Frequency-domain sequential recommendation models enhance sequence representation capacity through spectral transformations. However, existing methods typically adopt coarse-grained spectrum reweighting strategies that strengthen high-frequency components while amplifying random noise within frequency bands. Moreover, they generally rely on a coupled modeling mechanism that handles both long-term and short-term preferences within a single backbone network, lacking dedicated modeling paths tailored to their distinct temporal characteristics. To address these challenges, we propose a Balanced Frequency Decoupling Sequential Recommendation model (BFDRec). Specifically, we design an energy-aware spectrum denoising mechanism to adaptively suppress low-energy noises according to the energy distribution within each frequency band while preserving salient behavioral fluctuation signals. Additionally, we construct a multi-scale decoupled architecture to model users' multi-scale preferences and adaptively integrate them through a dynamic gating mechanism, aligning the sequence modeling process with the distinct temporal characteristics of different frequency bands. Extensive experiments across five real-world datasets demonstrate that BFDRec effectively achieves noise suppression and accurate multi-scale preference modeling, with average improvements of 6.67% and 5.05% in HR and NDCG, respectively, over advanced baseline models. Our code is available at https://anonymous.4open.science/r/BFDRec.

Graph neural networks (GNNs) have shown considerable promise in multi-behavior recommendation tasks, particularly for target behavior prediction (e.g., purchase conversion), by effectively integrating auxiliary behavioral signals (e.g., item browsing, cart addition). Recent advances in the field have substantially improved the modeling of hierarchical interactions and multi-behavior dependencies, effectively mitigating foundational challenges such as data sparsity. However, these state-of-the-art methods frequently overlook the semantic heterogeneity and inherent noise within auxiliary interactions, often resorting to uniform or simplistic denoising strategies that risk discarding valuable signals. To overcome this persistent limitation, the Denoising Cascade-Enhanced Multi-Behavior Recommendation (DCE-MBR) framework is introduced. DCE-MBR is designed to simultaneously suppress noise and preserve semantically informative interactions through a dual-stage architecture. First, a hierarchical graph denoising module dynamically removes noisy edges by applying behavior-specific thresholds across multiple levels of granularity, thereby preserving essential neighbor relations. Next, a cascade-enhanced module incrementally refines user preferences by propagating target behavior signals through auxiliary behavior paths, leading to improved feature representations. Comprehensive evaluations based on the Taobao as well as Tmall data collections show that DCE-MBR outperforms state-of-the-art baselines, achieving relative gains of 18.66% in Hit@10 and 15.42% in NDCG@10. These results confirm the model’s robustness against noisy interactions and its effectiveness in capturing intricate multi-behavior dependencies. The source code is publicly available at DCEMBR 1 .

Deep reinforcement learning (DRL) has emerged as a promising paradigm for home energy management systems (HEMS) due to its model-free nature and ability to handle complex dynamics. However, existing DRL-based approaches typically employ a unified reward function that aggregates multiple objectives into a single scalar, failing to account for the heterogeneous roles of controllable energy devices (CEDs) and their distinct causal relationships with control objectives. This leads to reward misattribution, where CEDs with simpler constraints dominate the optimization process while critical components such as battery storage remain underutilized. To address this challenge, we propose a causally aligned multi-agent reinforcement learning (MARL) framework that explicitly models CED-objective causal pathways using a structural causal model (SCM). A causal surgery procedure decomposes shared objectives into CED-specific variants, enabling individualized reward signals aligned with each CED’s causal responsibility. The proposed HR-MASAC algorithm features a multi-head centralized critic for learning vectorized Q-values and agent-specific entropy coefficients for heterogeneous exploration. Experiments across diverse home scenarios demonstrate that our method achieves 40.1% cost reduction and 57.1% comfort improvement over unified-reward baselines, with robust performance under sensor noise and household heterogeneity.

Session-based recommendation predicts the next item a user will interact with based on their short-term session behavior, typically without long-term user profiles. Existing approaches often fail to capture the hierarchical nature of user preferences, leading to suboptimal personalization and limited recommendation accuracy. In this work, we argue that user preferences exhibit coarse-grained and fine-grained characteristics, and item features should be modeled accordingly across these two levels to capture users' preference signals more accurately. To this end, we propose a novel method, Multi-Granularity Preference Enhancement with Hierarchical Feature Extraction (MPEHFE), for session-based recommendation. MPEHFE explicitly captures semantic item relationships at each granularity and enhances fine-grained preference modeling through a differentiable architecture search mechanism. It also identifies interactions inconsistent with the user's general intent as noise, leveraging contrastive learning to reinforce the representation of coarse-grained preferences. Moreover, experiments on three real-world benchmark datasets demonstrate that MPEHFE consistently outperforms state-of-the-art baselines, achieving relative improvements of 3%-9% in P@20 and 11%-56% in MRR@20.

The long-tail recommendation problem remains a significant challenge in modern recommender systems, primarily due to data sparsity and popularity bias, which hinder the accurate ID representation of users and items. Recent advancements in large language models (LLMs) have enabled the direct modeling of user and item semantic representations, offering potential improvements in representation learning through the alignment of these two types of representations. However, systems relying on LLM representation alignment face two critical challenges: (1) the substantial differences between LLMs and recommendation models in terms of training objectives, phases, and data; (2) the pervasive popularity bias in collaborative data. These challenges create a semantic gap between ID representations and semantic representations. Directly aligning these representations risks introducing recommendation-irrelevant noise, disrupting the collaborative information embedded in ID representations, and ultimately leading to suboptimal recommendation outcomes. To address this gap, we propose DeltaRec, aDouble-enhancement framework forlong-tailRecommendation. DeltaRec tackles the long-tail recommendation problem through two approaches. First, it incorporates semantic information for all items. Second, it provides additional supervision signals specifically for long-tail items. The framework begins by disentangling ID representations into interest representations and conformity representations. To integrate semantic information from LLMs while preserving popularity information, we design a contrastive learning-based semantic alignment module that aligns interest representations with semantic representations. Furthermore, to enhance the representation learning of unpopular items, we introduce a ranking-based behavior alignment module, which provides additional supervision signals for these items. To avoid introducing recommendation-irrelevant noise and disrupting collaborative semantics due to excessive alignment, we propose a curriculum learning-based training mechanism. Extensive experiments on real-world datasets demonstrate that DeltaRec effectively mitigates popularity bias and significantly improves long-tail recommendation performance without relying on prior knowledge of popularity distributions. Our code is available athttps://github.com/leo0481/DeltaRec/E3D7.

