Dynamic User Preferences Research Articles

Retraction Note: Big data analytics for dynamic network slicing in 5G and beyond with dynamic user preferences

Retraction Note: Big data analytics for dynamic network slicing in 5G and beyond with dynamic user preferences

Multi-Interest Multi-Round Conversational Recommendation System with Fuzzy Feedback Based User Simulator

Conversational recommendation system (CRS) is able to obtain fine-grained and dynamic user preferences based on interactive dialogue. Previous CRS assumes that the user has a clear target item, which often deviates from the real scenario. The user may have a clear single preference for some attribute types (e.g., brand) of items, while for other attribute types (e.g., color), the user may have multiple preferences or even no clear preferences, which leads to multiple acceptable items under multiple combinations of attribute instances. Furthermore, previous works assume that users would provide clear responses to any questions asked by the system. And, they also assume that users would be dedicated to the target item, that is, user would answer “yes” to the attribute corresponding to the target item and answer “no” to other attributes. However, users’ responses to attributes are not completely dependent on target items, but also influenced by users’ inherent interests. Besides, for some over-specific or equivocal questions, the feedback of user might not be clear (“yes”/“no”) and user might give some fuzzy response like “I don’t know”. To address the aforementioned issues, we first propose a more realistic conversational recommendation learning setting, namely Multi-Interest Multi-round Conversational Recommendation (MIMCR), where users may have multiple interests in attribute instance combinations and accept multiple items with partially overlapped combinations of attribute instances. To effectively cope with MIMCR, we propose a novel learning framework, namely Multiple Choice questions based on Multi-Interest Policy Learning. Moreover, we further propose a more realistic User-centric User Simulator with Fuzzy Feedback (UUSFF), which naturally calibrates the user response with additional fuzzy feedback based on user’s inherent preference. To better match the new scenario UUSFF, we propose a simple but effective adaption method for different backbones. Extensive experimental results on several datasets demonstrate the superiority of our methods for the proposed settings.

Hypergraph-enhanced multi-interest learning for multi-behavior sequential recommendation

Learning dynamic user preference has become an increasingly important component for many online platforms (e.g., video-sharing sites, e-commerce systems) to make sequential recommendations. In these platforms, user–item interactive behaviors are often multi-typed (e.g., click, add-to-favorite, purchase) with complex cross-type behavior inter-dependencies. Consequently, the multi-behavior sequence recommendation (MBSR) is gaining growing attention to meet practical application needs. However, most of the existing MBSR methods have not adequately explored the latent multi-dimensional real interests and multi-order multi-behavior dependencies, hampering the accurate inference of user preferences and further limiting recommendation performance. To this end, we devise a Hypergraph-Enhanced Multi-interest Learning Framework (HEML) equipped with a time-sensitive sequence module and a temporal-free hypergraph module, i.e., to learn both multi-interest and multi-behavior dependencies. For multi-interest extraction, a dual-scale transformer is designed to encode sequence patterns from coarse-grained level to fine-grained level, respectively. A classic capsule network is then exploited to extract the hidden two-level multi-interests explicitly. An interest-matching mechanism is presented to further adaptively match the most relevant general interests of the users at the current time. For multi-behavior dependencies, a user-tailored multi-behavior hypergraph is established to capture global multi-order (e.g., triadic or even high-order) dependencies across behaviors. A lightweight hypergraph convolutional network is then designed to perform a two-stage refined ‘node-hyperedge-node’ feature transformation on the hypergraph structure. We also introduce a cross-view co-guided learning mechanism to encourage the aggregation of sequence and hypergraph information across views. Numerous empirical investigations conducted across three authentic datasets demonstrate the consistent superiority of HEML over a diverse array of recommendation methodologies. We have released the implementation code at https://github.com/Breeze-del/HEMLCODE.

A graph attention network with contrastive learning for temporal review-based recommendations

In recent years, review-based recommendations have recently attracted extensive attention from researchers. However, applying reviews to improve recommendation performance still faces some problems that remain unsolved: (1) Most existing works cannot capture the time-varying user preferences and high-order collaborative features. (2) Most of the existing works often use supervised learning to train models with a limited interaction between users and items, which is not sufficient to learn the more accurate recommendation models. To overcome these problems, we propose a new Graph Attention Network with Contrastive Learning for temporary review-based recommendation, named GANCL. Specifically, to capture dynamic user preferences and high-order collaborative features, we design a user–item bipartite graph with time-series review information and ratings as its edges, and then use the graph attention and different gating mechanisms to extract the corresponding features. To make full use of the limited interaction between the users and items, we use the contrastive learning paradigm for the nodes and edges in the bipartite graph to more effectively model the user–item interaction. A large number of experiments on five public data from Amazon prove that the performance of the GANCL is improved by 2.76% and 2.83% respectively compared with the state-of-the-art algorithms in MSE and MAE.

