Ensure Timeliness and Accuracy: A Novel Sliding Window Data Stream Paradigm for Live Streaming Recommendation (2402.14399v1)
Abstract: Live streaming recommender system is specifically designed to recommend real-time live streaming of interest to users. Due to the dynamic changes of live content, improving the timeliness of the live streaming recommender system is a critical problem. Intuitively, the timeliness of the data determines the upper bound of the timeliness that models can learn. However, none of the previous works addresses the timeliness problem of the live streaming recommender system from the perspective of data stream design. Employing the conventional fixed window data stream paradigm introduces a trade-off dilemma between labeling accuracy and timeliness. In this paper, we propose a new data stream design paradigm, dubbed Sliver, that addresses the timeliness and accuracy problem of labels by reducing the window size and implementing a sliding window correspondingly. Meanwhile, we propose a time-sensitive re-reco strategy reducing the latency between request and impression to improve the timeliness of the recommendation service and features by periodically requesting the recommendation service. To demonstrate the effectiveness of our approach, we conduct offline experiments on a multi-task live streaming dataset with labeling timestamps collected from the Kuaishou live streaming platform. Experimental results demonstrate that Sliver outperforms two fixed-window data streams with varying window sizes across all targets in four typical multi-task recommendation models. Furthermore, we deployed Sliver on the Kuaishou live streaming platform. Results of the online A/B test show a significant improvement in click-through rate (CTR), and new follow number (NFN), further validating the effectiveness of Sliver.
- {{\{{TensorFlow}}\}}: a system for {{\{{Large-Scale}}\}} machine learning. In OSDI). 265–283.
- Rich Caruana. 1997. Multitask learning. Machine learning 28 (1997), 41–75.
- Streamrec: a real-time recommender system. In SIGMOD. 1243–1246.
- Pepnet: Parameter and embedding personalized network for infusing with personalized prior information. In KDD. 3795–3804.
- Streaming recommender systems. In WWW. 381–389.
- Olivier Chapelle. 2014. Modeling delayed feedback in display advertising. In KDD. 1097–1105.
- Terec: A temporal recommender system over tweet stream. Proceedings of the VLDB Endowment 6, 12 (2013), 1254–1257.
- ” I was afraid, but now I enjoy being a streamer!” Understanding the Challenges and Prospects of Using Live Streaming for Online Education. Proceedings of the ACM on Human-Computer Interaction 4, CSCW3 (2021), 1–32.
- Asymptotically unbiased estimation for delayed feedback modeling via label correction. In TheWebConf. 369–379.
- Wide & deep learning for recommender systems. In Proceedings of the 1st workshop on deep learning for recommender systems. 7–10.
- ContentCTR: Frame-level Live Streaming Click-Through Rate Prediction with Multimodal Transformer. arXiv preprint arXiv:2306.14392 (2023).
- Dynamic matrix factorization with priors on unknown values. In KDD. 189–198.
- Live streaming recommendations based on dynamic representation learning. Decision Support Systems (2023), 113957.
- Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In AIStat. 249–256.
- Real negatives matter: Continuous training with real negatives for delayed feedback modeling. In KDD. 2890–2898.
- Dynamically Expandable Graph Convolution for Streaming Recommendation. In TheWebConf. 1457–1467.
- Practical lessons from predicting clicks on ads at facebook. In Proceedings of the eighth international workshop on data mining for online advertising. 1–9.
- Adaptive mixtures of local experts. Neural computation 3, 1 (1991), 79–87.
- Online learning under delayed feedback. In ICML. 1453–1461.
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
- Addressing delayed feedback for continuous training with neural networks in CTR prediction. In Recsys. 187–195.
- Estimating conversion rate in display advertising from past erformance data. In KDD. 768–776.
- Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In KDD. 1930–1939.
- Entire space multi-task model: An effective approach for estimating post-click conversion rate. In SIGIR. 1137–1140.
- Online learning for recency search ranking using real-time user feedback. In CIKM. 1501–1504.
- Search-based user interest modeling with lifelong sequential behavior data for click-through rate prediction. In CIKM. 2685–2692.
- Recommendation on live-streaming platforms: Dynamic availability and repeat consumption. In Recsys. 390–399.
- Sebastian Ruder. 2017. An Overview of Multi-Task Learning in Deep Neural Networks. arXiv e-prints (2017), arXiv–1706.
- Progressive layered extraction (ple): A novel multi-task learning (mtl) model for personalized recommendations. In Recsys. 269–278.
- Billion-scale commodity embedding for e-commerce recommendation in alibaba. In KDD. 839–848.
- Streaming graph neural networks via continual learning. In CIKM. 1515–1524.
- Streaming CTR Prediction: Rethinking Recommendation Task for Real-World Streaming Data. arXiv preprint arXiv:2307.07509 (2023).
- Streaming ranking based recommender systems. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 525–534.
- Yuya Yoshikawa and Yusaku Imai. 2018. A nonparametric delayed feedback model for conversion rate prediction. arXiv preprint arXiv:1802.00255 (2018).
- Leveraging tripartite interaction information from live stream e-commerce for improving product recommendation. In KDD. 3886–3894.
- A deep bi-directional prediction model for live streaming recommendation. Information Processing & Management 58, 2 (2021), 102453.
- Deep interest evolution network for click-through rate prediction. In AAAI. 5941–5948.
- Deep interest network for click-through rate prediction. In KDD. 1059–1068.