# Fast Multi-Step Critiquing for VAE-based Recommender Systems

arXiv: https://arxiv.org/abs/2105.00774 · HTML: https://mlsanity.com/paper/2105.00774/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 51 references that are in the map.
- First posted on arXiv 3 May 2021.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Multimodal Generative Models for Scalable Weakly-Supervised Learning](https://mlsanity.com/paper/1802.05335/) (2018)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [Learning Factorized Multimodal Representations](https://mlsanity.com/paper/1806.06176/) (2018)
- [Recurrent Neural Networks with Top-k Gains for Session-based Recommendations](https://mlsanity.com/paper/1706.03847/) (2017)
- [Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence](https://mlsanity.com/paper/2006.08242/) (2020)
- [Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent](https://mlsanity.com/paper/2007.07422/) (2020)
- [How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements](https://mlsanity.com/paper/2005.12210/) (2020)
- [HotelRec: a Novel Very Large-Scale Hotel Recommendation Dataset](https://mlsanity.com/paper/2002.06854/) (2020)
- [Interacting with Explanations through Critiquing](https://mlsanity.com/paper/2005.11067/) (2020)
- [Knowledge-aware Autoencoders for Explainable Recommender Sytems](https://mlsanity.com/paper/1807.06300/) (2018)

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

- [Editable User Profiles for Controllable Text Recommendation](https://mlsanity.com/paper/2304.04250/) (2023)
- [A Survey on Fairness-aware Recommender Systems](https://mlsanity.com/paper/2306.00403/) (2023)
- [Self-Supervised Bot Play for Conversational Recommendation with Justifications](https://mlsanity.com/paper/2112.05197/) (2021)
- [Assistive Recipe Editing through Critiquing](https://mlsanity.com/paper/2205.02454/) (2022)
- [Privacy-Utility-Bias Trade-offs for Privacy-Preserving Recommender Systems](https://mlsanity.com/paper/2511.22515/) (2025)
- [Positive and Negative Critiquing for VAE-based Recommenders](https://mlsanity.com/paper/2204.02162/) (2022)

## Abstract (arXiv)

Recent studies have shown that providing personalized explanations alongside recommendations increases trust and perceived quality. Furthermore, it gives users an opportunity to refine the recommendations by critiquing parts of the explanations. On one hand, current recommender systems model the recommendation, explanation, and critiquing objectives jointly, but this creates an inherent trade-off between their respective performance. On the other hand, although recent latent linear critiquing approaches are built upon an existing recommender system, they suffer from computational inefficiency at inference due to the objective optimized at each conversation's turn. We address these deficiencies with M&Ms-VAE, a novel variational autoencoder for recommendation and explanation that is based on multimodal modeling assumptions. We train the model under a weak supervision scheme to simulate both fully and partially observed variables. Then, we leverage the generalization ability of a trained M&Ms-VAE model to embed the user preference and the critique separately. Our work's most important innovation is our critiquing module, which is built upon and trained in a self-supervised manner with a simple ranking objective. Experiments on four real-world datasets demonstrate that among state-of-the-art models, our system is the first to dominate or match the performance in terms of recommendation, explanation, and multi-step critiquing. Moreover, M&Ms-VAE processes the critiques up to 25.6x faster than the best baselines. Finally, we show that our model infers coherent joint and cross generation, even under weak supervision, thanks to our multimodal-based modeling and training scheme.