FIGURE 4 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
With the advent of information technology, the amount of online data generation has been massive. Recommendation systems have become an effective tool in filtering information and solving the problem of information overload. Machine learning algorithms to build these recommendation systems require well-balanced data in terms of class distribution,...
Context in source publication
Context 1
... Fig. 4, we present the architecture of auxiliary classifier that almost resembles the discriminator architecture except for the fact that we do not add any noise to the numerical columns, we do not take any condition or class label in the auxiliary classifier, and at the final layer, we implement a sigmoid activation function to get the ...
Similar publications
With the rapid development of science and technology, the college music big data management system also needs a computer-aided data model for optimization. In order to improve the efficiency of computer-aided teaching of the music big data management system in colleges and universities, this paper analyzes and processes the music database of music...
Citations
... In an attempt to address the persistent challenge of imbalanced data, a proposed solution involves a hybrid generative adversarial network (GAN) approach, specifically utilizing a conditional Wasserstein GAN with a gradient penalty to generate tabular data [25]. To enhance focus on minority classes, an auxiliary classifier loss is incorporated into this approach. ...
... Data generation approaches Statistical-based generation [8,9] Machine learning-based generation [10][11][12][13][14][15][16][17][18][19][20][21][22][23] Data characteristics Numerical data generation [24] Categorical data generation [25] Temporal data generation [26,27] Privacy preservation [28][29][30][31][32] ...
The rapid advancement of data generation techniques has spurred innovation across multiple domains. This comprehensive review delves into the realm of data generation methodologies, with a keen focus on statistical and machine learning-based approaches. Notably, novel strategies like the divide-and-conquer (DC) approach and cutting-edge models such as GANBLR have emerged to tackle a spectrum of challenges, spanning from preserving intricate data relationships to enhancing interpretability. Furthermore, the integration of generative adversarial networks (GANs) has sparked a revolution in data generation across sectors like healthcare, cybersecurity, and retail. This review meticulously examines how these techniques mitigate issues such as class imbalance, data scarcity, and privacy concerns. Through a meticulous analysis of evaluation metrics and diverse applications, it underscores the efficacy and potential of synthetic data in refining predictive models and decision-making software. Concluding with insights into prospective research trajectories and the evolving role of synthetic data in propelling machine learning and data-driven solutions across disciplines, this work provides a holistic understanding of the transformative power of contemporary data generation methodologies.
... Byun et al. [64] suggested a hybrid GAN technique to address the issue of data imbalance and improve the effectiveness of recommendation systems. To create tabular data with both numbers and categorical values, the test used conditional Wasserstein GAN with gradient penalty. ...
The growing demand for applications based on Generative Adversarial Networks (GANs) has prompted substantial study and analysis in a variety of fields. GAN models have applications in NLP, architectural design, text-to-image, image-to-image, 3D object production, audio-to-image, and prediction. This technique is an important tool for both production and prediction, notably in identifying falsely created pictures, particularly in the context of face forgeries, to ensure visual integrity and security. GANs are critical in determining visual credibility in social media by identifying and assessing forgeries. As the field progresses, a variety of GAN variations arise, along with the development of diverse assessment techniques for assessing model efficacy and scope. The article provides a complete and exhaustive overview of the most recent advances in GAN model designs, the efficacy and breadth of GAN variations, GAN limits and potential solutions, and the blooming ecosystem of upcoming GAN tool domains. Additionally, it investigates key measures like as Inception Score (IS) and Fréchet Inception Distance (FID) as critical benchmarks for improving GAN performance in contrast to existing approaches.
... The recurrent generative adversarial network (RecGAN) [24] combines a recurrent neural network (RNN) and a GAN to process temporal patterns. Unbalanced datasets are managed using a Wasserstein GAN acting as a generator and the packing generative adversarial network (PacGAN) as a discriminator [25]. Finally, a conditional generative adversarial network (CGAN) performs a conditional generation of ratings [26]. ...
