Cross-domain recommendation (CDR) has emerged as a promising solution by effectively alleviating data sparsity by leveraging information from auxiliary domains. However, a major challenge in CDR is its dependence on predefined alignment rules (e.g., structural or distribution matching) to achieve cross-domain knowledge transfer, which impose fixed transfer patterns and lack the flexibly need for diverse cross-domain scenarios. Furthermore, most existing approaches still rely on coarse-grained representations. Knowledge transfer built upon imprecise representations can, even with improved alignment rules, instead lead to negative transfer in the target domain. To address these challenges and optimize recommendation efficacy, a new framework named meta-learning driven few-shot knowledge transfer with dual-stage adaptive data replay for cross-domain recommendation (MFACDR) is proposed. Specifically, a new meta-learning driven few-shot knowledge transfer method is proposed. This method leverages overlapping parts as anchors to guide the non-overlapping parts in autonomously exploring alignment rules through meta-learning, thus enabling few-shot knowledge transfer and flexible handling of different cross-domain scenarios. In addition, a dual-stage adaptive data replay mechanism is proposed, which enables fine-grained cross-domain adaptability and helps to mitigate negative transfer. Extensive experiments on three real-world datasets consistently demonstrate the superior effectiveness and robustness of the proposed MFACDR.

Spatial Crowdsourcing (SC), which outsources location-dependent tasks to workers for physical completion, is gaining popularity. Recently, more complex tasks have emerged that require a group of workers collaborating in a coalition. Several pioneering studies have examined this issue using the server assigned tasks mode from an overall perspective, such as maximizing the total benefits of all workers. Unfortunately, maximizing the overall benefit does not necessarily align with maximizing individual benefits. In practice, crowd workers are often self-interested and autonomous, making decisions based on their personal perspectives. In this article, under the worker selected tasks mode, we investigate an important problem: Selfish Workers Coalition Formation (SWCF) problem in SC. Here, selfish workers autonomously form coalitions to accomplish tasks to maximize their individual benefits. Achieving a stable coalition formation for SWCF problem requires balancing cooperation and competition. First, we transform the SWCF problem into a hedonic coalition formation game using a devised exploited skills-based reward distribution model. Subsequently, we propose a distributed algorithm HCFTA and prove its Nash stability and performance bounds. Additionally, to enhance coalition formation efficiency, we propose a Markov blanket coloring parallel optimization algorithm MCPHCF . Extensive experiments demonstrate the superiority of the proposed methods on both synthetic and real-world datasets.

Contrastive learning (CL) has recently catalyzed a productive avenue of research for recommendation. The efficacy of most CL methods for recommendation may hinge on their capacity to learn representation uniformity by mapping the data onto a hypersphere. Nonetheless, applying contrastive learning to downstream recommendation tasks remains challenging, as existing CL methods encounter difficulties in capturing the nonlinear dependence of representations in high-dimensional space and struggle to learn hierarchical social dependency among users-essential points for modeling user preferences. Moreover, the subtle distinctions between the augmented representations render CL methods sensitive to noise perturbations. Inspired by the Hilbert-Schmidt independence criterion (HSIC), we propose a graph Contrastive Learning model with Kernel Dependence Maximization CL-KDM for social recommendation to address these challenges. Specifically, to explicitly learn the kernel dependence of representations and improve the robustness and generalization of recommendation, we maximize the kernel dependence of augmented representations in kernel Hilbert space by introducing HSIC into the graph contrastive learning. Additionally, to simultaneously extract the hierarchical social dependency across users while preserving underlying structures, we design a hierarchical mutual information maximization module for generating augmented user representations, which are injected into the message passing of a graph neural network to enhance recommendation. Extensive experiments are conducted on three social recommendation datasets, and the results indicate that CL-KDM outperforms various baseline recommendation methods.

Transfer learning-based recommendation mitigates the sparsity of user-item interactions by introducing auxiliary domains. Social influence extracted from direct connections between users typically serves as an auxiliary domain to improve prediction performance. However, direct social connections also face severe data sparsity problems that limit model performance. In contrast, users’ dependency on communities is another valuable social information that has not yet received sufficient attention. Although studies have incorporated community information into recommendation by aggregating users’ preferences within the same community, they seldom capture the structural discrepancies among communities and the influence of structural discrepancies on users’ preferences. To address these challenges, we propose a community-preserving recommendation framework with cyclic transfer learning, incorporating heterogeneous community influence into the rating domain. We analyze the characteristics of the community domain and its inter-influence on the rating domain, and construct link constraints and preference constraints in the community domain. The shared vectors that bridge the rating domain and the community domain are allowed to be more consistent with the characteristics of both domains. Extensive experiments are conducted on four real-world datasets. The results manifest the excellent performance of our approach in capturing real users’ preferences compared with other state-of-the-art methods.

