Existing multi-behavior recommendations tend to prioritize performance at the expense of explainability, while current explainable methods suffer from limited generalizability due to their reliance on external information. Neuro-Symbolic integration offers a promising avenue for explainability by combining neural networks with symbolic logic rule reasoning. Concurrently, we posit that user behavior chains (e.g., view->cart->buy) inherently embody an endogenous logic suitable for explicit reasoning. However, these observational multiple behaviors are plagued by confounders, causing models to learn spurious correlations. By incorporating causal inference into this Neuro-Symbolic framework, we propose a novel Causal Neuro-Symbolic Reasoning model for Explainable Multi-Behavior Recommendation (CNRE). CNRE operationalizes the endogenous logic by simulating a human-like decision-making process. Specifically, CNRE first employs hierarchical preference propagation to capture heterogeneous cross-behavior dependencies. Subsequently, it models the endogenous logic rule implicit in the user's behavior chain based on preference strength, and adaptively dispatches to the corresponding neural-logic reasoning path (e.g., conjunction, disjunction). This process generates an explainable causal mediator that approximates an ideal state isolated from confounding effects. Extensive experiments on three large-scale datasets demonstrate CNRE's significant superiority over state-of-the-art baselines, offering multi-level explainability from model design and decision process to recommendation results.

Sequential recommender systems (SRSs) are designed to suggest relevant items to users by analyzing their interaction sequences. However, SRSs often suffer from exposure bias in these sequences due to imbalanced item exposure and varied user activity levels, creating a self-reinforcing loop favoring popular items regardless of their true relevance. Most SRSs only focus on item dependencies to address exposure bias, while overlooking user-side exposure bias and the rich semantics behind interactions. These oversights result in a limited understanding of less active users' preferences and inaccurate preference capture for less exposed items, exacerbating exposure biases. Towards this end, we propose a novel methodLLM-enhancedDualPropensity ScoreEstimation (LDPE), which synergistically integrates Large Language Models (LLMs) and causal inference. First, LDPE leverages LLMs' superior ability in capturing rich semantics from textual data and then integrates collaborative information to generate debiased semantic-rich LLM-based user/item embeddings. With these debiased item/user embeddings, LDPE estimates time-aware debiased propensity scores from both the item and user sides. These dual propensity scores can fully mitigate exposure bias by considering item popularity, user activity levels, and temporal dynamics. Lastly, LDPE employs the transformer as the backbone of our method, incorporating estimated dual propensity scores for accurately predicting users' true preferences. Extensive experiments show that our LDPE outperforms state-of-the-art baselines in terms of recommendation performance.

Multi-Behavior Recommendation (MBR) aims to model personalized user preferences by integrating diverse interaction behaviors (e.g., page view, favorite, add to cart, purchase). However, latent confounders such as contextual influences and social relationships can obscure the true causal effects in real-world scenarios, thereby confounding the model’s prediction. Although existing MBR research extensively explores behavioral dependencies and heterogeneity, it frequently overlooks the impact of latent confounders, thereby limiting its ability to capture users’ genuine preferences. To address the limitations of existing methods, we identify two key challenges in MBR: (1) how to infer latent confounders, and (2) how to mitigate their influence across multi-behavior interactions. To this end, we propose Causal Variational Inference for Deconfounded (CVID) MBR. CVID employs a variational graph autoencoder to model latent uncertainty in multi-behavior interactions and introduces a confounder inference module to generate behavior-specific latent confounders via variational inference. In the conditional diffusion module, noise is progressively injected during the forward process to simulate the dynamic evolution of user preferences, while the reverse process leverages the inferred latent confounders to guide denoising through back-door adjustment, thereby recovering the true causal effects between multi-behavior interactions and the model’s prediction. Extensive experiments on public multi-behavior datasets demonstrate that CVID consistently outperforms state-of-the-art baselines in mitigating confounding effects and improving recommendation accuracy, validating its effectiveness and superiority.

