Linear-Time Graph Neural Networks for Scalable Recommendations

A Contextual Recurrent Collaborative Filtering framework for modelling sequences of venue checkins

In the era of digital transformation, personalized recommendation systems play a critical role in mitigating information overload by guiding users toward relevant content, products, and services. Traditional approaches such as Collaborative Filtering and Content-Based Filtering, while widely adopted, struggle with cold-start issues, data sparsity, and the inability to capture complex relationships within heterogeneous data. Recent advances in Graph Neural Networks (GNNs) present a promising paradigm, as user–item interactions, social connections, and knowledge graphs naturally exhibit graph structures. However, despite growing interest, there remains a lack of systematic reviews focusing specifically on the application of GNNs to personalized recommendation systems. This survey addresses that gap by analyzing recent studies from 2020 to 2025, classifying GNN architectures (e.g., GCN, GAT, GraphSAGE, LightGCN, and specialized variants), and mapping their application across collaborative, content-based, and hybrid recommendation strategies. The findings highlight GNNs’ superior ability to address cold-start and sparsity challenges, enhance personalization, and improve interpretability through integration with knowledge graphs. By consolidating current advancements and open challenges, this study contributes a comprehensive reference that bridges theoretical development with practical needs, while outlining future directions for more scalable, explainable, and ethical recommender systems.

Ranging from Matrix Factorization to deep learning based methods, recommender systems usually obtain user's (or item's) embedding via mapping from existed features. However, the collaborative signal is not encoded in the embedding process. Graph Neural Networks (GNNs) have been proved to be powerful in learning on graph data. But building recommender systems on GNNs faces challenges: the user-item graph encodes both interactions and opinions; user item interactions have heterogeneous strengths. To address these challenges, we proposed a novel framework on collaborative filtering recommendation via attention mechanism (GCFA), which models heterogeneous user-item interaction strengths and exploits the user-item graph structure by propagating embeddings on it. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework GCFA.

Social recommendation with Graph Neural Networks(GNNs) learns to represent cold users by fusing user-user social relations with user-item interactions, thereby alleviating the cold-start problem associated with recommender systems. Despite being well adapted to social relations and user-item interactions, these supervised models are still susceptible to popularity bias. Contrastive learning helps resolve this dilemma by identifying the properties that distinguish positive from negative samples. In its previous combinations with recommender systems, social relationships and cold-start cases in this context are not considered. Also, they primarily focus on collaborative features between users and items, leaving the similarity between items under-utilized. In this work, we propose socially-aware dual contrastive learning for cold-start recommendation, where cold users can be modeled in the same way as warm users. To take full advantage of social relations, we create dynamic node embeddings for each user by aggregating information from different neighbors according to each different query item, in the form of user-item pairs. We further design a dual-branch self-supervised contrastive objective to account for user-item collaborative features and item-item mutual information, respectively. On one hand, our framework eliminates popularity bias with proper negative sampling in contrastive learning, without extra ground-truth supervision. On the other hand, we extend previous contrastive learning methods to provide a solution to cold-start problem with social relations included. Extensive experiments on two real-world social recommendation datasets demonstrate its effectiveness.

The field of e-commerce provides customers with many kinds of goods to choose from. It is also a challenge for consumers to choose among tens of thousands of product categories. The emergence of recommender systems solves such problems for consumers to a certain extent because it would recommend products that may fulfil their needs for consumers. Finding user preferences or rankings for a specific item can be aided by recommender systems. It uses specialized software and techniques to offer suggestions for items utilized by various users. To increase customer satisfaction or sell different things for e-commerce platforms, recommender systems advise consumers about specific items they may be interested in or desire to utilize. Graph neural networks generalize effectively to new datasets because they can learn the graph structure of various datasets. To put it another way, this makes Graph Neural Networks (GNNs) the perfect recommender systems for various real-world issues. As a result, the growth and usage of neural graph networks in recommender systems and the limitations of graph neural networks will be covered in detail in this paper.

Recent studies reveal that recommender systems are vulnerable to data poisoning attack due to their openness nature. In data poisoning attack, the attacker typically recruits a group of controlled users to inject well-crafted user-item interaction data into the recommendation model's training set to modify the model parameters as desired. Thus, existing attack approaches usually require full access to the training data to infer items' characteristics and craft the fake interactions for controlled users. However, such attack approaches may not be feasible in practice due to the attacker's limited data collection capability and the restricted access to the training data, which sometimes are even perturbed by the privacy preserving mechanism of the service providers. Such design-reality gap may cause failure of attacks. In this paper, we fill the gap by proposing two novel adversarial attack approaches to handle the incompleteness and perturbations in user-item interaction data. First, we propose a bi-level optimization framework that incorporates a probabilistic generative model to find the users and items whose interaction data is sufficient and has not been significantly perturbed, and leverage these users and items' data to craft fake user-item interactions. Moreover, we reverse the learning process of recommendation models and develop a simple yet effective approach that can incorporate context-specific heuristic rules to handle data incompleteness and perturbations. Extensive experiments on two datasets against three representative recommendation models show that the proposed approaches can achieve better attack performance than existing approaches.

