The latent factor analysis (LFA) model has been widely used to uncover latent relationships from high-dimensional sparse (HiDS) matrices. However, the performance of LFA depends largely on the hyper-parameter value used in the model training. Traditional hyper-parameter tuning methods such as grid search suffer from inefficiency and inaccuracy. In recent years, the particle swarm optimization (PSO) algorithm offers an intelligent approach to adaptively adjust the hyper-parameter of LFA. However, the global optimal solution of the hyper-parameter tuning problem is not fixed due to its dynamic decision space. Therefore, it is difficult for PSO to determine the best hyper-parameter for each training iteration. To address this problem, this paper proposes a novel hyper-parameter adaptive adjustment algorithm called dynamic stochastic reorientation PSO (DSR-PSO) that adapts to constantly changing decision spaces. By randomly adjusting the search directions of particles and perturbing the elite particles, the dynamic property of the DSR-PSO can be enhanced, so that the hyper-parameter can be adjusted in real time throughout the model training process. Furthermore, this paper proves the convergence of the DSR-PSO and gives its convergence condition by discussing the distribution of the characteristic roots. Finally, this paper proposes the DSR-PSO-based LFA (DPL) model by incorporating the DSR-PSO-based hyper-parameter adjustment into the LFA to promote its model training, and analyzes its complexity. Experimental results on benchmark datasets show that the proposed DPL surpasses state-of-the-art LFA models in terms of accuracy and efficiency.

Abstract Recommender systems have been widely deployed in various real-world applications to help users identify content of interest from massive amounts of information. Traditional recommender systems work by collecting user-item interaction data in a cloud-based data center and training a centralized model to perform the recommendation service. However, such cloud-based recommender systems (CloudRSs) inevitably suffer from excessive resource consumption, response latency, as well as privacy and security risks concerning both data and models. Recently, driven by the advances in storage, communication, and computation capabilities of edge devices, there has been a shift of focus from CloudRSs to on-device recommender systems (DeviceRSs), which leverage the capabilities of edge devices to minimize centralized data storage requirements, reduce the response latency caused by communication overheads, and enhance user privacy and security by localizing data processing and model training. Despite the rapid rise of DeviceRSs, there is a clear absence of timely literature reviews that systematically introduce, categorize and contrast these methods. To bridge this gap, we aim to provide a comprehensive survey of DeviceRSs, covering three main aspects: (1) the deployment and inference of DeviceRSs, exploring how large recommendation models can be compressed and utilized within resource-constrained on-device environments; (2) the training and update of DeviceRSs, discussing how local data can be leveraged for model optimization on the device side; (3) the security and privacy of DeviceRSs, unveiling their potential vulnerability to malicious attacks and defensive strategies to safeguard these systems. Furthermore, we provide a fine-grained and systematic taxonomy of the methods involved in each aspect, followed by a discussion regarding challenges and future research directions. This is the first comprehensive survey on DeviceRSs that covers a spectrum of tasks to fit various needs. We believe this survey will help readers understand the current research status in this field, equip them with relevant technical foundations, and stimulate new research ideas for developing DeviceRSs.

To make room for privacy and efficiency, the deployment of many recommender systems is experiencing a shift from central servers to personal devices, where the federated recommender systems (FedRecs) and decentralized collaborative recommender systems (DecRecs) are arguably the two most representative paradigms. While both leverage knowledge (e.g., gradients) sharing to facilitate learning local models, FedRecs rely on a central server to coordinate the optimization process, yet in DecRecs, the knowledge sharing directly happens between clients. On the flip side, knowledge sharing also opens a backdoor for model poisoning attacks, where adversaries disguise themselves as benign clients and disseminate polluted knowledge to achieve malicious goals like promoting an item's exposure rate. Although research on such poisoning attacks provides valuable insights into finding security loopholes and corresponding countermeasures, existing attacks mostly focus on FedRecs, and are either inapplicable or ineffective for DecRecs. Compared with FedRecs where the tampered information can be universally distributed to all clients once uploaded to the cloud, each adversary in DecRecs can only communicate with neighbor clients of a small size, confining its impact to a limited range.