Overlapping graph clustering is essential to understand the nature and behavior of real complex systems including human interactions, technical systems and transportation network. However, in addition of topological structure, many real-world networked systems contain spare factors, i.e., attributes of networks. Despite the considerable efforts that have been made in graph clustering, they only concentrate on the topological structure, which lack a profound understanding of cluster configuration on attributed graphs. To address this great challenge, in this article, we propose a new overlapping graph clustering algorithm by integrating the topological and attributive information into a cluster potential game (CPG). Firstly, a generalized definition of the utility function is provided, which measures the payoff of each node based on different node-to-cluster distance functions. It is worth mentioning that the model we proposed is able to associate with the classic ordinal potential game well. Then, we define the measures of both tightness and the homogeneity in each cluster, and introduce a novel two-way selection mechanism. The goal is to extend the flexibility of the cluster potential game, so that one can achieve a win-win situation between nodes and clusters. Finally, a distributed and heterogeneous multiagent system (DHMAS) is carefully designed based on a fast self-learning algorithm (SLA) for attributed overlapping graph clustering. Two series of experiments are implemented in multi-types datasets and the results verify the effectiveness and the scalability after the comparison with the most advanced approaches of literature.

The rapid development of Massive Open Online Courses (MOOCs) platforms has created an urgent need for an efficient personalized course recommender system that can assist learners of all backgrounds and levels of knowledge in selecting appropriate courses. Currently, most existing methods utilize a sequential recommendation paradigm that captures the user’s learning interests from their learning history, typically through recurrent or graph neural networks. However, fewer studies have explored how to incorporate principles of human learning at both the course and category levels to enhance course recommendations. In this article, we aim at addressing this gap by introducing a novel model, named Prerequisite-Enhanced Catory-Aware Graph Neural Network (PCGNN), for course recommendation. Specifically, we first construct a course prerequisite graph that reflects the human learning principles and further pre-train the course prerequisite relationships as the base embeddings for courses and categories. Then, to capture the user’s complex learning patterns, we build an item graph and a category graph from the user’s historical learning records, respectively: (1) the item graph reflects the course-level local learning transition patterns and (2) the category graph provides insight into the user’s long-term learning interest. Correspondingly, we propose a user interest encoder that employs a gated graph neural network to learn the course-level user interest embedding and design a category transition pattern encoder that utilizes GRU to yield the category-level user interest embedding. Finally, the two fine-grained user interest embeddings are fused to achieve precise course prediction. Extensive experiments on two real-world datasets demonstrate the effectiveness of PCGNN compared with other state-of-the-art methods.

Detecting significant communities via an algorithmic game-theoretic model has recently shown great promise, which seeks to formulate community detection as a competitive game, enabling us to study the network's potential structure with a systematic tool. However, fully leveraging its potential to uncover the mechanism behind community formation remains a challenge. Here we proposeSCG—a Sequential Community Game model to track and characterize the network's structural property. Unlike conventional formulations where individual nodes are treated as players, our model considers communities as players who strive to maximize their structural utility by strategically selecting member nodes. By prioritizing significant communities sequentially,SCGenables differentiation between uncovered communities. Importantly, we establish the existence of a strict Nash equilibrium inSCG, suggesting its ability to capture a stable community structure. We run extensive experiments on several synthetic and real-world networks to testSCG's performance. Results show thatSCGcan help us well track the network's structural properties and also give us reliable performance compared to related baselines.

The joint use of node features and network topology to detect communities is called community detection in attributed networks. Most of the existing work along this line has been carried out through objective function optimization and has proposed numerous approaches. However, they tend to focus only on lower-order details, i.e., capture node features and network topology from node and edge views, and purely seek a higher degree of optimization to guarantee the quality of the found communities, which exacerbates unbalanced communities and free-rider effect. To further clarify and reveal the intrinsic nature of networks, we conduct triangle-oriented community detection considering node features and network topology. Specifically, we first introduce a triangle-based quality metric to preserve higher-order details of node features and network topology, and then formulate so-called two-level constraints to encode lower-order details of node features and network topology. Finally, we develop a local search framework based on optimizing our objective function consisting of the proposed quality metric and two-level constraints to achieve both non-overlapping and overlapping community detection in attributed networks. Extensive experiments demonstrate the effectiveness and efficiency of our framework and its potential in alleviating unbalanced communities and free-rider effect.

Tourism is an important industry and a popular leisure activity involving billions of tourists per annum. One challenging problem tourists face is identifying attractive Places-of-Interest (POIs) and planning the personalized trip with time constraints. Most of the existing trip recommendation methods mainly consider POI popularity and user preferences, and focus on the last visited POI when choosing the next POI. However, the visit patterns and their asymmetry property have not been fully exploited. To this end, in this article, we present a GRM-RTrip (short for G raph-based R epresentation M ethod for R einforce Trip Recommendation) framework. GRM-RTrip learns POI representations from incoming and outgoing views to obtain asymmetric POI-POI transition probability via POI-POI graph networks, and then fuses the trained POI representation into a user-POI graph network to estimate user preferences. Finally, after formulating the personalized trip recommendation as a Markov Decision Process (MDP), we utilize a reinforcement learning algorithm for generating a personalized trip with maximal user travel experience. Extensive experiments are performed on the public datasets and the results demonstrate the superiority of GRM-RTrip compared with the state-of-the-art trip recommendation methods.