Considering user dynamic preferences for mitigating negative effects of long-tail in recommender systems

Recommender systems focusing solely on accuracy, defined as the similarity of items to users' interests, often encounter the long-tail problem. This issue arises because short-head items, having received more ratings, dominate users' recommendation lists, while long-tail items, which are less popular, are underrepresented to maintain recommendation list precision. Unlike other approaches that treat users' preferences as fixed, this work advocates for considering dynamic user preferences to address the long-tail problem effectively. Specifically, we demonstrate two key observations: 1) users register varying proportions of ratings for long-tail and short-head items over time, and 2) item popularity is dynamic and undergoes changes over time. Consequently, recommendation lists can be dynamically adjusted to include different proportions of popular and unpopular items. We propose adapting the recommendation lists based on users' tenure in the system and their accrued ratings, allowing for higher inclusion of long-tail items for users with longer membership and more registered ratings. Additionally, we maintain an updated list of popular items as their popularity can fluctuate over time. In this study, modifications are made to the memetic algorithm to leverage users' dynamic preferences, demonstrating notable improvements. The proposed method achieves a precision of 90%, surpassing related works by 7% in addressing the long-tail problem, leading to increased participation of unpopular items in recommendation lists.

FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System

The filter bubble is a notorious issue in Recommender Systems (RSs), which describes the phenomenon whereby users are exposed to a limited and narrow range of information or content that reinforces their existing dominant preferences and beliefs. This results in a lack of exposure to diverse and varied content. Many existing works have predominantly examined filter bubbles in static or relatively-static recommendation settings. However, filter bubbles will be continuously intensified over time due to the feedback loop between the user and the system in the real-world online recommendation. To address these issues, we propose a novel paradigm, Multi-Facet Preference Learning for Pricking Filter Bubbles in Conversational Recommender System (FacetCRS), which aims to burst filter bubbles in the conversational recommender system (CRS) through timely user-item interactions via natural language conversations. By considering diverse user preferences and intentions, FacetCRS automatically model user preference into multi-facets, including entity-, word-, context-, and review-facet, to capture diverse and dynamic user preferences to prick filter bubbles in the CRS. It is an end-to-end CRS framework to adaptively learn representations of various levels of preference facet and diverse types of external knowledge. Extensive experiments on two publicly available benchmark datasets demonstrate that our proposed method achieves state-of-the-art performance in mitigating filter bubbles and enhancing recommendation quality in CRS.

MADM-based network selection and handover management in heterogeneous network: A comprehensive comparative analysis

As radio access technologies, processing speeds, and multimode interfaces of low-powered portable devices continue to advance, the future of wireless communication is envisioned to offer pervasive network coverage, high data rates, and a wide spectrum of services while maintaining high mobility. High data rates, wide range of services, huge connectivity, capacity, and good geographic coverage are being provided by the ultra-dense deployment of small base stations (BSs) in heterogeneous wireless networks (HWN). But dense deployment of small BSs, high mobility, network heterogeneity, imbalanced traffic, and dynamic user preferences lead to frequent handover. Network overhead, excessive energy consumption, and a decrease in service quality and user satisfaction can be due to frequent handover. So, handover management is one of the crucial challenges in the implementation of 5G and beyond in HWNs for ensuring seamless connectivity, energy efficiency, and the required quality of services and experiences. The effectiveness of handover decisions in HWNs relies on the implementation of a suitable network selection mechanism. Multi-attribute decision-making (MADM) is being used to model and analyze appropriate network selection complexities by considering a broad spectrum of intricate and conflicting decision criteria for efficient handover decisions in HWN. This article extensively explores, compares, and analyzes vital MADM techniques utilized for modeling appropriate network selection strategies in terms of algorithmic strategies, cardinality, types and significance of decision attributes, and network utilities. This article also examines, analyzes, and recognizes the recent mobility management challenges and trends in utilizing MADM strategies to tackle network selection issues in high-speed HWNs.