Federated recommender systems (FedRecs) have gained significant attention for their potential to protect user's privacy by keeping user privacy data locally and only communicating model parameters/gradients to the server. Nevertheless, the currently existing architecture of FedRecs assumes that all users have the same 0-privacy budget, i.e., they do not upload any data to the server, thus overlooking those users who are less concerned about privacy and are willing to upload data to get a better recommendation service. To bridge this gap, this paper explores a user-governed data contribution federated recommendation architecture where users are free to take control of whether they share data and the proportion of data they share to the server. To this end, this paper presents a cloud-device collaborative graph neural network federated recommendation model, named CDCGNNFed. It trains user-centric ego graphs locally, and high-order graphs based on user-shared data in the server in a collaborative manner via contrastive learning. Furthermore, a graph mending strategy is utilized to predict missing links in the graph on the server, thus leveraging the capabilities of graph neural networks over high-order graphs. Extensive experiments were conducted on two public datasets, and the results demonstrate the effectiveness of the proposed method.

In Location-based Social Networks (LBSNs), Point-of-Interest (POI) recommendation helps users discover interesting places. There is a trend to move from the conventional cloud-based model to on-device recommendations for privacy protection and reduced server reliance. Due to the scarcity of local user-item interactions on individual devices, solely relying on local instances is not adequate. Collaborative Learning (CL) emerges to promote model sharing among users. Central to this CL paradigm is reference data, which is an intermediary that allows users to exchange their soft decisions without directly sharing their private data or parameters, ensuring privacy and benefiting from collaboration. While recent efforts have developed CL-based POI frameworks for robust and privacy-centric recommendations, they typically use a single and unified reference for all users. Reference data that proves valuable for one user might be harmful to another, given the wide range of user preferences. Some users may not offer meaningful soft decisions on items outside their interest scope. Consequently, using the same reference data for all collaborations can impede knowledge exchange and lead to sub-optimal performance. To address this gap, we introduce the Decentralized Collaborative Learning with Adaptive Reference Data (DARD) framework, which crafts adaptive reference data for effective user collaboration. It first generates a desensitized public reference data pool with transformation and probability data generation methods. For each user, the selection of adaptive reference data is executed in parallel by training loss tracking and influence function. Local models are trained with individual private data and collaboratively with the geographical and semantic neighbors. During the collaboration between two users, they exchange soft decisions based on a combined set of their adaptive reference data. Our evaluations across two real-world datasets highlight DARD's superiority in recommendation performance and addressing the scarcity of available reference data.

To address privacy concerns and reduce network latency, there has been a recent trend of compressing cumbersome recommendation models trained on the cloud and deploying compact recommender models to resource-limited devices for the real-time recommendation. Existing solutions generally overlook device heterogeneity and user heterogeneity. They require devices with the same budget to share the same model and assume the available device resources (e.g., memory) are constant, which is not reflective of reality. Considering device and user heterogeneities as well as dynamic resource constraints, this paper proposes a Personalized Elastic Embedding Learning framework (PEEL) for the on-device recommendation, which generates Personalized Elastic Embeddings (PEEs) for devices with various memory budgets in a once-for-all manner, adapting to new or dynamic budgets, and addressing user preference diversity by assigning personalized embeddings for different groups of users. Specifically, it pretrains a global embedding table with collected user-item interaction instances and clusters users into groups. Then, it refines the embedding tables with local interaction instances within each group. PEEs are generated from the group-wise embedding blocks and their weights that indicate the contribution of each embedding block to the local recommendation performance. Given a memory budget, PEEL efficiently generates PEEs by selecting embedding blocks with the largest weights, making it adaptable to dynamic memory budgets on devices. Furthermore, a diversity-driven regularizer is implemented to encourage the expressiveness of embedding blocks, and a controller is utilized to optimize the weights. Extensive experiments are conducted on two public datasets, and the results show that PEEL yields superior performance on devices with heterogeneous and dynamic memory budgets.

Collaborative filtering (CF) based recommender systems are typically trained based on personal interaction data (e.g., clicks and purchases) that could be naturally represented as ego graphs. However, most existing recommendation methods collect these ego graphs from all users to compose a global graph to obtain high-order collaborative information between users and items, and these centralized CF recommendation methods inevitably lead to a high risk of user privacy leakage. Although recently proposed federated recommendation systems can mitigate the privacy problem, they either restrict the on-device local training to an isolated ego graph or rely on an additional third-party server to access other ego graphs resulting in a cumbersome pipeline, which is hard to work in practice. In addition, existing federated recommendation systems require resource-limited devices to maintain the entire embedding tables resulting in high communication costs.