Community detection on social networks is a fundamental and crucial task in the research field of social computing. Here we proposeDSCPCD—a dual structural consistency preserving community detection method to uncover the hidden community structure, which is designed regarding two criteria: 1) users interact with each other in a manner combining uncertainty and certainty; 2) original explicit network (two linked users are friends) and potential implicit network (two linked users have common friends) should have a consistent community structure, i.e.,dual structural consistency. Particularly,DSCPCDformulates each user in a social network as an individual in an evolutionary game associated with community-aware payoff settings, where the community state evolves under the guidance of replicator dynamics. To further seek each user's membership, we develop ahappinessindex to measure all users’ satisfaction towards two community structures in explicit and implicit networks, meanwhile, the dual community structural consistency between the two networks is also characterized. Specifically, each user is assumed to maximize thehappinessbounded by the evolutionary community state. We evaluateDSCPCDon several real-world and synthetic datasets, and the results show that it can yield substantial performance gains in terms of detection accuracy over several baselines.

Tourism is an important industry and a popular entertainment activity involving billions of visitors per annum. One challenging problem tourists face is identifying satisfactory products from vast tourism information. Most of travel recommendation methods regard the recommendation procedure as a static process and only focus on immediate rewards. Meanwhile, they often infer user intensions from click behaviors and ignore the informative keywords of the clicked products. To this end, in this article, we present a Keywords-enhanced Deep Reinforcement Learning model (KDRL) framework. Specifically, we formalize travel recommendation as a Markov Decision Process and implement it upon the Actor–Critic framework. It integrates keyword information into the reinforcement learning–(RL) based recommendation framework by devising novel state representation and reward function and learns the travel recommendation and keywords generation simultaneously. To the best of our knowledge, this is the first time that keywords are explicitly discussed and used in RL-based travel recommendations. Extensive experiments are performed on the real-world datasets and the results clearly show the superior performance of KDRL compared with the baseline methods.

Session-based travel packages recommendation aims to predict users’ next click based on their current and historical sessions recorded by Online Travel Agencies (OTAs). Recently, an increasing number of studies attempted to apply Graph Neural Networks (GNNs) to the session-based recommendation and obtained promising results. However, most of them do not take full advantage of the explicit latent structure from attributes of items, making learned representations of items less effective and difficult to interpret. Moreover, they only combine historical sessions (long-term preferences) with a current session (short-term preference) to learn a unified representation of users, ignoring the effects of historical sessions for the current session. To this end, this article proposes a novel session-based model named STR-VGAE, which fills subtasks of the travel packages recommendation and variational graph auto-encoders simultaneously. STR-VGAE mainly consists of three components: travel packages encoder , users behaviors encoder , and interaction modeling . Specifically, the travel packages encoder module is used to learn a unified travel package representation from co-occurrence attribute graphs by using multi-view variational graph auto-encoders and a multi-view attention network. The users behaviors encoder module is used to encode user’ historical and current sessions with a personalized GNN, which considers the effects of historical sessions on the current session, and coalesce these two kinds of session representations to learn the high-quality users’ representations by exploiting a gated fusion approach. The interaction modeling module is used to calculate recommendation scores over all candidate travel packages. Extensive experiments on a real-life tourism e-commerce dataset from China show that STR-VGAE yields significant performance advantages over several competitive methods, meanwhile provides an interpretation for the generated recommendation list.