Multi-behavior recommendation leverages multiple user-item interaction information to alleviate data sparsity. Although different types of user-item interactions are temporally mutually exclusive, the sequence of behavioral interactions consisting of multi-level positive feedback signals contains rich information. However, most existing studies have unilaterally focused on the positive utility of auxiliary behaviors, ignoring multi-level user preference information. Effectively fusing multi-behavioral data and better modeling behavioral dependencies are urgent problems that need to be addressed for multi-behavior recommendation. We propose the p arallel learning of p ositive and n egative interests with an a uxiliary-view r epresentation e nhancement (PPN-ARE) scheme for multi-level user interest learning based on multi-behavioral interaction sequences. Specifically, multi-level positive and negative feedback view chains are constructed from multi-behavioral sequence data to learn multi-level user interests. User preference evolution is simulated during multi-behavior interactions using residual connections, and the shortcomings of the cascading structure used for higher-order graph learning are analytically highlighted. The influence of low-quality embeddings of auxiliary behaviors is filtered, and the learning of target behaviors is optimized by designing a representation enhancement layer. Finally, the model is optimized using a multi-task training framework. The experimental results indicate that PPN-ARE significantly improved over the state-of-the-art (SOTA). The open source code is available at https://github.com/lhybq/PPN-ARE .

With the rapid deployment of large language model (LLM) technology across various fields, numerous LLMs have been deployed on edge servers (ESs) to provide low-latency generative services for edge devices. However, as factual knowledge evolves, the massive number of parameters in LLMs poses significant challenges for updating LLMs on ESs. Existing studies employ federated fine-tuning to update LLMs, but these unconstrained updating approaches can lead to overfitting and knowledge forgetting, while also resulting in substantial overhead. Knowledge editing (KE), as a promising technology, ensures the injection of new knowledge while preserving existing knowledge by editing specific parameters. In this paper, we propose multi-ES collaborative KE for the first time and design the CoKE and pCoKE frameworks in edge-cloud scenarios. These frameworks enhance editing efficiency by extracting identical expressions of the same knowledge across different LLM parameters for collaborative editing across multiple ESs. Additionally, we incorporate a personalized selection module in pCoKE to provide domain-specific generative services on ESs. To further reduce editing latency, we design a binary search-based resource allocation algorithm to balance editing latency across ESs. Extensive experiments demonstrate that CoKE and pCoKE reduce editing latency by 73% while maintaining high editing quality. Moreover, pCoKE achieves an approximately 6% improvement in editing quality.

Recommender systems that mine users’ intentions to explore their potential interaction preferences have received increasing attention. However, the existing research on intent recommendation has some limitations. On one hand, the extant studies only consider users’ historical interaction information and the sparse interactions cannot reflect users’ potential interaction intention; on the other hand, they do not consider the changes in users’ kinematic and static intentions over time and the importance of users’ intention disentanglement representation, which makes it impossible for the general intention recommendation model to obtain a better representation of the intention. We propose a multitask recommendation model with dynamic and static intent integration and de-entanglement. The model mines users’ dynamic and static intents and then combines them with regularization to model the independence of the intents, encouraging the differences between the intents. Meanwhile, to further alleviate the data sparsity problem, this study additionally constructs user–user and item–item graphs using four different similarity measures, such as cosine similarity and mutual information, applies graph convolutional networks to learn about the three graphs, and then captures the complementarity between different graphs using a graph-level cross-attention mechanism. Extensive comparative experiments and ablation studies on three public datasets demonstrate that DSI-ID consistently outperforms all baseline methods, achieving a 3.5%–7.4% improvement in recommendation performance over the best baseline.

Along with the increasing popularization of social platforms, rumors in the Web environment have become one of the significant threats to human society. Existing rumor detection methods ignore modeling and analyzing the community structure of the rumor propagation network. This article proposes a new community-enhanced dynamic graph convolutional network (CDGCN) for effective rumor detection on online social networks, which utilize the communities formed in a rumor propagation process to improve rumor detection accuracy. CDGCN uses a designed method that combines node features and topology features to identify the communities and learn the community features of rumors. Following this, a graph convolutional network (GCN) with a community-aware attention mechanism is proposed to enable the nodes to dynamically aggregate information from their neighboring nodes’ global and community features, effectively prioritizing critical neighborhood information, enhancing the representation of both local community structures and global network patterns for improved analytical performance. The final rumor representations generated by the GCN are processed by a classifier to detect false rumors. Comprehensive experiments and comparison studies are conducted on four real-world datasets to validate the effectiveness of CDGCN.

Session-based recommendation (SBR) methods often rely on user behavior data, which can struggle with the sparsity of session data, limiting performance. Researchers have identified that beyond behavioral signals, rich semantic information in item descriptions is crucial for capturing hidden user intent. While Large Language Models (LLMs) offer new ways to leverage this semantic data, the challenges of session anonymity, short-sequence nature, and high LLM training costs have hindered the development of a lightweight, efficient LLM framework for SBR. To address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views. This two-stage framework leverages the strengths of both LLMs and traditional SBR models while minimizing training costs. In the first stage, we use multi-view prompts to infer latent user intentions at the session semantic level, supported by an intent localization module to alleviate LLM hallucinations. In the second stage, we align and unify these semantic inferences with behavioral representations, effectively merging insights from both large and small models. Extensive experiments on two real datasets demonstrate that the LLM4SBR framework can effectively improve model performance. We release our codes along with the baselines at https://github.com/tsinghua-fib-lab/LLM4SBR .