Graph neural networks have been clearly proven to be powerful in recommendation tasks since they can capture high-order user-item interactions and integrate them with rich attributes. However, they are still limited by the cold-start problem and data sparsity. Using social relationships to assist recommendation is an effective practice, but it can only moderately alleviate these problems. In addition, rich attributes are often unavailable, which prevents graph neural networks from being fully effective. Hence, we propose to enrich the model by mining multiple implicit feedback and constructing a triple GCN component. We have noticed that users may be influenced not only by their trusted friends but also by the ratings that already exist. The implicit influence spreads among the item’s previous and potential raters, and makes a difference on future ratings. The implicit influence is analyzed on the mechanism of information propagation, and fused with the user’s binary implicit attitude, since negative influence propagates as well as the positive one. Furthermore, we leverage explicit feedback, social relationships, and multiple implicit feedback in the triple GCN component. Abundant experiments on real-world datasets reveal that our model has improved significantly in the rating prediction task compared with other state-of-the-art methods.

The task of network alignment is to obtain the node pairs which belong to the same entity from different networks. Existing embedding-based network alignment methods either use node structural or attribute information as inputs for node embeddings. These pieces of information are not always available in real-world datasets, and current methods that consider single information embedding may fail when there is excessive network noise. To address the aforementioned issue, we utilize a multi-layer Graph Attention Networks(GATs) to design an unsupervised node embedding model, which trains two GATs for structural and attribute information in a single graph and embeds the source nodes and target nodes into the same embedding space. By applying graph augmentation techniques, the model learns structural embeddings and attribute embeddings for every node in the networks based on structural and attribute consistency. Moreover, we apply a topological alignment refinement process to get aligned node pairs, which further enhances the accuracy of network alignment by leveraging the similarity of the structure between networks. Through extensive experiments, we have demonstrated that our model outperforms the state-of-the-art models in terms of alignment accuracy and its ability to handle attribute and structural noise. Additionally, our model exhibits relatively low complexity.

Detecting anomalies for dynamic graphs has drawn increasing attention due to their wide applications in social networks, e-commerce, and cybersecurity. Recent deep learning-based approaches have shown promising results over shallow methods. However, they fail to address two core challenges of anomaly detection in dynamic graphs: the lack of informative encoding for unattributed nodes and the difficulty of learning discriminate knowledge from coupled spatial-temporal dynamic graphs. To overcome these challenges, in this paper, we present a novelTransformer-basedAnomalyDetection framework forDYnamic graphs (TADDY). Our framework constructs a comprehensive node encoding strategy to better represent each node’s structural and temporal roles in an evolving graphs stream. Meanwhile, TADDY captures informative representation from dynamic graphs with coupled spatial-temporal patterns via a dynamic graph transformer model. The extensive experimental results demonstrate that our proposed TADDY framework outperforms the state-of-the-art methods by a large margin on six real-world datasets.

Graph embeddings have become a key paradigm to learn node representations and facilitate downstream graph analysis tasks. Many real-world scenarios such as online social networks and communication networks involve streaming graphs, where edges connecting nodes are continuously received in a streaming manner, making the underlying graph structures evolve over time. Such a streaming graph raises great challenges for graph embedding techniques not only in capturing the structural dynamics of the graph, but also in efficiently accommodating high-speed edge streams. Against this background, we propose SGSketch, a highly-efficient streaming graph embedding technique via incremental neighborhood sketching. SGSketch cannot only generate high-quality node embeddings from a streaming graph by gradually forgetting outdated streaming edges, but also efficiently update the generated node embeddings via an incremental embedding updating mechanism. Our extensive evaluation compares SGSketch against a sizable collection of state-of-the-art techniques using both synthetic and real-world streaming graphs. The results show that SGSketch achieves superior performance on different graph analysis tasks, showing 31.9% and 21.9% improvement on average over the best-performing static and dynamic graph embedding baselines, respectively. Moreover, SGSketch is significantly more efficient in both embedding learning and incremental embedding updating processes, showing 54x-1813x and 118x-1955x speedup over the baseline techniques, respectively.

The past flourishing years of sequential point-of-interest (POI) recommendation began with the introduction of Self-Attention Network (SAN), which quickly superseded CNN or RNN as the state-of-the-art backbone. To realize the fine-grained users' behavior patterns modeling, recent works utilize modified attention mechanisms or neural network layers to process spatial-temporal factors. However, due to the significant increase on either model's parameter scale or computational burden, we argue that these methods can be further improved. In this paper, we exploit two lightweight approaches, Time Aware Position Encoder (TAPE) and Interval Aware Attention Block (IAAB), to impel SAN by considering the spatial-temporal intervals among POIs separately, where requiring neither extra parameters nor high computational cost. On the one hand, TAPE, adjusting the positions in sequences based on the timestamps dynamically and generating positional representations with sinusoidal transformation, can enhance sequence representations to reflect both the absolute order and relative temporal proximity among all POIs. On the other hand, IAAB, point-wise adding the scaled spatial-temporal intervals to the attention map, can promote the attention mechanism attaching importance to the spatial relation among all POIs under the constraints of time conditions and providing more explainable recommendation. We integrate these two modules into SAN and propose a Spatial-Temporal Interval-Aware sequential POI recommender, namely STiSAN, as an end-to-end deployment. Experimental results based on three public LBSN datasets and one real-world city transportation dataset demonstrate STiSAN's superior performance (average 13.01% improvement against the strongest baseline). Moreover, we validate the extensibility and interpretability of TAPE and IAAB through metric evaluation and visualization separately.