Accurate house prediction is of great significance to various real estate stakeholders such as house owners, buyers, and investors. We propose a location-centered prediction framework that differs from existing work in terms of data profiling and prediction model. Regarding data profiling, we make an important observation as follows – besides the in-house features such as floor area, the location plays a critical role in house price prediction. Unfortunately, existing work either overlooked it or had a coarse grained measurement of locations. Thereby, we define and capture a fine-grained location profile powered by a diverse range of location data sources, including transportation profile, education profile, suburb profile based on census data, and facility profile. Regarding the choice of prediction model, we observe that a variety of approaches either consider the entire data for modeling, or split the entire house data and model each partition independently. However, such modeling ignores the relatedness among partitions, and for all prediction scenarios, there may not be sufficient training samples per partition for the latter approach. We address this problem by conducting a careful study of exploiting the Multi-Task Learning (MTL) model. Specifically, we map the strategies for splitting the entire house data to the ways the tasks are defined in MTL, and select specific MTL-based methods with different regularization terms to capture and exploit the relatedness among tasks. Based on real-world house transaction data collected in Melbourne, Australia, we design extensive experimental evaluations, and the results indicate a significant superiority of MTL-based methods over state-of-the-art approaches. Meanwhile, we conduct an in-depth analysis on the impact of task definitions and method selections in MTL on the prediction performance, and demonstrate that the impact of task definitions on prediction performance far exceeds that of method selections.

Vulnerability assessment—a critical issue for networks—attempts to foresee unexpected destructive events or hostile attacks in the whole system. In this article, we consider a new Markov global connectivity metric—Kemeny constant, and take its derivative called Markov criticality to identify critical links. Markov criticality allows us to find links that are most influential on the derivative of Kemeny constant. Thus, we can utilize it to identity a critical link ( i , j ) from node i to node j , such that removing it leads to a minimization of networks’ global connectivity, i.e., the Kemeny constant. Furthermore, we also define a novel vulnerability index to measure the average speed by which we can disconnect a specified ratio of links with network decomposition. Our method is of high efficiency, which can be easily employed to calculate the Markov criticality in real-life networks. Comprehensive experiments on several synthetic and real-life networks have demonstrated our method’s better performance by comparing it with state-of-the-art baseline approaches.

The design of fusion engines is a subject of great importance in a variety of fields. In this paper, we focus on the problem of linear fusion at the feature level for multiple signal matrices with noises, with the features being extremal eigenvectors. When given multiple similarity matrices, the objective is to find an estimate of the latent signal eigenspace. The concentration result for the inner product of features from different matrix samples is developed, utilizing the random matrix theory. Based on of the theoretical results, we proposed an efficient algorithm,EigFuse, to solve the constrained data-driven optimization problem with different level of noises. Our method is of high efficiency by comparing it with state-of-the-art baseline approaches with multiple noise levels. Comprehensive experiments on several synthetic as well as real-life networks demonstrate our method’s superior performance.

As an e-commerce feature, the personalized recommendation is invariably highly-valued by both consumers and merchants. The e-tourism has become one of the hottest industries with the adoption of recommendation systems. Several lines of evidence have confirmed the travel-product recommendation is quite different from traditional recommendations. Travel products are usually browsed and purchased relatively infrequently compared with other traditional products (e.g., books and food), which gives rise to the extreme sparsity of travel data. Meanwhile, the choice of a suitable travel product is affected by an army of factors such as departure, destination, and financial and time budgets. To address these challenging problems, in this article, we propose a Probabilistic Matrix Factorization with Multi-Auxiliary Information (PMF-MAI) model in the context of the travel-product recommendation. In particular, PMF-MAI is able to fuse the probabilistic matrix factorization on the user-item interaction matrix with the linear regression on a suite of features constructed by the multiple auxiliary information. In order to fit the sparse data, PMF-MAI is built by a whole-data based learning approach that utilizes unobserved data to increase the coupling between probabilistic matrix factorization and linear regression. Extensive experiments are conducted on a real-world dataset provided by a large tourism e-commerce company. PMF-MAI shows an overwhelming superiority over all competitive baselines on the recommendation performance. Also, the importance of features is examined to reveal the crucial auxiliary information having a great impact on the adoption of travel products.

With the explosion of social media networks, many modern applications are concerning about people's connections, which leads to the so-called social computing. An elusive question is to study how opinion communities form and evolve in real-world networks with great individual diversity and complex human connections. In this scenario, the classic K-means technique and its extended versions could not be directly applied, as they largely ignore the relationship among interactive objects. On the other side, traditional community detection approaches in statistical physics would be neither adequate nor fair: they only consider the network topological structure but ignore the heterogeneous-objects' attributive information. To this end, we attempt to model a realistic social media network as a discrete-time dynamical system, where the opinion matrix and the community structure could mutually affect each other. In this paper, community detection in social media networks is naturally formulated as a multi-objective optimization problem (MOOP), i.e., finding a set of densely connected components with similar opinion vectors. We propose a novel and powerful graph K-means framework, which is composed of three coupled phases in each discrete-time period. Specifically, the first phase uses a fast heuristic approach to identify those opinion leaders who have relatively high local reputation; the second phase adopts a novel dynamic game model to find the locally Pareto-optimal community structure; and the final phase employs a robust opinion dynamics model to simulate the evolution of the opinion matrix. We conduct a series of comprehensive experiments on real-world benchmark networks to validate the performance of GK-means through comparisons with the state-of-the-art graph clustering technologies.