Heterogeneous computing systems are extensively utilized to execute a wide range of time-critical services, which encompass numerous interdependent tasks organized in the form of workflows. In practice, the dynamic arrival of workflows often interleaves with their execution, leading to resource contention among multiple workflows and potentially causing QoS (Quality of Service) degradation. However, compared to the extensive research on single workflow scheduling, interleaved workflow scheduling has received relatively less attention. Moreover, the challenge of effectively scheduling limited computing resources to promptly complete consecutively arriving workflows remains underexplored, despite its practical importance. To fill this gap, this work proposes a method called Urgency-based List Scheduling (ULS) for dynamically scheduling deadline-constrained interleaved workflows. In ULS, a novel task property called urgency is introduced to prioritize tasks from multiple workflows by capturing real-time execution information, and each newly arrived workflow is scheduled with the outstanding tasks of prior workflows based on a list-based strategy to make more informed decisions. Extensive evaluation experiments are performed and the findings illustrate that ULS can achieve a reduction of at least 68% in deadline miss rates and 77% in overall tardiness compared to existing methods.

Federated point-of-interest (POI) recommendation achieves global model training and optimization through a distributed training framework, ensuring that user data is always stored locally on the client side, thereby effectively protecting user data privacy. However, this distributed nature of data also severely limits the performance improvement of POI recommendation models under federated learning. On the one hand, in such a distributed data environment, the semantic fragmentation of feature spaces in local client data hinders the learning of user personalized preference representations, thereby limiting the improvement of local model personalization performance. On the other hand, the heterogeneity in data quantity, quality, and distribution among clients leads to significant differences in local model training.The traditional average aggregation strategy is difficult to effectively alleviate this difference, affecting the global aggregation efficiency and resulting in insufficient performance of the global model. To address these challenges, this paper proposes a federated POI recommendation method based on heterogeneous graph semantics (FedHGS). This method enhances the representation of local user preferences and improves the personalization of local models by learning personalized user preference features through heterogeneous graph semantic mining. Additionally, it introduces local model distillation alignment and performance-aware aggregation to balance training differences across clients and improve the performance of the global POI recommendation model. Finally, extensive experiments are conducted to verify both the global and local performance advantages of FedHGS.

The rise of smart devices has accelerated location-based services, creating vast trajectory data for Point-of-Interest (POI) recommendations. However, user omissions or privacy concerns often result in incomplete trajectory data, compromising sequential patterns and spatiotemporal relationships. Existing solutions using graph structures, self-supervised learning (SSL), or spatiotemporal contexts still face two limitations: (1) graph-based and SSL methods produce suboptimal trajectory representations due to respective inherent constraints; (2) noise interference persists when modeling distorted spatiotemporal signals. To mitigate these issues, we propose aDynamic Structure-aware GraphMasked Autoencoder andSpatiotemporalDiffusion for Next-POIRecommendation (DMSDRec). Specifically, we introduce a dynamic structure-aware improved graph masked autoencoder that adaptively and dynamically distills global transitional information for self-supervised augmentation. It naturally avoids the noise introduced by existing SSL methods' dependency on manual views augmentation. Meanwhile, the masked reconstruction task synergistically enhances trajectory representations by capturing deeper cross-sequence dependencies. Additionally, we propose an effective latent-space spatiotemporal diffusion denoising method. First, we employ graph structures to model spatiotemporal relationships, utilizing higher-order structural information to alleviate the linear spatiotemporal relationship deviations caused by incomplete trajectories. Building on this, we implement diffusion models in the latent space to systematically identify and remove noise from spatiotemporal representations. Through experimental results on two real-world datasets, we demonstrate the superiority of our proposed DMSDRec in terms of recommendation accuracy and robustness.

The current sequential recommendation systems mainly focus on mining information related to users to make personalized recommendations. However, there are two subjects in the user historical interaction sequence: users and items. We believe that mining sequence information only from the users' perspective is limited, ignoring effective information from the perspective of items, which is not conducive to alleviating the data sparsity problem. To explore potential links between items and use them for recommendation, we propose Intent-guided Bilateral Long and Short-Term Information Mining with Contrastive Learning for Sequential Recommendation (IBLSRec), which interpretively integrates three kinds of information mined from the sequence: user preferences, user intentions, and potential relationships between items. Specifically, we model the potential relationships between interactive items from a long-term and short-term perspective. The short-term relationship between items is regarded as noise; the long-term relationship between items is regarded as a stable common relationship and integrated with the user's personalized preferences. In addition, user intent is used to guide the modeling of user preferences to refine the representation of user preferences further. A large number of experiments on four real data sets validate the superiority of our model.

In recent years, next Point-of-Interest (POI) recommendation is essential for many location-based services, aiming to predict the most likely POI a user will visit next. Current research employs graph-based and sequential methods, which have significantly improved performance. However, there are still limitations: numerous methods overlook the fact that user intent is constantly changing and complex. Furthermore, prior studies have seldom addressed spatiotemporal correlations while considering differences in user behavior patterns. Additionally, implicit feedback contains noise. To address these issues, we propose a recommender model named HGDRec for the next POI recommendation. Specifically, we introduce an approach for extracting trajectory intent by integrating multi-dimensional trajectory representations to achieve a multi-level understanding of user trajectories. Then, by analyzing users' long trajectories, we construct global hypergraph structures across spatiotemporal regions to comprehensively capture user behavior patterns. Additionally, to further optimize trajectory intent representation, we employ a feature optimization method based on the improved diffusion model. Extensive experiments on three real-world datasets validate the superiority of HGDRec over the state-of-the-art methods.