Time-aware multi-behavior graph network model for complex group behavior prediction

In the multifaceted landscape of social networks, user behaviors manifest in various patterns, contributing to the diversity of group behaviors. Current research on group behavior modeling often limits its focus to single behavioral types, overlooking the interplay among different behaviors. To bridge this gap, we introduce Time-aware Multi-behavior Graph Network (TMGN) model. This model integrates heterogeneous graph representation learning to discern patterns in user-item interactions across multiple behaviors, capitalizing on dynamic user preferences through time encoding strategy. Additionally, TMGN harnesses a self-attention multi-behavior fusion network to effectively amalgamate characteristics of diverse behaviors, which can tackle the complex hierarchical dependences among distinct group behaviors. Empirical validation on Yelp and the MovieLens 10M datasets demonstrates that TMGN outperforms the leading baseline model, KHGT, by 5.9 %, 23.93 %, and 8.57 % in HR@5, NDCG@5, and Recall@5 metrics, respectively. The findings offer substantial theoretical and practical insights for predicting group behavior on online platforms.

BiLSTCAN: A Novel SRS-Based Bidirectional Long Short-Term Capsule Attention Network for Dynamic User Preference and Next-Item Recommendation

BiLSTCAN: A Novel SRS-Based Bidirectional Long Short-Term Capsule Attention Network for Dynamic User Preference and Next-Item Recommendation

RETRACTED ARTICLE: Big data analytics for dynamic network slicing in 5G and beyond with dynamic user preferences

RETRACTED ARTICLE: Big data analytics for dynamic network slicing in 5G and beyond with dynamic user preferences

Delving Deep into NutriScan: Automated Nutrition Table Extraction and Ingredient Recognition

Abstract: Our paper introduces an innovative solution for automating the detection of nutrition tables and recognition of ingredients on packaged food products, addressing the growing demand for tools that facilitate the extraction of essential dietary information from food packaging. The increasing interest in healthy eating and dietary awareness underscores the need for precise and efficient tools to assist consumers and health-conscious individuals in making well-informed food choices. Harnessing state-of-the-art technology, we enhance the accuracy of nutrition table and ingredient detection through fine-tuning the EfficientDet model. We further extract textual content from these tables using PaddleOCR a sophisticated optical character recognition tool. Additionally, we employ regular expressions to meticulously capture crucial nutritional details, including salt or sodium content, carbohydrates, total fat, saturated fat, trans fat, protein values, additives, and allergens found in the product. To empower users in their dietary decision-making, we introduce a dynamic user preference system. Users can tailor their dietary requirements, specifying allergies and preferences for sugar, saturated fat, total fat, or salt content. Our system then evaluates food products and offers personalized recommendations including the nutri-score, indicating their alignment with the user's health goals. Extensive experimentation and evaluation confirm the high accuracy and efficiency of our method in both nutrition table and ingredient recognition. These paper underscores the transformative potential of our approach, which can revolutionize the accessibility of dietary information, encourage healthier eating habits, and promote dietary transparency

T3SRS: Tensor Train Transformer for compressing sequential recommender systems

In recent years, attention mechanisms have gained popularity in sequential recommender systems (SRSs) due to obtaining dynamic user preferences efficiently. However, over-parameterization of these models often increases the risk of overfitting. To address this challenge, we propose a Transformer model based on tensor train networks. Initially, we propose a tensor train layer (TTL) to accommodate the original weight matrix, thus reducing the space complexity of the mapping layer. Based on the TTL, we reconfigure the multi-head attention module and the position-wise feed-forward network. Finally, a tensor train layer replaces the output layer to complete the overall compression. According to the experimental results, the proposed model compresses SRSs parameters effectively, achieving compression rates of 76.2%−85.0%, while maintaining or enhancing sequence recommendation performance. To our knowledge, the Tensor Train Transformer is the first model compression approach for Transformer-based SRSs, and the model is broadly applicable.

SKYLINE QUERY BASED ON USER PREFERENCES IN CELLULAR ENVIRONMENTS

The recommendation system is an important tool for providing personalized suggestions to users about products or services. However, previous research on individual recommendation systems using skyline queries has not considered the dynamic personal preferences of users. Therefore, this study aims to develop an individual recommendation model based on the current individual preferences and user location in a mobile environment. We propose an RFM (Recency, Frequency, Monetary) score-based algorithm to predict the current individual preferences of users. This research utilizes the skyline query method to recommend local cuisine that aligns with the individual preferences of users. The attributes used in selecting suitable local cuisine include individual preferences, price, and distance between the user and the local cuisine seller. The proposed algorithm has been implemented in the JALITA mobile-based Indonesian local cuisine recommendation system. The results effectively recommend local cuisine that matches the dynamic individual preferences and location of users. Based on the implementation results, individual recommendations are provided to mobile users anytime and anywhere they are located. In this study, three skyline objects are generated: soto betawi (C5), Mie Aceh Daging Goreng (C4), and Gado-gado betawi (C3), which are recommended local cuisine based on the current individual preferences (U1) and user location (L1). The implementation results are exemplified for one user located at (U1L1), providing recommendations for soto betawi (C5) with an individual preference score of 0.96, Mie Aceh Daging Goreng (C4) with an individual preference score of 0.93, and Gado-gado betawi (C3) with an individual preference score of 0.98. Thus, this research contributes to the field of individual recommendation systems by considering the dynamic user location and preferences.