The association-rule-based approach is one of the most common technologies for building recommender systems and it has been extensively adopted for commercial use. A variety of techniques, mainly including eligible rule selection and multiple rules combination, have been developed to create effective recommendation. Unfortunately, little attention has been paid to the scalability concern of rule-based recommendation methods. However, the computational complexity of rule-based methods shall increase drastically with the growth of both online customers and rules, which are usually several millions in typical e-commerce platforms. Moreover, the dynamic change of users’ actions requires rule-based methods make recommendations in nearly real-time, which further highlights the scalability issue of rule-based recommender systems. In this article, we present a distributed framework that can scale different association-rule-based recommendation methods in a unified way. Specifically, based on the summarization of existing rule-based approaches, a generic tree-type structure is defined to store separate kinds of patterns, and an efficient algorithm is designed for mining eligible patterns along with computing recommendation scores. To handle the ever-increasing number of online customers, a distributed framework is proposed, where two load-balanced strategies for partitioning tree are put forward to fit sparse and dense data, respectively. Extensive experiments on five real-life data sets demonstrate that the efficiency of association-rule-based recommender systems can be significantly improved by the proposed framework.

Multi-task learning aims to learn multiple tasks jointly by sharing information among related tasks such that the generalization performance over different tasks could be improved. Although multi-task learning has been demonstrated to obtain performance gain in comparison with the single task learning, the main challenge that learning what to share with whom is still not fully resolved. In this paper, we propose a robust clustered multi-task learning approach that clusters tasks into several groups by learning the representative tasks. The main assumption behind our approach is that each task can be represented by a linear combination of some representative tasks that can characterize all tasks. The correlation between tasks can be indicated by the corresponding combination coefficient. By imposing a row-sparse constraint on the correlation matrix, our approach could select the representative tasks and encourage information sharing among the related tasks. In addition, the $l_1,2 $-norm is applied to the representation loss to enhance the robustness of our approach. To solve the resulting bi-convex optimization problem, we design an efficient optimization method based on the alternating direction method of multipliers and accelerated proximal gradient method. Finally, experimental results on synthetic and real-world data sets validate the effectiveness of the proposed approach.

Driven by profits, spam reviews for product promotion or suppression become increasingly rampant in online shopping platforms. This paper focuses on detecting hidden spam users based on product reviews. In the literature, there have been tremendous studies suggesting diversified methods for spammer detection, but whether these methods can be combined effectively for higher performance remains unclear. Along this line, a hybrid PU-learning-based Spammer Detection (hPSD) model is proposed in this paper. On one hand, hPSD can detect multi-type spammers by injecting or recognizing only a small portion of positive samples, which meets particularly real-world application scenarios. More importantly, hPSD can leverage both user features and user relations to build a spammer classifier via a semi-supervised hybrid learning framework. Experimental results on movie data sets with shilling injection show that hPSD outperforms several state-of-the-art baseline methods. In particular, hPSD shows great potential in detecting hidden spammers as well as their underlying employers from a real-life Amazon data set. These demonstrate the effectiveness and practical value of hPSD for real-life applications.

The objective of consensus clustering is to find a single partitioning which agrees as much as possible with existing basic partitionings. Consensus clustering emerges as a promising solution to find cluster structures from heterogeneous data. As an efficient approach for consensus clustering, the K-means based method has garnered attention in the literature, however the existing research efforts are still preliminary and fragmented. To that end, in this paper, we provide a systematic study of K-means-based consensus clustering (KCC). Specifically, we first reveal a necessary and sufficient condition for utility functions which work for KCC. This helps to establish a unified framework for KCC on both complete and incomplete data sets. Also, we investigate some important factors, such as the quality and diversity of basic partitionings, which may affect the performances of KCC. Experimental results on various realworld data sets demonstrate that KCC is highly efficient and is comparable to the state-of-the-art methods in terms of clustering quality. In addition, KCC shows high robustness to incomplete basic partitionings with many missing values.