Users' behaviors on recommendation platforms are typically driven by evolving intentions. Existing sequential recommendation models have two main limitations in capturing these intentions: insufficient modeling of higher-order relationships between prefix sequences and target items, and lack of effective mechanisms for capturing complex temporal dependencies. To address these challenges, we propose a Spatio-Temporal Intent Modeling framework (STIRec) that enhances recommendations through spatial and temporal dimensions. Our key innovations include: (1) a Multi-Hop Intent Aggregation mechanism that constructs a Spatial Intent Graph modeling three types of relationships (prefix-target, prefix-prefix, target-target), capturing common intent patterns through graph neural networks from a global perspective; (2) a Multi-Span Self-Attention module that fuses long and short-term query information to comprehensively model user behaviors and evolving intentions across temporal dimensions. These complementary mechanisms work together to understand user intent better, integrating global contextual patterns and temporal evolution dynamics. Experiments on five public datasets show that STIRec outperforms state-of-the-art methods by an average of 9.78% in recommendation accuracy, with enhanced robustness against noisy data. Source code is available athttps://github.com/theshy877/STIRec.

Next Point-of-interest recommendation involves modeling user interactions with Point-of-interests (PoIs) to analyze user behavior patterns and suggest future scenarios. Data sparsity problems in PoI recommendations can significantly impact the performance of the recommendation model. This paper introduces the Graph Convolutional Network and Multiple Context-Aware PoI Recommendation model (GMCA). First, we present a weighted graph convolutional network that aims to capture the optimal representations of users and PoIs within the user-PoI interaction graph. Second, we employ a fine-grained approach to analyze user check-in records and cluster them into multiple user activity centers. Furthermore, we incorporate time, location, and social context information into the matrix decomposition process. Third, User activity centers are constructed by clustering user check-in records, and the geographical influence of PoI location on user behavioral patterns is explored using probabilistic factor decomposition. The evaluation of the GMCA model on the Yelp and Gowalla datasets shows a significant improvement in Precision@10 indicators. Specifically, there is a 13.85% increase in Precision@10 on the Yelp dataset and a 9.01% increase on the Gowalla dataset. The effectiveness of the GMCA model has been confirmed through numerous experiments conducted on two public datasets.

Addressing the common issues in the cultivation of collaborative innovation abilities for software engineering talents, such as imperfections in the industry-education integration system, inefficiencies in the management mechanism, and poor connections between the education chain, talent chain, and industry chain, this article introduces the implementation measures for cultivating the collaborative innovation abilities of software engineering talents from the perspectives of organizational models, training models, practical systems, and safeguard mechanisms under the context of industry-education integration.

With the unprecedented power of social media and public opinion, the widespread rumors on social media have brought a severe negative impact on public life. This paper introduces a new rumor detection method STAC(Spatial-Temporal Adversarial Classifier). STAC aggregates rumor propagation at a finer granularity by jointly modeling their spatial structural and time-series features. In addition, STAC uses an auxiliary adversarial topic classifier to improve generalization to emerging news topics. Experimental results show that STAC exhibits advantages in early detection and overall performance. STAC employs a graph convolutional network to capture the structural information of the propagation graph and uses a bidirectional recurrent neural network to learn the sequence features of the propagation path. Through a gating mechanism, STAC aggregates the learned structural features with temporal features in a fine-grained manner. STAC proves its effectiveness in the experiments by showing advantages in early detection and overall performance. STAC performs better in rumor detection tasks and can detect rumors at an early stage.

User behavior sequence modeling represents users' interests and preferences, which has a crucial impact on click-through rate (CTR) prediction models and recommendation systems. In practical scenarios, multiple types of interactive behaviors usually constitute users' complex interests and preferences. However, existing CTR prediction models based on multi-type interactive behavior modeling have two limitations: (1) they cannot handle noise in users' global interests, resulting in the inability to model accurate global interest preferences; (2) they struggle to depict users' local interest patterns and cannot model the complex patterns embedded in multi-behavior sequences. To overcome these limitations, an Adaptive Local and Global Interests Network For Click-Through Rate Prediction (ALGIN) is proposed, which effectively models global and local interests within multi-behavior interaction sequences through a unified framework. Firstly, ALGIN employs a Fourier Global Interest Modeling module to eliminate noise in the behavioral sequence; secondly, ALGIN designs a Multi-Scale Local Interest Extraction module to capture behavioral patterns within multi-type interactive sequences; finally, an Item-driven Interest Selector is used to integrate users' local interests with their global interests. Experiments on multiple public datasets demonstrate that the ALGIN model outperforms the current state-of-the-art (SOTA), and ablation experiments confirm the effectiveness of each module within the model.

In cloud computing, private cloud tends to exhibit high controllability but lack scalability, whereas public cloud is just the opposite. The hybrid cloud formed by combining them can effectively balance controllability and scalability, and has been widely adopted in industry for executing workflows. The network connecting public and private clouds goes through Internet and its bandwidth is rather limited in comparison with that inside clouds. Hence, cross-cloud data transmission can become a bottleneck of executing workflows in such environment. Moreover, multiple data communications may contend for bandwidth resources, thereby incurring delay. To address these concerns, this work establishes a scheduling model for workflow execution across public and private clouds, where a queueing mode is innovatively employed to address potential network communication contention. A contention-cognizant list scheduling (CCLS) heuristic equipped with task duplication is devised to minimize workflow makespan. It adopts a novel task sorting attribute to schedule tasks and cross-cloud data communications by using available computation and communication resources, and employs task duplication to obviate the needs for certain data communications. Experiments are conducted with realistic workflows and diverse settings, and the results verify the superiority of CCLS over the existing ones as it can always achieve the best makespanNote to Practitioners—A crucial challenge for workflow scheduling across public and private clouds is that the cross-cloud bandwidth resource is relatively limited and multiple data communications may contend for it in practice. However, this communication contention issue has largely been neglected in existing investigations. To advance the state of the art, this paper proposes a communication contention-cognizant scheduling approach based on a queueing mode to minimize the makespan for workflow execution across public and private clouds. The proposed approach can be readily put into use and experimental results show that it performs better than traditional scheduling approaches that fail to consider communication contention.

