Knowledge-aware Autoencoders for Explainable Recommender Systems

Bellini, Vito; Schiavone, Angelo; Noia, Tommaso Di; Ragone, Azzurra; Sciascio, Eugenio Di

doi:10.1145/3270323.3270327

Cited by 26 publications

(27 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural-symbolic Systems [297,298,299,300] KB-enhanced Systems [24,169,301,308,309,310] Deep Formulation [264,302,303,304,305] Relational Reasoning [75,312,313,314] Case-base Reasoning [316,317,318] Fig. 11.a) ( Fig.…”

Section: Hybrid Transparent and Black-box Methodsmentioning

confidence: 99%

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

et al. 2020

View full text Add to dashboard Cite

In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

show abstract

Section: Hybrid Transparent and Black-box Methodsmentioning

confidence: 99%

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We want to stress here that, although each autoencoder is trained over a not huge number of samples, in [9] we prove that recommendation results have very good performance in terms of accuracy and diversity also compared to state-of-theart algorithms. 8 To train such kinds of autoencoder, we inhibit the feedforward and backpropagation step for those neurons which result to be not connected in the KG by using a masking multiplier matrix M where rows and columns represent respectively items and features.…”

Section: Semantics-aware Autoencodermentioning

confidence: 99%

“…The strength of SemAuto is its explainability since the model, as previously said, is interpretable. To validate the explanation we are able to furnish users, we set up an online experiment leveraging on an A/B test platform we built ad-hoc [8]; thanks to 892 volunteers, we evaluated the effectiveness of our approach and compared its results to two baselines. Hence, we primarily focus on the following research questions:…”

Section: Explanationmentioning

confidence: 99%

Semantics-Aware Autoencoder

et al. 2019

Self Cite

View full text Add to dashboard Cite

Recommender Systems are widely adopted in nowadays services such as e-commerce websites, multimedia streaming platforms, and many others. They help users to find what they are looking for by suggesting relevant items leveraging their past preferences. Deep Learning models are very effective in solving the recommendation problem; as a matter of fact, many deep learning architectures have been proposed over the years. Even if deep learning models outperform many state-of-the-art algorithms, the worst disadvantage is about their interpretability: explaining the reason a specific item has been recommended to a user is quite a difficult task since the model is not interpretable. Accuracy in the recommendation is no more enough since users are also expecting a useful explanation for the suggested items. Users, on the other hand, want to know why. In this paper, we present SemAuto, a novel approach based on an Autoencoder Neural Network that makes it possible to semantically label neurons in hidden layers, thus paving the way to the model's interpretability and consequently to the explanation of a recommendation. We tested our semanticsaware approach with respect to other state-of-the-art algorithms to prove the recommendation's accuracy. Furthermore, we performed an extensive A/B test with real users to evaluate the explanation we generate.

show abstract

“…producing transparent recommendations and explanations. An example of their explanation style is shown inFigure 2.9.The study of[8] focuses on the issue of explaining the output of a black box recommender system. In this work, the recommender system is built using Autoencoder Neural Network technique that is also aware of the Knowledge Graphs retrieved from the Semantic Web.…”

mentioning

confidence: 99%

“…8 shows three graphs of the MEP, MER, and xF-score performance of all models when these metrics use the neighborhood explainability graph in the book domain. PMF was the winner, followed by AMF, while the performance of all other models was low.…”

mentioning

confidence: 99%

An explainable recommender system based on semantically-aware matrix factorization.

Alshammari¹

View full text Add to dashboard Cite

show abstract

Knowledge-aware Autoencoders for Explainable Recommender Systems

Cited by 26 publications

References 19 publications

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Semantics-Aware Autoencoder

An explainable recommender system based on semantically-aware matrix factorization.

Contact Info

Product

Resources

About