... Finally, the conceptual problem of the 'quality paradox' inherent in these quality measures is heavily present in the RS scenario, where a generated dataset should not be too similar to the source, otherwise it would not be useful, and should not be too different from the source, otherwise it would not be representative. Therefore, research papers that generate synthetic datasets [23][24][25] test them by running several CF Machine Learning models and comparing the results obtained on different instances of the generated datasets from the same source data. This is the strategy that our paper follows in its 'Results' section. ...
... This particularly happens if the GAN suffers from mode collapse. In these cases, there are samples with identical information, and we create the set H where duplicated samples are removed (25). ...
Currently, generative applications are reshaping different fields, such as art, computer vision, speech processing, and natural language. The computer science personalization area is increasingly relevant since large companies such as Spotify, Netflix, TripAdvisor, Amazon, and Google use recommender systems. Then, it is rational to expect that generative learning will increasingly be used to improve current recommender systems. In this paper, a method is proposed to generate synthetic recommender system datasets that can be used to test the recommendation performance and accuracy of a company on different simulated scenarios, such as large increases in their dataset sizes, number of users, or number of items. Specifically, an improvement in the state-of-the-art method is proposed by applying the Wasserstein concept to the generative adversarial network for recommender systems (GANRS) seminal method to generate synthetic datasets. The results show that our proposed method reduces the mode collapse, increases the sizes of the synthetic datasets, improves their ratings distributions, and maintains the potential to choose the desired number of users, number of items, and starting size of the dataset. Both the baseline GANRS and the proposed Wasserstein-based WGANRS deep learning architectures generate fake profiles from dense, short, and continuous embeddings in the latent space instead of the sparse, large, and discrete raw samples that previous GAN models used as a source. To enable reproducibility, the Python and Keras codes are provided in open repositories along with the synthetic datasets generated to test the proposed architecture (https://github.com/jesusbobadilla/ganrs.git).
Graphical abstract
... In this work [9] proposes a hybrid GAN approach to address the data imbalance problem and improve the performance of recommendation systems. The authors implement a conditional Wasserstein GAN with gradient penalty to generate tabular data that includes both numerical and categorical values. ...
... Emulation of user behavior dynamics, Cascading DQN algorithm with application to real-world data [9] Data imbalance in recommendation systems ...
Generative Adversarial Networks (GANs) have emerged as powerful tools in the realm of artificial intelligence, reshaping various domains, from image generation to text synthesis and music composition. In recent years, researchers have ventured into the realm of integrating GANs into recommendation systems, driven by the desire to elevate the quality of recommendations. This article presents an in-depth exploration of the current landscape surrounding the incorporation of GANs in recommendation systems. Researchers have harnessed the potential of GANs to craft highly personalized recommendations by incorporating user and item features. Notably, techniques like conditional GANs have been employed to consider user demographics, browsing history, and item attributes, enabling the tailoring of recommendations to individual preferences. Nevertheless, challenges have surfaced, including issues related to training stability, mode collapse, scalability limitations, and data privacy concerns in the application of GANs to recommendation systems. Diligent and persistent research endeavors are actively addressing these challenges with the overarching goal of not only overcoming the hurdles but also enhancing the stability and performance of GANs within recommendation systems. This article serves as a comprehensive guide to the current state of GANs in recommendation systems, offering insights into their potential and the evolving landscape of research and development in this field.
... The traditional Recommender Systems encounter some problems [118] which can be solved by generative AI. VAE can be combined(hybrid) with other models to generate items and to mitigate recommender system's problems [119], [120], [121] GAN can also be combined with other models to generate items and to solve the problems of recommender system [122], [123]. ...
... In their article [90] introduced a GAN-based framework using positive-unlabeled sampling, which was shown to be effective and efficient in comparison to other baselines. [123] incorporated user trust information into a GAN-based recommender system, resulting in improved recommendation accuracy, and [43] focused on the security aspect, using a modified GAN architecture to detect data pollution attacks on recommender systems. These studies collectively demonstrate the potential of GANs in enhancing the performance and security of recommender systems. ...