Recommender systems play a significant role in information filtering and have been utilized in different scenarios, such as e-commerce and social media. With the prosperity of deep learning, deep recommender systems show superior performance by capturing non-linear information and item-user relationships. However, the design of deep recommender systems heavily relies on human experiences and expert knowledge. To tackle this problem, Automated Machine Learning (AutoML) is introduced to automatically search for the proper candidates for different parts of deep recommender systems. This survey performs a comprehensive review of the literature in this field. Firstly, we propose an abstract concept for AutoML for deep recommender systems (AutoRecSys) that describes its building blocks and distinguishes it from conventional AutoML techniques and recommender systems. Secondly, we present a taxonomy as a classification framework containing feature selection search, embedding dimension search, feature interaction search, model architecture search, and other components search. Furthermore, we put a particular emphasis on the search space and search strategy, as they are the common thread to connect all methods within each category and enable practitioners to analyze and compare various approaches. Finally, we propose four future promising research directions that will lead this line of research.

As a crucial component of most modern deep recommender systems, feature embedding maps high-dimensional sparse user/item features into low-dimensional dense embeddings. However, these embeddings are usually assigned a unified dimension, which suffers from the following issues: (1) high memory usage and computation cost. (2) sub-optimal performance due to inferior dimension assignments. In order to alleviate the above issues, some works focus on automated embedding dimension search by formulating it as hyper-parameter optimization or embedding pruning problems. However, they either require well-designed search space for hyperparameters or need time-consuming optimization procedures. In this paper, we propose a Single-Shot Embedding Dimension Search method, called SSEDS, which can efficiently assign dimensions for each feature field via a single-shot embedding pruning operation while maintaining the recommendation accuracy of the model. Specifically, it introduces a criterion for identifying the importance of each embedding dimension for each feature field. As a result, SSEDS could automatically obtain mixed-dimensional embeddings by explicitly reducing redundant embedding dimensions based on the corresponding dimension importance ranking and the predefined parameter budget. Furthermore, the proposed SSEDS is model-agnostic, meaning that it could be integrated into different base recommendation models. The extensive offline experiments are conducted on two widely used public datasets for CTR (Click Through Rate) prediction task, and the results demonstrate that SSEDS can still achieve strong recommendation performance even if it has reduced 90% parameters. Moreover, SSEDS has also been deployed on the WeChat Subscription platform for practical recommendation services. The 7-day online A/B test results show that SSEDS can significantly improve the performance of the online recommendation model while reducing resource consumption.

Imbalanced classification on graphs is ubiquitous yet challenging in many real-world applications, such as fraudulent node detection. Recently, graph neural networks (GNNs) have shown promising performance on many network analysis tasks. However, most existing GNNs have almost exclusively focused on the balanced networks, and would get unappealing performance on the imbalanced networks. To bridge this gap, in this paper, we present a generative adversarial graph network model, called ImGAGN to address the imbalanced classification problem on graphs. It introduces a novel generator for graph structure data, named GraphGenerator, which can simulate both the minority class nodes' attribute distribution and network topological structure distribution by generating a set of synthetic minority nodes such that the number of nodes in different classes can be balanced. Then a graph convolutional network (GCN) discriminator is trained to discriminate between real nodes and fake (i.e., generated) nodes, and also between minority nodes and majority nodes on the synthetic balanced network. To validate the effectiveness of the proposed method, extensive experiments are conducted on four real-world imbalanced network datasets. Experimental results demonstrate that the proposed method ImGAGN outperforms state-of-the-art algorithms for semi-supervised imbalanced node classification task.

Recently, graph neural networks (GNNs) have been shown to be an effective tool for learning the node representations of the networks and have achieved good performance on the semi-supervised node classification task. However, most existing GNNs methods fail to take networks’ temporal information into account, therefore, cannot be well applied to dynamic network applications such as the continuous-time link prediction task. To address this problem, we propose a Temporal Dependent Graph Neural Network (TDGNN), a simple yet effective dynamic network representation learning framework which incorporates the network temporal information into GNNs. TDGNN introduces a novel Temporal Aggregator (TDAgg) to aggregate the neighbor nodes’ features and edges’ temporal information to obtain the target node representations. Specifically, it assigns the neighbor nodes aggregation weights using an exponential distribution to bias different edges’ temporal information. The performance of the proposed method has been validated on six real-world dynamic network datasets for the continuous-time link prediction task. The experimental results show that the proposed method outperforms several state-of-the-art baselines.