demonstrate FlowTime's significant superiority over SOTA methods.

Abstract

Explore similar work

FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors

Probabilistic Residual Learning for Online Recommendations

RecRec: Recursive Refinement for Sequential Recommendation