# Joint Training Capsule Network for Cold Start Recommendation

arXiv: https://arxiv.org/abs/2005.11467 · HTML: https://mlsanity.com/paper/2005.11467/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2020.

## Built on by (most cited first, 6 of 6)

- [Zero-Shot Recommender Systems](https://mlsanity.com/paper/2105.08318/) (2021)
- [Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce](https://mlsanity.com/paper/2306.05011/) (2023)
- [Pre-trained Recommender Systems: A Causal Debiasing Perspective](https://mlsanity.com/paper/2310.19251/) (2023)
- [LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks](https://mlsanity.com/paper/2604.12096/) (2026)
- [RESUS: Warm-Up Cold Users via Meta-Learning Residual User Preferences in CTR Prediction](https://mlsanity.com/paper/2210.16080/) (2022)
- [Probabilistic Residual Learning for Online Recommendations](https://mlsanity.com/paper/2607.20863/) (2026)

## Abstract (arXiv)

This paper proposes a novel neural network, joint training capsule network (JTCN), for the cold start recommendation task. We propose to mimic the high-level user preference other than the raw interaction history based on the side information for the fresh users. Specifically, an attentive capsule layer is proposed to aggregate high-level user preference from the low-level interaction history via a dynamic routing-by-agreement mechanism. Moreover, JTCN jointly trains the loss for mimicking the user preference and the softmax loss for the recommendation together in an end-to-end manner. Experiments on two publicly available datasets demonstrate the effectiveness of the proposed model. JTCN improves other state-of-the-art methods at least 7.07% for CiteULike and 16.85% for Amazon in terms of Recall@100 in cold start recommendation.