Intrinsically motivated reinforcement learning based recommendation with counterfactual data augmentation

Deep reinforcement learning (DRL) has shown promising results in modeling dynamic user preferences in RS in recent literature. However, training a DRL agent in the sparse RS environment poses a significant challenge. This is because the agent must balance between exploring informative user-item interaction trajectories and using existing trajectories for policy learning, a known exploration and exploitation trade-off. This trade-off greatly affects the recommendation performance when the environment is sparse. In DRL-based RS, balancing exploration and exploitation is even more challenging as the agent needs to deeply explore informative trajectories and efficiently exploit them in the context of RS. To address this issue, we propose a novel intrinsically motivated reinforcement learning (IMRL) method that enhances the agent’s capability to explore informative interaction trajectories in the sparse environment. We further enrich these trajectories via an adaptive counterfactual augmentation strategy with a customised threshold to improve their efficiency in exploitation. Our approach is evaluated on six offline datasets and three online simulation platforms, demonstrating its superiority over existing state-of-the-art methods. The extensive experiments show that our IMRL method outperforms other methods in terms of recommendation performance in the sparse RS environment.

Learning To Rank for E commerce Cart Optimization

In the competitive landscape of e-commerce, optimizing the shopping cart experience is crucial for enhancing customer satisfaction and boosting conversion rates. This paper explores the application of Learning to Rank (LTR) techniques to optimize e-commerce cart functionality. Learning to Rank, a subset of machine learning, involves training models to order items or features in a way that maximizes relevance based on user preferences. By employing LTR algorithms, e-commerce platforms can improve the relevance of product recommendations, streamline the checkout process, and tailor user interactions based on historical data and user behaviour. The study outlines the integration of LTR models into e-commerce systems, focusing on how these models can predict and prioritize products that users are more likely to purchase. This involves analysing user interactions, purchase history, and product attributes to develop ranking models that enhance the cart's efficiency and effectiveness. The research also addresses challenges such as data sparsity, dynamic user preferences, and the need for real-time updates, offering solutions and best practices for implementing LTR in practical settings. The results demonstrate that applying LTR techniques can significantly improve cart optimization by presenting users with more relevant product options, reducing cart abandonment rates, and increasing overall sales. This paper provides a comprehensive framework for e-commerce businesses seeking to leverage LTR for cart optimization, highlighting both theoretical insights and practical implications.

LightGCAN: A lightweight graph convolutional attention network for user preference modeling and personalized recommendation

Graph Neural Network (GNN) is a promising technique in representation learning on graph data. Graph Convolution Network (GCN) and Graph Attention Network (GAT) are two main representative techniques in GNN, which can learn node embedding on the graph by aggregating the embedding of the neighborhoods. However, the complex computation process of existing GCN and GAT makes them less effective for tasks with complex graph structures. Moreover, traditional GCN and GAT ignore the time factor in user representation learning, so the obtained user preference model is static and cannot reflect the dynamics of user preferences. In this work, we propose a time-aware Lightweight Graph Convolutional Attention Network (LightGCAN), which can capture static and dynamic user preferences efficiently by using different GNN strategies. Specifically, static user preferences are modeled by a GCN with only neighborhood aggregation, and dynamic user preferences are extracted by a time-aware GAT based on recently interacted items. Static and dynamic user preferences are then combined and fed into a dual-channel Deep Neural Network (DNN) model for feature interaction learning and matching score prediction. Extensive experiments on different datasets show that LightGCAN is superior to the SOTA recommendation method.

C-DeepTrust: A Context-Aware Deep Trust Prediction Model in Online Social Networks.