Popularity bias is a common phenomenon in the user-item interaction, which means a user interacts with the items just because of the items' popularity, but the user does not actually interest in these items. Neglecting popularity bias in recommendation systems can result in favoring popular items over personal preferences. This paper proposes a new recommendation framework for enhancing theDisEntanglement of popularity bias based onContrastiveLearning (DECL). In DECL, the interest and conformity representation sets of the users and the items are generated through a disentangled representation learning process. A contrastive learning process is then performed to optimize the distributions of the disentangled sets in the representation space. A customized loss function is designed to facilitate the parameter optimization, and the final recommendation is made based on the interest and conformity. Extensive experiments and comparison studies are conducted on three real-world datasets to validate the effectiveness of the proposed DECL framework. The experiment results show that compared with the state-of-the-art methods, DECL can achieve up to 10.69% performance improvement on the Ciao dataset. This indicates the proposed system can effectively disentangle popularity bias in recommendation and has large application potential.

Owing to real-world demands for global collaboration and increasing volumes of data to be analyzed, many data-intensive workflow applications are deployed in geographically distributed (geo-distributed) datacenters (DCs). In such an environment, inter-DC bandwidths are much slower than intra-DC ones, and how to effectively schedule inter-DC data communication without contention is crucial to a workflow's execution time. Meanwhile, the diversity of data privacy requirements in geo-distributed DCs causes an additional challenge. This paper introduces a workflow scheduling model for geo-distributed DCs where inter-DC communications are explicitly considered and data privacy is protected. A Communication-contention-Aware Privacy-preserving Scheduling (CAPS) method is proposed to solve it for the first time. CAPS distributes workflow tasks to DCs via a simulated annealing method such that privacy constraints are respected and the overall inter-DC data transmission time is minimized. It adopts a list scheduling heuristic to schedule tasks and data communications to computation and network resources, respectively. In experiments, CAPS is compared against leading-edge methods with realistic workflows and network settings. The results reveal that it can reduce workflow makespan by 7.08-87.53% in comparison with its peers, while guaranteeing data privacy and resolving all the communication contention issues, which has not been seen in the existing work.

Next point-of-interest (POI) recommendation optimizes user travel experiences and enhances platform revenues by providing users with potentially appealing next location choices. In recent research, scholars have successfully mined users' general tastes and varying interests by modeling long-term and short-term check-in sequences. However, conventional methods for long and short-term modeling predominantly employ distinct encoders to process long and short-term interaction data independently, with disparities in encoders and data limiting the ultimate performance of these models. Instead, we propose a shared trajectory encoder and a novel Contrastive learning of Long and Short-term Preferences for next POI Recommendation (CLSPRec) model to better utilize the preference similarity among the same users and distinguish different users' travel preferences for more accurate next POI prediction. CLSPRec adopts a masking strategy in long-term sequences to enhance model robustness and further strengthens user representation through short-term sequences. Extensive experiments on three real-world datasets validate the superiority of our model. Our code is publicly available at https://github.com/Wonderdch/CLSPRec.

Session-based Recommendation (SBR) has recently received significant attention due to its ability to provide personalized recommendations based on the interaction sequences of anonymous session users. The challenges facing SBR consist mainly of how to utilize information other than the current session and how to reduce the negative impact of irrelevant information in the session data on the prediction. To address these challenges, we propose a novel graph attention network-based model called Multiple Sparse Graph Attention Networks (MSGAT). MSGAT leverages two parallel channels to model intra-session and inter-session information. In the intra-session channel, we utilize a gated graph neural network to perform initial encoding, followed by a self-attention mechanism to generate the target representation. The global representation is then noise-reduced based on the target representation. Additionally, the target representation is used as a medium to connect the two channels. In the inter-session channel, the noise-reduced relation representation is generated using the global attention mechanism of target perception. Moreover, MSGAT fully considers session similarity from the intent perspective by integrating valid information from both channels. Finally, the intent neighbor collaboration module effectively combines relevant information to enhance the current session representation. Extensive experiments on five datasets demonstrate that simultaneous modeling of intra-session and inter-session data can effectively enhance the performance of the SBR model.

The next Point-of-interest (POI) recommendation task is to predict the next POI that users may be interested in. POI check-in sequence implicitly reflects the user’s location transition patterns, and the sequence modeling relies on the engineering of multiple independent features. Even though traditional POI recommendation models can fulfill the predicting task via entangled features, those black box models fail to mine the intrinsic check-in intention. The disentanglement representation learning method enables models to disentangle targeting intentions and provide interpretability for recommended results. However, existing disentanglement representation studies focus on disentangling user preference but neglect the entangled location characteristic. Besides, unrecorded check-ins result in inconsecutive transition sequences, which may influence their disentanglement qualities. Therefore, we proposed CrossDR, a Cross-sequence Location Disentanglement Representation method for the next POI recommendation, to explore how spatial and temporal factors influence check-in behaviors by a global view of location transitions. We apply disentanglement learning along with the time-masked data augmentation method and frequency-domain learning technique to further alleviate the short trajectory cold start problem caused by consecutive sequence generation. Experiments on two real-world datasets show our model has competitive capability compared to strong baselines.

