Deep Learning in Recommender Systems

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Big Data and Augmented Intelligence".

Deadline for manuscript submissions: 20 December 2024 | Viewed by 3493

Special Issue Editors

Department of Computer Science and Automation, Science Faculty, University of Salamanca, Plaza de los Caídos s/n, 37008 Salamanca, Spain
Interests: data mining; web mining; machine learning; deep learning; recommender system; decision support in medicine
Special Issues, Collections and Topics in MDPI journals
BISITE Research Group, University of Salamanca, Edificio Multiusos I + D + I, 37007 Salamanca, Spain
Interests: artificial intelligence; multi-agent systems; cloud computing and distributed systems; technology-enhanced learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Deep learning is a fast-growing area that has an ever-increasing number of application domains. Recommendation systems are one such domain where deep learning offers promising results. Their use ranges from obtaining user feedback from reviews and comments on social media through sentiment analysis to the creation of models that capture the complex relationships between users and items, generally through attribute embedding. Among the many deep learning techniques are graph neural networks (GNN), which are lately gaining a significant amount of importance in recommendation systems for their ability to represent relationships. However, a major problem of GNN and, generally, all deep learning approaches, is the high sensitivity to data biases. Therefore, facing this drawback is a major concern for researchers in this area. This Special Issue provides an opportunity to address the challenges of today's deep learning-based recommender systems through the presentation of new research advances. The topics of interest include, but are not limited to, the following:

  • Deep learning methods for recommender systems;
  • GNN-based recommendation methods;
  • Implicit user feedback from sentiment analysis;
  • Bias and fairness in recommender systems based on deep learning;
  • Multi-objective recommendations based on deep learning;
  • Deep learning techniques for session-based recommendations;
  • Deep learning approaches for context-aware recommender systems.

Dr. María N. Moreno García
Dr. Fernando De la Prieta
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Future Internet is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • recommender systems
  • deep learning
  • GNN
  • implicit feedback
  • session-based recommendations
  • context-aware recommendations
  • bias
  • fairness

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

15 pages, 2026 KiB  
Article
Optimizing Session-Aware Recommenders: A Deep Dive into GRU-Based Latent Interaction Integration
Future Internet 2024, 16(2), 51; https://doi.org/10.3390/fi16020051 - 01 Feb 2024
Viewed by 595
Abstract
This study introduces session-aware recommendation models, leveraging GRU (Gated Recurrent Unit) and attention mechanisms for advanced latent interaction data integration. A primary advancement is enhancing latent context, a critical factor for boosting recommendation accuracy. We address the existing models’ rigidity by dynamically blending [...] Read more.
This study introduces session-aware recommendation models, leveraging GRU (Gated Recurrent Unit) and attention mechanisms for advanced latent interaction data integration. A primary advancement is enhancing latent context, a critical factor for boosting recommendation accuracy. We address the existing models’ rigidity by dynamically blending short-term (most recent) and long-term (historical) preferences, moving beyond static period definitions. Our approaches, pre-combination (LCII-Pre) and post-combination (LCII-Post), with fixed (Fix) and flexible learning (LP) weight configurations, are thoroughly evaluated. We conducted extensive experiments to assess our models’ performance on public datasets such as Amazon and MovieLens 1M. Notably, on the MovieLens 1M dataset, LCII-PreFix achieved a 1.85% and 2.54% higher Recall@20 than II-RNN and BERT4Rec+st+TSA, respectively. On the Steam dataset, LCII-PostLP outperformed these models by 18.66% and 5.5%. Furthermore, on the Amazon dataset, LCII showed a 2.59% and 1.89% improvement in Recall@20 over II-RNN and CAII. These results affirm the significant enhancement our models bring to session-aware recommendation systems, showcasing their potential for both academic and practical applications in the field. Full article
(This article belongs to the Special Issue Deep Learning in Recommender Systems)
Show Figures

