# Generative Regression Based Watch Time Prediction for Short-Video Recommendation

arXiv: https://arxiv.org/abs/2412.20211 · HTML: https://mlsanity.com/paper/2412.20211/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 59 references that are in the map.
- First posted on arXiv 28 Dec 2024.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems](https://mlsanity.com/paper/2202.10842/) (2022)
- [KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos](https://mlsanity.com/paper/2208.08696/) (2022)
- [Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation](https://mlsanity.com/paper/2206.06003/) (2022)
- [Real-time Short Video Recommendation on Mobile Devices](https://mlsanity.com/paper/2208.09577/) (2022)
- [Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation](https://mlsanity.com/paper/2109.13527/) (2021)
- [Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation](https://mlsanity.com/paper/2306.03392/) (2023)
- [Billion-user Customer Lifetime Value Prediction: An Industrial-scale Solution from Kuaishou](https://mlsanity.com/paper/2208.13358/) (2022)
- [CREAD: A Classification-Restoration Framework with Error Adaptive Discretization for Watch Time Prediction in Video Recommender Systems](https://mlsanity.com/paper/2401.07521/) (2024)
- [DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias](https://mlsanity.com/paper/2208.05190/) (2022)
- [TeaForN: Teacher-Forcing with N-grams](https://mlsanity.com/paper/2010.03494/) (2020)
- [Counteracting Duration Bias in Video Recommendation via Counterfactual Watch Time](https://mlsanity.com/paper/2406.07932/) (2024)
- [OptDist: Learning Optimal Distribution for Customer Lifetime Value Prediction](https://mlsanity.com/paper/2408.08585/) (2024)
- [Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework](https://mlsanity.com/paper/2306.17426/) (2023)
- [SWaT: Statistical Modeling of Video Watch Time through User Behavior Analysis](https://mlsanity.com/paper/2408.07759/) (2024)

## Built on by (most cited first, 13 of 13)

- [HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models](https://mlsanity.com/paper/2506.03922/) (2025)
- [Fine-Grained Zero-Shot Object Detection](https://mlsanity.com/paper/2507.10358/) (2025)
- [RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer](https://mlsanity.com/paper/2603.14290/) (2026)
- [RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems](https://mlsanity.com/paper/2607.29241/) (2026)
- [RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360degImage Quality Assessment](https://mlsanity.com/paper/2603.14297/) (2026)
- [Generative Bid Shading in Real-Time Bidding Advertising](https://mlsanity.com/paper/2508.06550/) (2025)
- [RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems](https://mlsanity.com/paper/2602.23012/) (2026)
- [DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression](https://mlsanity.com/paper/2606.07599/) (2026)
- [Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction](https://mlsanity.com/paper/2608.23356/) (2026)
- [Learnable Instance Attention Filtering for Adaptive Detector Distillation](https://mlsanity.com/paper/2603.26088/) (2026)
- [FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors](https://mlsanity.com/paper/2606.01352/) (2026)
- [PIT-SUN: A Deployable Empirical Marginal Transform Framework with Expectation-Consistent Recovery for Regression in Recommender Systems](https://mlsanity.com/paper/2607.08202/) (2026)
- [Generative Optimization for Incentivized Advertising with Global Level Constraints](https://mlsanity.com/paper/2608.04421/) (2026)

## Abstract (arXiv)

Watch time prediction (WTP) has emerged as a pivotal task in short video recommendation systems, designed to quantify user engagement through continuous interaction modeling. Predicting users' watch times on videos often encounters fundamental challenges, including wide value ranges and imbalanced data distributions, which can lead to significant estimation bias when directly applying regression techniques. Recent studies have attempted to address these issues by converting the continuous watch time estimation into an ordinal regression task. While these methods demonstrate partial effectiveness, they exhibit notable limitations: (1) the discretization process frequently relies on bucket partitioning, inherently reducing prediction flexibility and accuracy and (2) the interdependencies among different partition intervals remain underutilized, missing opportunities for effective error correction. Inspired by language modeling paradigms, we propose a novel Generative Regression (GR) framework that reformulates WTP as a sequence generation task. Our approach employs textitstructural discretization to enable nearly lossless value reconstruction while maintaining prediction fidelity. Through carefully designed vocabulary construction and label encoding schemes, each watch time is bijectively mapped to a token sequence. To mitigate the training-inference discrepancy caused by teacher-forcing, we introduce a textitcurriculum learning with embedding mixup strategy that gradually transitions from guided to free-generation modes. We evaluate our method against state-of-the-art approaches on two public datasets and one industrial dataset. We also perform online A/B testing on the Kuaishou App to confirm the real-world effectiveness. The results conclusively show that GR outperforms existing techniques significantly.