We present a physics‐informed deep neural network (DNN) method for estimating hydraulic conductivity in saturated and unsaturated flows governed by Darcy's law. For saturated flow, we approximate hydraulic conductivity and head with two DNNs and use Darcy's law in addition to measurements of hydraulic conductivity and head to train these DNNs. For unsaturated flow, we approximate unsaturated conductivity function and capillary pressure with DNNs and train these DNNs using measurements of capillary pressure and the Richards equation. Because it is difficult to measure unsaturated conductivity in the field, we assume that no measurements of unsaturated conductivity are available. The proposed approach enforces the partial differential equation (PDE) (Darcy or Richards equation) constraints by minimizing the PDE residual at select points in the simulation domain. We demonstrate that physics constraints increase the accuracy of DNN approximations of sparsely observed functions and allow for training DNNs when no direct measurements of the functions of interest are available. For the saturated conductivity estimation problem, we show that the physics‐informed DNN method is more accurate than the state‐of‐the‐art maximum a posteriori probability method. For the unsaturated flow in homogeneous porous media, we find that the proposed method can accurately estimate the pressure‐conductivity relationship based on the capillary pressure measurements only, even in the presence of measurement noise.

Recent studies have shown that the problems of cold processing and data sparsity in recommender systems can be well alleviated with the help of knowledge graph information. Meanwhile, since the information in recommender systems can be represented by graph data structure, graph neural network has great advantages in recommendatory system. Therefore, graph neural network can better mine the deep relationship between objects in the recommender systems which combines with information from knowledge graph. This paper reviews the application of graph neural network in knowledge graph aided recommendation systems. Specifically, this paper firstly sorts out the related knowledge of knowledge graph, recommendation system and graph neural network, including the cold processing and data sparsity, the structure of knowledge graph, and the basic modules of graph neural network. This paper also summarizes the methods such as KGAT and CKAN used in knowledge graph aided recommendation systems in recent years, and gives some discussion on the development of this field.

The shifting of the neutral axis in the cross section of ship structures is an important result of progressive collapse analyses. The main purpose of the present study is to apply a Deep Neural Network (DNN) method to linear systems and estimate in a relatively short time span the shift of the neutral axis for intact and damaged ships. First, the initial source data related to the intact condition and to several symmetric damaged grounding scenarios of five different vessels (Double Hull Oil Tanker, Single Hull Tanker, 1350TEU Container Vessel, 3500TEU Container Vessel, Bulk Carrier) have been determined with a self-developed code based on the well-established Smith method. With the application of the DNN, the shift of the neutral axis has been predicted for a set of completely new damage scenarios of a ship cross section, demonstrating that the deep neural network approach can estimate the neutral axis performance. The successful prediction obtained within this paper will lead to the DNN’s application for computing the ultimate strength capacity.

Learning instrumental variable representation for debiasing in recommender systems.

Recommender systems act as filtering algorithms to provide users with items that might meet their interests according to the expressed preferences and items' characteristics. As of today, the collaborative filtering paradigm, along with deep learning techniques to learn high-quality users' and items' representations, constitute the de facto standard for personalized recommendation, showing remarkable recommendation accuracy performance. Nevertheless, recommendation remains a highly-challenging task. Among the most debated open issues in the community, this thesis considers two algorithmic and conceptual ones, namely: (i) the inexplicable nature of users' preferences, especially when they come in the form of implicit feedback; (ii) the effective exploitation of the collaborative information in the designing and training of recommendation models. In domains such as fashion, food, and media content recommendation, the shallow item's profile can be enhanced through the multimodal characteristics describing items [Malitesta et al., 2023]. Driven by these assumptions, in the first part of this thesis, we apply multimodal deep learning strategies for multimedia recommendation; the scope is to study and design recommendation algorithms based upon the principles of multimodality to possibly match each item's characteristic to the implicit preference expressed by the user [Deldjoo et al., 2022], thus addressing the (i) issue. Recent collaborative filtering approaches profile users and items through embedding vectors in the latent space. However, such models disregard structural properties naturally encoded into the user-item interaction data. Indeed, recommendation datasets are easily describable under the topology of a bipartite and undirected graph, with users and items being the graph nodes connected at multiple distance hops. In this respect, the application of graph neural networks , recent deep learning techniques specifically tailored to learn from non-euclidean data, can provide a refined representation of users and items to mine near- and long-distance relationships in the user-item graphs [Anelli et al., 2023b]. Indeed, this is one possible solution to exploit the collaborative information, which is effectively propagated within the user-item graph, addressing the (ii) issue. Conclusively, this thesis aims to match the two families of recommendation strategies by leveraging graph neural networks and multimodal information data [Anelli et al., 2022]. In doing so, other numerous micro-aspects within the two macro-areas (introduced above) are examined. Indeed, the thesis is a systematic compendium of careful analyses regarding, among others, reproducibility, novel evaluation dimensions [Anelli et al., 2023a], and tasks/scenarios complementary to recommendation. Awarded by : Politecnico di Bari, Bari, Italy on 30 January 2024. Supervised by : Tommaso Di Noia. Available at : https://hdl.handle.net/11589/264941.