Transfer learning uses auxiliary domains to help complete learning tasks of the target domain. However, the combination of recommendation and transfer learning often has two problems. One is that it's difficult to find an auxiliary domain which is highly related to the target domain. The other is that useful information in auxiliary domains cannot be fully utilized. To make use of the knowledge in auxiliary domains as much as possible, this paper proposes a cyclic transfer learning method which can transfer the shared knowledge in the auxiliary domain and target domain multiple times. Combining this method with recommendation, this paper presents a recommendation framework based on heterogeneous feedbacks and cyclic transfer learning (HCTL-Rec). By studying the relationship between different behaviors of users, this paper proposes two specific recommendation algorithms which combine the novel framework with two auxiliary domains. One is to use users' binary attitude information as an auxiliary domain to better represent users' ratings. The other is to use users' trust relationship as an auxiliary domain and make social recommendation. Experiments are carried out on two real-world datasets with trust relationship. The results show that recommendation quality of the two specific algorithms can achieve significant improvement compared with other state-of-the-art algorithms and can effectively relieve the cold-start problem.

In this article, we propose and study a novel data-driven framework for Targeted Outdoor Advertising Recommendation (TOAR) with a special consideration of user profiles and advertisement topics. Given an advertisement query and a set of outdoor billboards with different spatial locations and rental prices, our goal is to find a subset of billboards, such that the total targeted influence is maximum under a limited budget constraint. To achieve this goal, we are facing two challenges: (1) it is difficult to estimate targeted advertising influence in physical world; (2) due to NP hardness, many common search techniques fail to provide a satisfied solution with an acceptable time, especially for large-scale problem settings. Taking into account the exposure strength, advertisement matching degree, and advertising repetition effect, we first build a targeted influence model that can characterize that the advertising influence spreads along with users mobility. Subsequently, based on a divide-and-conquer strategy, we develop two effective approaches, i.e., a master–slave-based sequential optimization method, TOAR-MSS, and a cooperative co-evolution-based optimization method, TOAR-CC, to solve our studied problem. Extensive experiments on two real-world datasets clearly validate the effectiveness and efficiency of our proposed approaches.

Moving route prediction offers important benefits for many emerging location-aware applications such as target advertising and urban traffic management. A common approach to route prediction is to match similar trace recordings from a larger volume of historical trajectories, and return the targeted recorded path as desired answer. However, due to privacy concerns, incentive mechanism and other reasons, especially in small business environment, a limited dataset with sparse trajectories is only available. Actually, the existing sparse dataset cannot cover sufficient query routes, and then the match-based approach may return no results at all. Moreover, the existing sparse dataset may fail many trajectory mining approaches that work well on general environment. In this paper, we investigate moving route prediction from sparse trajectory dataset, and propose a novel hybrid model, namely HMRP, to address the above problem. To avoid sparse distribution over spatial semantic layer, a road network map reconstruction methods are proposed to accommodate the sparse trajectories in semantic transformation. And then, by training historical trajectories, the implicit mobility patterns and Markov transition model are constructed to support route prediction. When a query trajectory arrives, towards its derived potential destination, our proposed HMRP model integrates pattern matching strategy and Markov probability distribution to predict its future route gradually in a complementary way. Experiments on real-life taxicab GPS recorded dataset demonstrate that HMRP method can improve movement prediction precision significantly, comparing with the baseline prediction algorithms. And the response time for each query trajectory is acceptable for most application cases.

Moving destination prediction offers an important category of location-based applications and provides essential intelligence to business and governments. In existing studies, a common approach to destination prediction is to match the given query trajectory with massive recorded trajectories by similarity calculation. Unfortunately, due to privacy concerns, budget constraints, and many other factors, in most circumstances, we can only obtain a sparse trajectory dataset. In sparse dataset, the available moving trajectories are far from enough to cover all possible query trajectories; thus the predictability of the matching-based approach will decrease remarkably. Toward destination prediction with sparse dataset, instead of searching similar trajectories over the sparse records, we alternatively examine the changes of distances from sampling locations to final destination on query trajectory. The underlying idea is intuitive: It is directly motivated by travel purpose, people always get closer to the final destination during the movement. By borrowing the conception of gradient descent in optimization theory, we propose a novel moving destination prediction approach, namely MGDPre. Building upon the mobility gradient descent, MGDPre only investigates the behavior characteristics of query trajectory itself without matching historical trajectories, and thus is applicable for sparse dataset. We evaluate our approach based on extensive experiments, using GPS trajectories generated by a sample of taxis over a 10-day period in Shenzhen city, China. The results demonstrate that the effectiveness, efficiency, and scalability of our approach outperform state-of-the-art baseline methods.