Interactions of users and items can be naturally modeled as a user-item bipartite graph in recommender systems, and emerging research is devoted to exploring user-item graphs for collaborative filtering methods. In reality, user-item interaction usually stems from more complex underlying factors, such as the users’ specific preferences. A user-item bipartite graph could be used to understand the differences in motivation. However, existing research has not clearly proposed and modeled the factors that affect the differences, ignoring the similarities between user pairs and item pairs, preventing them from capturing fine-grained user preferences more effectively. In addition to the two points mentioned above, most GNN-based models for recommendation have the following two limitations: First, the model’s accuracy depends on the number of observed interactions in the dataset. Secondly, node representations are vulnerable to noisy interactions. This work has developed a novel recommendation model called “Multi-Attribute and Implicit Relationship Factors With Self-Supervised Learning for Collaborative filtering” (MIS-CF), which explicitly proposes and models multi-attribute and implicit relationship factors for collaborative filtering recommendation. Meanwhile, an auxiliary self-supervised learning task is designed to help the downstream task optimize the node representation. MIS-CF aggregates multi-attribute spaces through the user-item bipartite graph and establishes user-user and item-item graphs to model the similar relationship information of neighbor pairs through a memory model. The self-supervised learning task generates contrastive learning via self-discrimination, thus mining the rich auxiliary signals within the data, improving the accuracy and robustness of our model. Moreover, the sparse regularizer is utilized to alleviate the overfitting problem. Extensive experimental results on three public datasets not only show the significant performance and robustness gain of the proposed model but also prove the effectiveness and interpretability of fine-grained implicit factors modeling.

To support rapidly increasing services and applications from users, multi-tier computing is emerged as a promising system-level computing architecture by distributing computing/caching/communication/networking capabilities between cloud servers to users, especially deploying edge servers at network edges (e.g., base stations). However, due to heterogeneous content requests of users and a high-cost hit manner with direct hits, edge caching is still a most serious issue to be addressed. In this paper, we investigate the issue of recommendation-enabled edge caching in mobile two-tier (edge-cloud) computing networks. Particularly, we integrate recommender systems and edge caching to support both direct hits and soft hits and thus improve the resource utilization of edge servers. We model the factors affecting the user quality of experience as a comprehensive system cost and further formulate the problem as a multi-agent Markov decision process with the goal of minimizing the long-term average system cost. To address the formulated problem, we propose a decentralized recommendation-enabled edge caching framework that leverages a discrete multi-agent variant of soft actor-critic and federated learning. The proposed framework enables each edge server to learn its best policy locally and generate judicious decisions independently. Finally, trace-driven simulation results demonstrate that the proposed framework converges to a better caching policy and outperforms several existing algorithms on average system cost reduction.

Dense text retrieval has become a widely used paradigm for recalling existing language models , and efficient dense text retrieval is essential for obtaining sufficiently accurate candidate samples. However, the existing methods for dense text retrieval, which typically use dual-encoder architectures to match similar queries and documents, suffer from a lack of information interaction at low data volumes, resulting in suboptimal performance. Additionally, existing research relies on negative sampling techniques that do not take into account the negative effects of single negative sampling bias on the robustness of the model. These limitations hinder the development of more robust dense text retrieval models . In this paper, we propose a multi-view contrast learning architecture, named MvCR, to address these issues. MvCR improves the performance of dense text retrieval by performing contrast learning with multiple views while significantly increasing the model’s ability to discriminate between positive and negative samples. Additionally, we propose a data augmentation method that focuses on increasing the number of hard negative samples with accurate and semantic matching features. The experimental results have shown that MvCR can perform as well as strong baseline models even when the data volume is small. Furthermore, MvCR achieved better results on two popular retrieval benchmarks with comparable amounts of data. Specifically, MRR@10 was 39 . 1 ( + 0 . 9 % ) and Recall@50 was 87 . 8 ( + 1 . 4 % ) on the MS-MARCO dataset. And Recall@5 increased to 77 . 2 ( + 1 . 8 % ) and Recall@50 increased to 85 . 3 ( + 1 . 0 % ) on the Natural Questions dataset.

Feature selection (FS) is an essential technique widely applied in data mining. Recent studies have shown that evolutionary computing (EC) is very promising for FS due to its powerful search capability. However, most existing EC-based FS methods use a length-fixed encoding to represent feature subsets. This inflexible encoding turns ineffective when high-dimension data are handled, because it results in a huge search space, as well as a large amount of training time and memory overhead. In this article, we propose a length-adaptive genetic algorithm with Markov blanket (LAGAM), which adopts a length-variable individual encoding and enables individuals to evolve in their own search space. In LAGAM, features are rearranged decreasingly based on their relevance, and an adaptive length changing operator is introduced, which extends or shortens an individual to guide it to explore in a better search space. Local search based on Markov blanket (MB) is embedded to further improve individuals. Experiments are conducted on 12 high-dimensional datasets and results reveal that LAGAM performs better than existing methods. Specifically, it achieves a higher classification accuracy by using fewer features.

In decision-making systems, how to address uncertainty plays an important role for the improvement of system performance in uncertainty reasoning. Dempster—Shafer evidence (DSE) theory is an effective method to address uncertainty in decision-making problems by means of basic belief assignments (BBAs) and Dempster's combination rule. In the DSE theory, divergence measure between BBAs, which is beneficial for conflict information management in decision making, remains an open issue. In this paper, several generalized evidential divergences (EDs) are proposed and studied to measure the difference and discrepancy between BBAs in DSE theory, which have more universal applicability in decision theory. On this basis, a uniform BJS divergence-based decision-making algorithm is devised to improve the decision level. Furthermore, the extensions of weighted BJS to decision-making algorithms are discussed by considering not only subjective weights but also objective weights. Notably, this is the first work to propose the weighted BJS divergence in DSE theory providing a promising way to analyze decision-making problems from different perspectives. Finally, the proposed BJS-based decision-making algorithm is applied to pattern classification. The results validate that the proposed decision-making algorithm is beneficial for diverse real-world datasets and outperforms several well-known related works and demonstrates higher classification accuracy as well as robustness.