Recommender Systems (RSs), which generate personalized content, have become a technological tool with diverse applications for users. While numerous RSs have been proposed and successfully implemented across various domains, traditional AI-based RSs still encounter certain challenges, such as data sparsity, cold start, and diversity. Generative Artificial Intelligence in recommender systems is a recent advancement used by platforms like Netflix, Spotify, and Amazon to recommend items, news, videos, audios, goods, and services to their customers/users or to personalize experiences for their customers/users. The main purpose of this review is to compare traditional AI-based recommender systems with generative AI-based recommender systems. A total of fifty-two (52) papers, published between 2019 and February 2024, were selected from six major online libraries. To get a more comprehensive understanding of the selected study, we reviewed the selected studies techniques, and the models, datasets, and metrics used. Our systematic review reveals that generative AI models, such as generative adversarial networks (GANs), variational autoencoder (VAEs) and autoencoders have been widely used in recommender systems and they perform better than traditional AI techniques. Among the 30 datasets analyzed, MovieLens was the most frequently used, accounting for 33%, while Amazon datasets accounted for 11%, Recall and RSME are the most commonly used metrics. Our literature review offers understandings into the Generative AI techniques used across different recommender systems and provides suggestions for the future research. Finally, we elaborated on open issues and discussed current and future trends in generative AI-based recommendation systems.
... A GAN-based approach to handle the problem of data imbalance in recommender systems was proposed by [36]. They made use of conditional Wasserstein GAN to generate missing data for minority class to perform recommendations. ...
The aim of personalized news recommendation is to suggest news stories to the users that are most interesting for them. To improve the user experience, it is important that these news items are not only relevant to the user but also get recommended to them as soon as they are available. The inability of traditional collaborative filtering approach to recommend such cold start items has led to techniques that incorporate latent features of items in order to make cold start recommendations such as content based filtering and deep neural network-based approaches. However, these existing techniques do not make use of any collaborative information between users and items as well as latent features at the same time and thus fail to provide any serendipity which is an important aspect of any recommender system. Moreover, these underlying collaborative signals between users and items are crucial to improving the overall quality of recommender systems and can also be utilized to make cold start recommendations. In this paper, we propose the Generative Collaborative Zero-Shot Recommender System framework (GCZRec) which makes use of both the latent user and item features as well as the underlying collaborative information to generate both warm start and cold start recommendations. We evaluate our framework for news recommendation task given cold start and warm start cases for both users and news items. We also discuss that our model can be plugged in and used as preprocessing to improve the performance of an existing recommender system.
... In one study, GANs were trained using an adversarial setting, where the generator and discriminator constantly tried to outsmart each other. This process forced the generator to learn to produce increasingly realistic data while the discriminator learned to become better at differentiating between real and fake data [14]. ...
(1) Background: The categorization of recurrent and non-recurrent odontogenic keratocyst is complex and challenging for both clinicians and pathologists. What sets this cyst apart is its aggressive nature and high likelihood of recurrence. Despite identifying various predictive clinical/radiological/histopathological parameters, clinicians still face difficulties in therapeutic management due to its inherent aggressive nature. This research aims to build a pipeline system that accurately detects recurring and non-recurring OKC. (2) Objective: To automate the risk stratification of OKCs as recurring or non-recurring based on whole slide images (WSIs) using an attention-based image sequence analyzer (ABISA). (3) Materials and methods: The presented architecture combines transformer-based self-attention mechanisms with sequential modeling using LSTM (long short-term memory) to predict the class label. This architecture leverages self-attention to capture spatial dependencies in image patches and LSTM to capture sequential dependencies across patches or frames, making it suitable for this image analysis. These two powerful combinations were integrated and applied on a custom dataset of 48 labeled WSIs (508 tiled images) generated from the highest zoom level WSI. (4) Results: The proposed ABISA algorithm attained 0.98, 1.0, and 0.98 testing accuracy, recall, and area under the curve, respectively, whereas VGG16, VGG19, and Inception V3, standard vision transformer attained testing accuracies of 0.80, 0.73, 0.82, 0.91, respectively. ABISA used 58% fewer trainable parameters than the standard vision transformer. (5) Conclusions: The proposed novel ABISA algorithm was integrated into a risk stratification pipeline to automate the detection of recurring OKC significantly faster, thus allowing the pathologist to define risk stratification faster.
