The concept of Federated Learning (FL) is a distributed-based machine learning (ML) approach that trains its model using edge devices. Its focus is on maintaining privacy by transmitting gradient updates along with users' learning parameters to the global server in the process of training as well as preserving the integrity of data on the user-end of internet of medical things (IoMT) devices. Instead of a direct use of user data, the training which is performed on the global server is done on the parameters while the model modification is performed locally on IoMT devices. But the major drawback of this federated learning approach is its inability to preserve user privacy complete thereby resulting in gradients leakage. Thus, this study first presents a summary of the process of learning and further proposes a new approach for federated medical recommender system which employs the use of homomorphic cryptography to ensure a more privacy-preservation of user gradients during recommendations. The experimental results indicate an insignificant decrease with respect to the metrics of accuracy, however, a greater percentage of user-privacy is achieved. Further analysis also shows that performing computations on encrypted gradients at the global server scarcely has any impact on the output of the recommendation while guaranteeing a supplementary secure channel for transmitting user-based gradients back and forth the global server. The result of this analysis indicates that the performance of federated stochastic modification minimized gradient (FSMMG) algorithm is greatly increased at every given increase in the number of users and a good convergence is achieved as well. Also, experiments indicate that when compared against other existing techniques, the proposed FSMMG outperforms at 98.3% encryption accuracy.

With the proliferation of privacy issues surrounding the Internet of Medical (IoMT) recommender system data, this study presents a Secure Recommendation and Training Technique (SERTT) which is contingent on a combination of both federated learning and blockchain approaches. Firstly, the study presents a new framework for recording, sorting, and transmission of IoMT data while incorporating blockchain to ensure that the IoMT data transmitted to cloud servers is not made vulnerable by the sharing of the original data. Secondly, by utilizing medical data, the study designs a Recommender Data Management Neural Architecture (REDMANA) which is based on federated learning and model searching training framework. The proposed technique guarantees that the model gradients which are trained by each node are not disclosed all through the universal training and modeling procedure. This makes the raw data inaccessible to either the IoMT data provider or the user. Considering that the model ensures that users can only obtain their necessary inquiries, neither medical data suppliers nor users can obtain access to raw data. Thus, it reduces the issues of safeguarding medical data sets to the issues of securing data processing. Using numerical analysis and experiments the proposed technique is compared with other existing techniques, the result shows that the proposed SERTT system is efficient and secures recommender data management training and modeling technique and that it performs previously designed techniques as compared.

Recommender systems (RS) have been developed to make personalized suggestions and enrich users’ preferences in various online applications to address the information explosion problems. However, traditional recommender-based systems act as black boxes, not presenting the user with insights into the system logic or reasons for recommendations. Recently, generating explainable recommendations with deep knowledge graphs (DKG) has attracted significant attention. DKG is a subset of explainable artificial intelligence (XAI) that utilizes the strengths of deep learning (DL) algorithms to learn, provide high-quality predictions, and complement the weaknesses of knowledge graphs (KGs) in the explainability of recommendations. DKG-based models can provide more meaningful, insightful, and trustworthy justifications for recommended items and alleviate the information explosion problems. Although several studies have been carried out on RS, only a few papers have been published on DKG-based methodologies, and a review in this new research direction is still insufficiently explored. To fill this literature gap, this paper uses a systematic literature review framework to survey the recently published papers from 2018 to 2022 in the landscape of DKG and XAI. We analyze how the methods produced in these papers extract essential information from graph-based representations to improve recommendations’ accuracy, explainability, and reliability. From the perspective of the leveraged knowledge-graph related information and how the knowledge-graph or path embeddings are learned and integrated with the DL methods, we carefully select and classify these published works into four main categories: the Two-stage explainable learning methods, the Joint-stage explainable learning methods, the Path-embedding explainable learning methods, and the Propagation explainable learning methods. We further summarize these works according to the characteristics of the approaches and the recommendation scenarios to facilitate the ease of checking the literature. We finally conclude by discussing some open challenges left for future research in this vibrant field.

Recommender systems (RS) have been widely deployed in many real-world applications, but usually suffer from the long-standing user/item cold-start problem. As a promising approach, cross-domain recommendation (CDR), which has attracted a surge of interest, aims to transfer the user preferences observed in the source domain to make recommendations in the target domain. Traditional machine learning and deep learning methods are not designed to learn from complex data representations such as graphs, manifolds and 3D objects. However, current trends in data generation include these complex data representations. In addition, existing research works do not consider the complex dimensions and the locality structure of items, which however, contain more discriminative information essential for improving the performance accuracy of the recommender system. Furthermore, similar outcomes between test samples and their neighboring training data restrained in the kernel space are not fully realized from the recommended objects belonging to the same object category to capture the embedded discriminative information effectively. These challenges leave the problem of sparsity and the cold-start of items/users unsolved and hence impede the performance of the cross-domain recommender system, causing it to suggest less relevant and undistinguished items to the user. To handle these challenges, we propose a novel deep learning (DL) method, Discriminative Geometric Deep Learning (D-GDL) for cross-domain recommender systems. In the proposed D-GDL, a discriminative function based on sparse local sensitivity is introduced into the structure of the DL network. In the D-GDL, a local representation learning (i.e., a local sensitivity-based deep convolutional belief network) is introduced into the structure of the DL network to effectively capture the local geometric and visual information from the structure of the recommended 3D objects. A kernel-based method (i.e., a local sensitivity deep belief network) is also incorporated into the structure of the DL framework to map the complex structure of recommended objects into high dimensional feature space and achieve an effective recognition result. An improved kernel density estimator is created to serve as a weighing function in building a high dimensional feature space, which makes it more resistant to geometric noise and computation performance. The experiment results show that the proposed D-GDL significantly outperforms the state-of-the-art methods in both sparse and dense settings for cross-domain recommendation tasks.

Next Basket Recommender systems in e-commerce face challenges such as data sparsity, evolving user preferences, and cross-domain transfer limitations. We propose the Temporal Dual-Target Cross-Domain Recommendation Framework (T-DualCRF) to address these issues. T-DualCRF integrates multi-channel embeddings (user feedback, knowledge graphs, temporal features) and a dual-target mechanism for robust cross-domain knowledge transfer. It also employs time-aware embeddings and a temporal heterogeneous graph to model user preference changes. The framework’s hybrid optimization mechanism, combining the Multi-Verse Optimizer and Whale Optimization Algorithm, enhances recommendation accuracy and stability. Experimental results on Amazon datasets show that T-DualCRF significantly outperforms existing models, with improvements of up to 20% in F1-score and 17% in NDCG, effectively mitigating data sparsity and adapting to real-time user behavior changes.