The graph neural network (GNN) has recently become an emerging research topic for processing non-euclidean data structures since the data used in various popular application domains are usually modeled as a graph, such as social networks, recommendation systems, and computer vision. Previous GNN accelerators commonly utilize the hybrid architecture to resolve the issue of “hybrid computing pattern” in GNN training. Nevertheless, the hybrid architecture suffers from poor utilization of hardware resources mainly due to the dynamic workloads between different phases in GNN. To address these issues, existing GNN accelerators adopt a unified structure with numerous processing elements and high bandwidth memory. However, the large amount of data movement between the processor and memory could heavily downgrade the performance of such accelerators in real-world graphs. As a result, the processing-in-memory architecture, such as the ReRAM-based crossbar, becomes a promising solution to reduce the memory overhead of GNN training. In this work, we present the TCAM-GNN, a novel TCAM-based data processing strategy, to enable high-throughput and energy-efficient GNN training over ReRAM-based crossbar architecture. Several hardware co-designed data structures and placement methods are proposed to fully exploit the parallelism in GNN during training. In addition, we propose a dynamic fixed-point formatting approach to resolve the precision issue. An adaptive data reusing policy is also proposed to enhance the data locality of graph features by the bootstrapping batch sampling approach. Overall, TCAM-GNN could enhance computing performance by 4.25× and energy efficiency by 9.11× on average compared to the neural network accelerators.

The Recommender System (RS) has obtained a pivotal role in e-commerce. To improve the performance of RS, review text information has been extensively utilized. However, it is still a challenge for RS to extract the most informative feature from a tremendous amount of reviews. Another significant issue is the modeling of user–item interaction, which is rarely considered to capture high- and low-order interactions simultaneously. In this paper, we design a multi-level attention mechanism to learn the usefulness of reviews and the significance of words by Deep Neural Networks (DNN). In addition, we develop a hybrid prediction structure that integrates Factorization Machine (FM) and DNN to model low-order user–item interactions as in FM and capture the high-order interactions as in DNN. Based on these two designs, we build a Multi-level Attentional and Hybrid-prediction-based Recommender (MAHR) model for recommendation. Extensive experiments on Amazon and Yelp datasets showed that our approach provides more accurate recommendations than the state-of-the-art recommendation approaches. Furthermore, the verification experiments and explainability study, including the visualization of attention modules and the review-usefulness prediction test, also validated the reasonability of our multi-level attention mechanism and hybrid prediction.

A recommendation system is a set of programs that utilize different methodologies for relevant item selection for the user. Graph neural networks have been extensively used in recent years to improve the quality of recommendations across all domains. A general recommendation system’s main goal is to recommend items to the user accurately, and it frequently prioritizes items that are well-liked or mainstream. If the model concentrates only on one specific item category from the users’ past preferences, then recommendations for the target user will become too obvious. To address this problem, diversity in the recommendation system is introduced. The model IG-DivRS (Item-Enhanced Graph Neural Network for a Diversified Recommendation System) is proposed. Our proposed model uses a Graph Neural Network (GNN) with the user’s interacted and non-interacted item history for diversified recommendation generation. The novelty of our proposed model is to explore the effect of non-interacted items on the target user for diversified recommendation generation. Instead of selecting random non-interacted items for the target user, we apply the DPP(Determinantal Point Process) algorithm to select the non-interacted item appropriately. The detailed experimental analysis shows that our model ID-DivRS outperforms the state-of-the-art model in accuracy and diversity.

A genetic algorithms-based hybrid recommender system of matrix factorization and neighborhood-based techniques