... Therefore, it is necessary to come up with a solution for the dilemma of how to use these data to improve people's lives. The recommendation system is to recommend a set of items that meet user preferences for users in massive data, which can well solve the problem of information overload (Shafqat & Byun, 2022;Wang et al., 2023). Therefore, an efficient and credible personalised recommendation system is needed by all major platforms. ...
In the age of big data, recipe recommendation is of great significance. It can recommend recipes in line with the user's eating habits in massive data. Compared with other recommendation tasks, recipe recommendation is influenced by multiple aspects and requires fine-grained learning to obtain entity representations. Therefore, the traditional recommendation method cannot meet people's requirements. In this paper, we propose the Collaborative Knowledge Propagation Graph Attention Network for Recipes Recommendation (CGRS). This method designs collaborative information propagation to make full use of user interaction and recipe attribute information to meet the needs of multiple influencing factors. Use the graph attention feature learning network to obtain the high-order feature information of the entity to meet the demand for fine-grained representation. Specifically, the method first obtains the multi-hop triplet sets of users and recipes through a collaborative message propagation strategy. Then utilises a graph attention feature learning layer to learn the topological proximity structure features of the triplet sets. Obtain high-level semantic information of entities by superimposing network layers. Design an attention aggregator at the prediction layer to refine the embedding representation of entities. Finally predict the user-recipe interaction probability. Experimental results prove the advancement and effectiveness of CGRS.
... This means that many items have been supplied to users, leading to the possibility of users not being able to make quick decisions according to their interests and requirements [2]. A recommender system (RS) is an intelligent and successful information filtering system that offers items of interest to users [3], thus helping them to deal with difficulties related to information overload [4,5], and providing a personalized top items list per user. ...
Recently, social trust information has become a significant additional factor in obtaining high-quality recommendations. It has also helped to alleviate the problems of collaborative filtering. In this paper, we exploit explicit and implicit trust relations and incorporate them to take advantage of more ratings (as they exist) of trusted neighbors to mitigate the sparsity issue. We further apply the idea of weighted voting of the ensemble classifier for the election of the most appropriate trust neighbors' ratings. Additionally, the certainty of these elected rating values was confirmed by calculating their reliability using a modified version of Pearson's Correlation Coefficient. Finally, we applied the K-Nearest Neighbors method with a linear combination of original and trust-elected ratings using a contribution weight to obtain the best prediction value. Extensive experiments were conducted on two real-world datasets to show that our proposed approach outperformed all comparable algorithms in terms of both coverage and accuracy. Specifically, the improvement ratio ranged approximately from 4% as a minimum to 20% on FilmTrust, and to 10% on Epinions as a maximum in terms of F-measure between the inverse of Mean Absolute Error (accuracy) and coverage.
... They used six different classification algorithms for experimental analysis of the effect of oversampling. Shafqat and Byun [23] used the data from an online shopping mall in Jeju. They proposed a hybrid GAN to solve the data imbalance problem and improve the recommendation system's performance. ...
Class imbalance is a prevalent problem that not only reduces the performance of the machine learning techniques but also causes the lacking of the inherent complex characteristics of data. Though the researchers have proposed various ways to deal with the problem, they have yet to consider how to select a proper treatment, especially when uncertainty levels are high. Applying rough-fuzzy theory to the imbalanced data learning problem could be a promising research direction that generates the synthetic data and removes the outliers. The proposed work identifies the positive, boundary, and negative regions of the target set using the rough set theory and removes the objects in the negative region as outliers. It also explores the positive and boundary regions of the rough set by applying the fuzzy theory to generate the samples of the minority class and remove the samples of the majority class. Thus the proposed rough-fuzzy approach performs both oversampling and undersampling to handle the imbalanced class problem. The experimental results demonstrate that the novel technique allows qualitative and quantitative data handling.