A large body of the literature on automated program repair develops approaches where patches are automatically generated to be validated against an oracle (e.g., a test suite). Because such an oracle can be imperfect, the generated patches, although validated by the oracle, may actually be incorrect. While the state-of-the-art explores research directions that require dynamic information or rely on manually-crafted heuristics, we study the benefit of learning code representations in order to learn deep features that may encode the properties of patch correctness. Our empirical work investigates different representation learning approaches for code changes to derive embeddings that are amenable to similarity computations of patch correctness identification, and assess the possibility of accurate classification of correct patch by combining learned embeddings with engineered features. Experimental results demonstrate the potential of learned embeddings to empower Leopard (a patch correctness predicting framework implemented in this work) with learning algorithms in reasoning about patch correctness: a machine learning predictor with BERT transformer-based learned embeddings associated with XGBoost achieves an AUC value of about 0.803 in the prediction of patch correctness on a new dataset of 2,147 labeled patches that we collected for the experiments. Our investigations show that deep learned embeddings can lead to complementary/better performance when comparing against the state-of-the-art, PATCH-SIM, which relies on dynamic information. By combining deep learned embeddings and engineered features, Panther (the upgraded version of Leopard implemented in this work) outperforms Leopard with higher scores in terms of AUC, +Recall and -Recall, and can accurately identify more (in)correct patches that cannot be predicted by the classifiers only with learned embeddings or engineered features. Finally, we use an explainable ML technique, SHAP, to empirically interpret how the learned embeddings and engineered features are contributed to the patch correctness prediction.

The conventional sequential recommendation tends to recommend an item to a sequence due to the concurrence of this item in other similar sequences. It is a typical collaborative filtering recommendation strategy that suffers from the data sparsity problem. Integrating the item-side information into the recommendation model can alleviate the data sparsity problem and avoid the privacy issue. However, roughly fusing item-side information in item embeddings to optimize for final recommendation accuracy might lose the objective associations among items. Thus, this paper proposes a self-supervised learning task on item-side information to generate the item representation space in advance of the recommendation task. The space can gather similar items and separate the different items. Then we reform a recently successful sequential recommendation method, self-attention network, by integrating an untrainable mechanism to fully take advantage of the pre-trained item representation space. The two procedures comprise a hybrid recommendation framework to achieve collaborative filtering and content-based recommendation strategies. Extensive experiments conducted on two benchmark datasets demonstrate the superiority of our proposed methods over other baseline methods.

Session-based recommendations (SBR) have attracted much attention because of their high commercial value. SBR aims to predict a user's next click based on the sequence of previous sessions. However, existing graph neural network (GNN)-based recommendation methods only focus on session graphs and ignore the time frame in the session which contains valuable temporal information for reducing the impact of user's unintentional clicks. Meanwhile, the expression ability of hidden factors in GNNs is neglected. In order to solve the above limitations, this paper propose an improving Graph Neural Network via Time sessions (TGNN) model. For the data preprocessing aspect, TGNN builds temporal sessions from the time frame in the dataset. Dwell time recurrent network explores complex temporal influence on items by learning time features. Multi-head attention is introduced to enhance the expression ability of hidden factors. Target-aware attention is utilized to activate different user interests for different target items adaptively, which can obtain interest expression changes of target items. Comparative experiments are conducted on two public datasets, and experimental results show that our method outperforms state-of-the-art methods. Ablation experiments demonstrate the effectiveness of the proposed model.

Abstract With the rapid development of information technology, the problem of “information overload” emerges when users choose cloud services. How to integrate multi‐source information to achieve accurate service recommendation is an urgent problem to be solved by current recommendation systems. This article proposes a cloud service recommendation method based on extended multi‐source information fusion. First, we propose a score prediction based on matrix decomposition and topic matrix, and we fully mine existing explicit data and feedback data, such as user ratings, social trust information, reviews, and user personalized preferences and so on. Second, in order to solve the problems of data sparseness and cold start of the system, we integrate the score, social trust information and review into a comprehensive model through collaborative filtering (CF), and propose a multi‐source information fusion recommendation method. The CF fusion method mainly combines two parts: social matrix decomposition and topic matrix decomposition. Finally, in order to further improve the accuracy and scalability, the implicit feature matrix is integrated into the user rating matrix, and the original CF enhancement based on scoring matrix decomposition is a matrix decomposition method that can learn implicit features. Experimental results show that compared with other recommendation algorithms, the cloud service recommendation method proposed in this article can improve the recommendation accuracy and allow users to choose satisfactory cloud services.

Cloud platforms have recently become a popular target execution environment for numerous workflow applications. Hence, effective workflow scheduling strategies in cloud environments are in high demand. However, existing scheduling algorithms are grounded on an idealized target platform model where virtual machines are fully connected, and all communications can be performed concurrently. A significant aspect neglected by them is endpoint communication contention when executing workflows, which has a large impact on workflow makespan. This article investigates how to incorporate contention awareness into cloud workflow scheduling and proposes a new practical scheduling model. Endpoint communication contention-aware List Scheduling Heuristic (ELSH) is designed to minimize workflow makespan. It uses a novel task ranking property and schedules data communications to communication resources besides scheduling tasks to computing resources. Moreover, a rescheduling technique is employed to improve the schedule. In experiments, ELSH is evaluated against the traditional contention-oblivious list scheduling algorithm, which is adapted to address contention during execution in practice. The experimental results reveal that ELSH performs more efficaciously compared with the adapted traditional ones.Note to Practitioners—This article aims to advance the state of the art for workflow scheduling in clouds by taking into account endpoint communication contention that can occur in practice but has largely been neglected in existing investigations. A scheduling method called Endpoint communication contention-aware List Scheduling Heuristic (ELSH) is then proposed to optimize workflow makespan. Experimental results based on synthetic and realistic workflows show that ELSH performs better than traditional scheduling algorithms that fail to consider endpoint communication contention, especially for the workflow with a large communication-to-computation-cost ratio. The proposed approach can be readily put into use and help cloud service providers to offer their customers high-quality services when executing the latter’s workflows.