Figure 1

21 pages, 1096 KiB  
Article
Evaluating Embeddings from Pre-Trained Language Models and Knowledge Graphs for Educational Content Recommendation
Future Internet 2024, 16(1), 12; https://doi.org/10.3390/fi16010012 - 29 Dec 2023
Cited by 1 | Viewed by 1333
Abstract
Educational content recommendation is a cornerstone of AI-enhanced learning. In particular, to facilitate navigating the diverse learning resources available on learning platforms, methods are needed for automatically linking learning materials, e.g., in order to recommend textbook content based on exercises. Such methods are [...] Read more.
Educational content recommendation is a cornerstone of AI-enhanced learning. In particular, to facilitate navigating the diverse learning resources available on learning platforms, methods are needed for automatically linking learning materials, e.g., in order to recommend textbook content based on exercises. Such methods are typically based on semantic textual similarity (STS) and the use of embeddings for text representation. However, it remains unclear what types of embeddings should be used for this task. In this study, we carry out an extensive empirical evaluation of embeddings derived from three different types of models: (i) static embeddings trained using a concept-based knowledge graph, (ii) contextual embeddings from a pre-trained language model, and (iii) contextual embeddings from a large language model (LLM). In addition to evaluating the models individually, various ensembles are explored based on different strategies for combining two models in an early vs. late fusion fashion. The evaluation is carried out using digital textbooks in Swedish for three different subjects and two types of exercises. The results show that using contextual embeddings from an LLM leads to superior performance compared to the other models, and that there is no significant improvement when combining these with static embeddings trained using a knowledge graph. When using embeddings derived from a smaller language model, however, it helps to combine them with knowledge graph embeddings. The performance of the best-performing model is high for both types of exercises, resulting in a mean Recall@3 of 0.96 and 0.95 and a mean MRR of 0.87 and 0.86 for quizzes and study questions, respectively, demonstrating the feasibility of using STS based on text embeddings for educational content recommendation. The ability to link digital learning materials in an unsupervised manner—relying only on readily available pre-trained models—facilitates the development of AI-enhanced learning. Full article
(This article belongs to the Special Issue Deep Learning in Recommender Systems)
Show Figures

Figure 1

19 pages, 2019 KiB  
Article
Dual-Channel Feature Enhanced Collaborative Filtering Recommendation Algorithm
Future Internet 2023, 15(6), 215; https://doi.org/10.3390/fi15060215 - 15 Jun 2023
Cited by 1 | Viewed by 764
Abstract
The dual-channel graph collaborative filtering recommendation algorithm (DCCF) suppresses the over-smoothing problem and overcomes the problem of expansion in local structures only in graph collaborative filtering. However, DCCF has the following problems: the fixed threshold of transfer probability leads to a decrease in [...] Read more.
The dual-channel graph collaborative filtering recommendation algorithm (DCCF) suppresses the over-smoothing problem and overcomes the problem of expansion in local structures only in graph collaborative filtering. However, DCCF has the following problems: the fixed threshold of transfer probability leads to a decrease in filtering effect of neighborhood information; the K-means clustering algorithm is prone to trapping clustering results into local optima, resulting in incomplete global interaction graphs; and the impact of time factors on the predicted results was not considered. To solve these problems, a dual-channel feature enhanced collaborative filtering recommendation algorithm (DCFECF) is proposed. Firstly, the self-attention mechanism and weighted average method are used to calculate the threshold of neighborhood transition probability for each order in local convolutional channels; secondly, the K-means++ clustering algorithm is used to determine the clustering center in the global convolutional channel, and the fuzzy C-means clustering algorithm is used for clustering to solve the local optimal problem; then, time factor is introduced to further improve predicted results, making them more accurate. Comparative experiments using normalized discounted cumulative gain (NDCG) and recall as evaluation metrics on three publicly available datasets showed that DCFECF improved by up to 2.3% and 4.1% on two metrics compared to DCCF. Full article
(This article belongs to the Special Issue Deep Learning in Recommender Systems)
Show Figures

Figure 1

Back to TopTop