Trust prediction provides valuable support for decision making, information dissemination, and product promotion in online social networks. As a complex concept in the social network community, trust relationships among people can be established virtually based on: 1) their interaction behaviors, e.g., the ratings and comments that they provided; 2) the contextual information associated with their interactions, e.g., location and culture; and 3) the relative temporal features of interactions and the time periods when the trust relationships hold. Most of the existing works only focus on some aspects of trust, and there is not a comprehensive study of user trust development that considers and incorporates 1)-3) in trust prediction. In this article, we propose a context-aware deep trust prediction model C-DeepTrust to fill this gap. First, we conduct user feature modeling to obtain the user's static and dynamic preference features in each context. Static user preference features are obtained from all the ratings and reviews that a user provided, while dynamic user preference features are obtained from the items rated/reviewed by the user in time series. The obtained context-aware user features are then combined and fed into the multilayer projection structure to further mine the context-aware latent features. Finally, the context-aware trust relationships between users are calculated by their context-aware feature vector cosine similarities according to the social homophily theory, which shows a pervasive property of social networks that trust relationships are more likely to be developed among similar people. Extensive experiments conducted on two real-world datasets show the superior performance of our approach compared with the representative baseline methods.

A novel neighbor selection scheme based on dynamic evaluation towards recommender systems.

Collaborative filtering is a kind of widely used and efficient technique in various online environments, which generates recommendations based on the rating information of his/her similar-preference neighbors. However, existing collaborative filtering methods have some inadequacies in revealing the dynamic user preference change and evaluating the recommendation effectiveness. The sparsity of input data may further exacerbate this issue. Thus, this paper proposes a novel neighbor selection scheme constructed in the context of information attenuation to bridge these gaps. Firstly, the concept of the preference decay period is given to describe the pattern of user preference evolution and recommendation invalidation, and thus two types of dynamic decay factors are correspondingly defined to gradually weaken the impact of old data. Then, three dynamic evaluation modules are built to evaluate the user's trustworthiness and recommendation ability. Finally, A hybrid selection strategy combines these modules to construct two neighbor selection layers and adjust the neighbor key thresholds. Through this strategy, our scheme can more effectively select capable and trustworthy neighbors to provide recommendations. The experiments on three real datasets with different data sizes and data sparsity show that the proposed scheme provides excellent recommendation performance and is more suitable for real applications, compared to the state-of-the-art methods.

Improving the spatial–temporal aware attention network with dynamic trajectory graph learning for next Point-Of-Interest recommendation

Next Point-Of-Interest (POI) recommendation aim to predict users’ next visits by mining their movement patterns. Existing works attempt to extract spatial–temporal relationships from historical check-ins; however, the following critical factors have not been adequately considered: (1) structured features implied in trajectory that reflect individual visit tendency; (2) collaborative signals from other users and (3) dynamic user preference. To this end, we jointly take into full consideration the graph-structured information as well as sequential effects of user trajectory sequences and propose the Trajectory Graph enhanced Spatial–Temporal aware Attention Network (TGSTAN). Given the general preference among users and the shifts of individual interests over time, we present a novel trajectory-aware dynamic graph convolution network module (TDGCN) to facilitate the capturing of local spatial correlations. Specifically, TDGCN dynamically adjusts the normalized adjacency matrix of the trajectory graph by element-wise multiplication with self-attentive POI representations. The local trajectory graph is generated from the same training batch to reflect real-time and collaborative signals, while also following causality. Moreover, we explicitly integrate spatial–temporal interval information with bilinear interpolation to comprehensively attach relative proximity to attention mechanism when capturing long-term dependence. Extensive experiments on three real-world Location-Based Social Networks datasets (Foursquare_TKY, Weeplaces and Gowalla_CA) demonstrate that the proposed TGSTAN consistently outperforms the existing state-of-the-art baselines with an average of 8.18%, 6.59%, and 9.60% improvement on the three datasets, respectively.

Multi-dimensional Graph Neural Network for Sequential Recommendation

Graph neural networks (GNNs) technology has been widely used in recommendation systems because most information in recommendation systems has a graph structure in nature, and GNNs have advantages in graph representation learning. In sequential recommendation, the relationships between interacting items can be constructed as an isomorphic graph, and (GNNs) can capture high-order information between graph nodes. Many models have used graph-based methods for sequential recommendation, and achieved great success. However, the existing research only considers the number of interactions between items when constructing the item graph. As such, revisions are needed to capture the multi-dimensional transformation relationships between items. Hence, we emphasize the importance of multi-dimensional information, and we propose a Category and Time information integrated Graph Neural Network (CTGNN), which combines the item category and interaction time information with a multi-layer graph convolution network to form multi-dimensional fine-grained item representations. In addition, we design a temporal self-attention network to model the dynamic user preference and make the next-item recommendation. Finally, we conduct extensive experiments on three real-world datasets, and the results demonstrate the excellent performance of the proposed model.