# Cold Item Integration in Deep Hybrid Recommenders via Tunable Stochastic Gates

arXiv: https://arxiv.org/abs/2112.07615 · HTML: https://mlsanity.com/paper/2112.07615/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 12 Dec 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches](https://mlsanity.com/paper/1907.06902/) (2019)
- [Collaborative Deep Learning for Recommender Systems](https://mlsanity.com/paper/1409.2944/) (2014)
- [Item2Vec: Neural Item Embedding for Collaborative Filtering](https://mlsanity.com/paper/1603.04259/) (2016)
- [Hybrid Recommender Systems: A Systematic Literature Review](https://mlsanity.com/paper/1901.03888/) (2019)
- [Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering](https://mlsanity.com/paper/2010.07042/) (2020)
- [Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference](https://mlsanity.com/paper/2106.01186/) (2021)
- [Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding](https://mlsanity.com/paper/1908.05161/) (2019)
- [Bayesian Neural Word Embedding](https://mlsanity.com/paper/1603.06571/) (2016)
- [Neural Attentive Multiview Machines](https://mlsanity.com/paper/2002.07696/) (2020)
- [Bayesian Hierarchical Words Representation Learning](https://mlsanity.com/paper/2004.07126/) (2020)
- [Attentive Item2Vec: Neural Attentive User Representations](https://mlsanity.com/paper/2002.06205/) (2020)
- [HybridSVD: When Collaborative Information is Not Enough](https://mlsanity.com/paper/1802.06398/) (2018)
- [RecoBERT: A Catalog Language Model for Text-Based Recommendations](https://mlsanity.com/paper/2009.13292/) (2020)
- [Trust-Based Collaborative Filtering: Tackling the Cold Start Problem Using Regular Equivalence](https://mlsanity.com/paper/1807.06839/) (2018)

## Built on by (most cited first, 8 of 8)

- [Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps](https://mlsanity.com/paper/2204.11073/) (2022)
- [Interpreting BERT-based Text Similarity via Activation and Saliency Maps](https://mlsanity.com/paper/2208.06612/) (2022)
- [MetricBERT: Text Representation Learning via Self-Supervised Triplet Training](https://mlsanity.com/paper/2208.06610/) (2022)
- [Efficient Discovery and Effective Evaluation of Visual Perceptual Similarity: A Benchmark and Beyond](https://mlsanity.com/paper/2308.14753/) (2023)
- [Fidelity-Aware Recommendation Explanations via Stochastic Path Integration](https://mlsanity.com/paper/2511.18047/) (2025)
- [Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems](https://mlsanity.com/paper/2511.18024/) (2025)
- [Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up](https://mlsanity.com/paper/2302.14395/) (2023)
- [General Item Representation Learning for Cold-start Content Recommendations](https://mlsanity.com/paper/2404.13808/) (2024)

## Abstract (arXiv)

A major challenge in collaborative filtering methods is how to produce recommendations for cold items (items with no ratings), or integrate cold item into an existing catalog. Over the years, a variety of hybrid recommendation models have been proposed to address this problem by utilizing items' metadata and content along with their ratings or usage patterns. In this work, we wish to revisit the cold start problem in order to draw attention to an overlooked challenge: the ability to integrate and balance between (regular) warm items and completely cold items. In this case, two different challenges arise: (1) preserving high quality performance on warm items, while (2) learning to promote cold items to relevant users. First, we show that these two objectives are in fact conflicting, and the balance between them depends on the business needs and the application at hand. Next, we propose a novel hybrid recommendation algorithm that bridges these two conflicting objectives and enables a harmonized balance between preserving high accuracy for warm items while effectively promoting completely cold items. We demonstrate the effectiveness of the proposed algorithm on movies, apps, and articles recommendations, and provide an empirical analysis of the cold-warm trade-off.