A Look Inside the Black-Box: Towards the Interpretability of Conditioned Variational Autoencoder for Collaborative Filtering

@article{Carraro2020ALI,
  title={A Look Inside the Black-Box: Towards the Interpretability of Conditioned Variational Autoencoder for Collaborative Filtering},
  author={Tommaso Carraro and Mirko Polato and Fabio Aiolli},
  journal={Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization},
  year={2020}
}
Deep learning-based recommender systems are nowadays defining the state-of-the-art. Unfortunately, their hard interpretability restrains their application in scenarios in which explainability is required/desirable. Many efforts have been devoted to injecting explainable information inside deep models. However, there is still a lot of work that needs to be done to fill this gap. In this paper, we take a step in this direction by providing an intuitive interpretation of the inner representation… 
1 Citations

Figures from this paper

References

SHOWING 1-10 OF 16 REFERENCES
Conditioned Variational Autoencoder for top-N item recommendation
TLDR
A Conditioned Variational Autoencoder for constrained top-N item recommendation where the recommended items must satisfy a given condition is proposed, and it is suggested that C-VAE can be used in other recommendation scenarios, such as context-aware recommendation.
An Explainable Autoencoder For Collaborative Filtering Recommendation
TLDR
This work designs an explainable recommendation system using an Autoencoder model whose predictions can be explained using the neighborhood based explanation style.
Variational Autoencoders for Collaborative Filtering
TLDR
A generative model with multinomial likelihood and use Bayesian inference for parameter estimation is introduced and the pros and cons of employing a principledBayesian inference approach are identified and characterize settings where it provides the most significant improvements.
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificial
Neural Collaborative Filtering
TLDR
This work strives to develop techniques based on neural networks to tackle the key problem in recommendation --- collaborative filtering --- on the basis of implicit feedback, and presents a general framework named NCF, short for Neural network-based Collaborative Filtering.
Hybrid Collaborative Recommendation via Semi-AutoEncoder
TLDR
A novel structure, Semi-AutoEncoder, based on AutoEncoder is generalized into a hybrid collaborative filtering model for rating prediction as well as personalized top-n recommendations, demonstrating its state-of-the-art performances.
Auto-Encoding Variational Bayes
TLDR
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Knowledge-aware Autoencoders for Explainable Recommender Systems
TLDR
This paper evaluates how different information encoded in a Knowledge Graph are perceived by users when they are adopted to show them an explanation and compares how the use of categorical information, factual one or a mixture of them both in building explanations, affect explanatory criteria for a recommender system.
CFGAN: A Generic Collaborative Filtering Framework based on Generative Adversarial Networks
TLDR
This paper proposes a novel GAN-based collaborative filtering (CF) framework to provide higher accuracy in recommendation and validate that vector-wise adversarial training employed in CFGAN is really effective to solve the problem of existing GAn-based CF methods.
Principal component analysis: a review and recent developments
  • I. Jolliffe, J. Cadima
  • Computer Science
    Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
  • 2016
TLDR
The basic ideas of PCA are introduced, discussing what it can and cannot do, and some variants of the technique have been developed that are tailored to various different data types and structures.
...
...