The backbone is the natural abstraction of a complex network, which can help people to understand it in a more simplified form. Backbone extraction becomes more challenging as many networks are evolving into large scale and the weight distributions are spanning several orders of magnitude. Traditional filter-based methods tend to include many outliers into the backbone. What is more, they often suffer from the computational inefficiency-the exhaustive search of all nodes or edges is often prohibitively expensive. In this work, we propose a Local Search based Backbone Extraction Heuristic (LS-BEH) to find the backbone in a complex weighted network. First, a strict filtering rule is carefully designed to determine edges to be preserved or discarded. Second, we present a local search model to examine part of edges in an iterative way. Experimental results on two real-life networks demonstrate the advantage of LS-BEH over the classic disparity filter method by either effectiveness or efficiency validity.

Detecting abnormalities from multiple correlated time series is valuable to those applications where a credible realtime event prediction system will minimize economic losses (e.g. stock market crash) and save lives (e.g. medical surveillance in the operating theatre). For example, in an intensive care scenario, anesthetists perform a vital role in monitoring the patient and adjusting the flow and type of anesthetics to the patient during an operation. An early awareness of possible complications is vital for an anesthetist to correctly react to a given situation. In this demonstration, we provide a comprehensive medical surveillance system to effectively detect abnormalities from multiple physiological data streams for assisting online intensive care management. Particularly, a novel online support vector regression (OSVR) algorithm is developed to approach the problem of discovering the abnormalities from multiple correlated time series for accuracy and real-time efficiency. We also utilize historical data streams to optimize the precision of the OSVR algorithm. Moreover, this system comprises a friendly user interface by integrating multiple physiological data streams and visualizing alarms of abnormalities.

Recent years have witnessed the explosive growth of online social media. Weibo, a famous "Chinese Twitter", has attracted over 0.5 billion users in less than four years, with more than 1000 tweets generated in every second. These tweets are informative but very fragmented, and thus would be better archived from an event perspective, as done by Weibo itself in the "Micro-Topic" program. This effort, however, is yet far from satisfaction for not providing enough analytical power to events. In light of this, in this demo paper, we propose SEA, a System for Event Analysis on Chinese tweets. In general, SEA is an event-centric, multi-functional platform that conducts panoramic analysis on Weibo events from various aspects, including the semantic information of the events, the temporal and spatial trends, the public sentiments, the hidden sub-events, the key users in the event diffusion and their preferences, etc. These functions are enabled by the integration of various analytical models and by the noSQL techniques adopted purposefully for massive tweets management. Finally, a case study on the "Spring Festival" event demonstrates the effectiveness of SEA. To our best knowledge, SEA is the first third-party system that provides panoramic analysis to Weibo events.

Shilling attackers apply biased rating profiles to recommender systems for manipulating online product recommendations. Although many studies have been devoted to shilling attack detection, few of them can handle the hybrid shilling attacks that usually happen in practice, and the studies for real-life applications are rarely seen. Moreover, little attention has yet been paid to modeling both labeled and unlabeled user profiles, although there are often a few labeled but numerous unlabeled users available in practice. This paper presents a Hybrid Shilling Attack Detector, or HySAD for short, to tackle these problems. In particular, HySAD introduces MC-Relief to select effective detection metrics, and Semi-supervised Naive Bayes (SNB_lambda) to precisely separate Random-Filler model attackers and Average-Filler model attackers from normal users. Thorough experiments on MovieLens and Netflix datasets demonstrate the effectiveness of HySAD in detecting hybrid shilling attacks, and its robustness for various obfuscated strategies. A real-life case study on product reviews of Amazon.cn is also provided, which further demonstrates that HySAD can effectively improve the accuracy of a collaborative-filtering based recommender system, and provide interesting opportunities for in-depth analysis of attacker behaviors. These, in turn, justify the value of HySAD for real-world applications.

Collaborative filtering (CF) based recommender systems are vulnerable to shilling attacks. In some leading e-commerce sites, there exists a large number of unlabeled users, and it is expensive to obtain their identities. Existing research efforts on shilling attack detection fail to exploit these unlabeled users. In this article, Semi-SAD, a new semi-supervised learning based shilling attack detection algorithm is proposed. Semi-SAD is trained with the labeled and unlabeled user profiles using the combination of naïve Bayes classifier and EM-», augmented Expectation Maximization (EM). Experiments on MovieLens datasets show that our proposed Semi-SAD is efficient and effective.