Network function virtualization (NFV) is a promising paradigm where network functions are migrated from dedicated hardware appliances onto software middleboxes to promote service agility and reduce management costs. Benefiting from the NFV, the service function chain (SFC) has emerged as a popular network service form. It allows network traffic to pass through a series of virtual network functions in a specific order required by the business logic to arrange a complex service. However, SFC deployment is facing new challenges in seeking a trade-off between pursuing the objective of high long-term average revenue and making decisions in an online manner. In this paper, we propose DRL-D, a deep reinforcement learning-based approach for the online SFC deployment problem to satisfy different demands of SFC requests within resource constraints of the underlying infrastructure. DRL-D aims to maximize the long-term average revenue by combining the strengths of the graph convolutional network in learning a comprehensive representation of network state and the temporal-difference learning in generating deployment solutions for the SFC requests on the fly. Then a heuristic algorithm and a new prioritized experience replay technique are integrated to optimize the DRL framework and reduce the time complexity. Experimental results demonstrate the superiority of our DRL-D approach when compared with other benchmarks in terms of the long-term average revenue, acceptance ratio, and revenue-to-cost ratio. Performance evaluation shows that DRL-D possesses good robustness under different scales of physical networks and achieves excellent deployment performance within acceptable runtime.

Centrality measures are widely used to map each node to its importance in a network. For many practical applications, vital nodes bearing high centrality scores have superior positions over other nodes. To benefit from the positive impact of becoming a vital node, the problem of improving the centrality of the target node has attracted increasing attention. Many existing studies attack this problem by directly increasing the centrality score of the target node on the premise of knowing the network structure. However, these methods suffer from privacy issues due to their dependence on the network structure and may lose their effectiveness because other nodes can simultaneously increase the scores. Therefore, in this paper, we explore the following question: given a black-box network whose structure is unknown, is it possible to improve the centrality ranking (rather than the score) of a target node by implementing certain strategies? We provide an affirmative answer to this question. First, to avoid relying on the network structure for promotion, we propose strategies that freeze the original graph while appending nodes and edges just around the target node. Second, to guide strategies for effectively boosting centrality, we devise two principles that provide the target node with either the maximum gain or the minimum loss of centrality scores over other nodes. We prove that a strategy meeting the proposed principles is guaranteed to upgrade the target node's ranking. Extensive experiments were conducted to verify the effectiveness of the proposed strategies on black-box networks.

During the process of cloud manufacturing, service composition is an essential technology to ensure the smooth execution of the task. An important challenge for cloud manufacturing is how to implement effective and accurate service composition strategy, which are to execute the task effectively while also satisfy the requirements of user by maximizing the overall quality of service (QoS). However, the current cloud manufacturing service composition methods generally have the problem of poor solution quality in the large scale environment. To solve this problem, we propose a hybrid optimization algorithm, named hybrid-TC, which is a hybrid of the teaching-learning-based optimization algorithm (TLBO) and the crisscross optimization algorithm (CSO). First, we added Skyline query in the initialization phase to improve the convergence speed and the quality of the solution. Second, the horizontal crossover of CSO is used in the teaching phase of original TLBO, thereby some dimensions in the population that trapped in the local optimum have the chance to jump out of the iteration. Finally, the offspring individuals learned in the teaching-phase will continue to learn to improve the quality of the solution. Experiments show that our proposed method is effective for improving the solution quality of large-scale environmental service composition.

Abstract Many fault localization approaches recently utilize deep learning to learn an effective localization model showing a fresh perspective with promising results. However, localization models are generally learned from class imbalance datasets; that is, the number of failing test cases is much fewer than passing test cases. It may be highly susceptible to affect the accuracy of learned localization models. Thus, in this paper, we explore using data resampling to reduce the negative effect of the imbalanced class problem and improve the accuracy of learned models of deep‐learning‐based fault localization. Specifically, for deep‐learning‐based fault localization, its learning feature may require duplicate essential data to enhance the weak but beneficial experience incurred by the class imbalance datasets. We leverage the property of test cases (i.e., passing or failing) to identify failing test cases as the duplicate essential data and propose an iterative oversampling approach to resample failing test cases for producing a class balanced test suite. We apply the test case resampling to representative localization models using deep learning. Our empirical results on eight large‐sized programs with real faults and four large‐sized programs with seeded faults show that the test case resampling significantly improves fault localization effectiveness.

As ubiquitous and personalized services are growing boomingly, an increasingly large amount of traffic is generated over the network by massive mobile devices. As a result, content caching is gradually extending to network edges to provide low-latency services, improve quality of service, and reduce redundant data traffic. Compared to the conventional content delivery networks, caches in edge networks with smaller sizes usually have to accommodate more bursty requests. In this article, we propose an evolving learning-based content caching policy, named PA-Cache in edge networks. It adaptively learns time-varying content popularity and determines which contents should be replaced when the cache is full. Unlike conventional deep neural networks (DNNs), which learn a fine-tuned but possibly outdated or biased prediction model using the entire training dataset with high computational complexity, PA-Cache weighs a large set of content features and trains the multi-layer recurrent neural network from shallow to deeper when more requests arrive over time. We extensively evaluate the performance of our proposed PA-Cache on real-world traces from a large online video-on-demand service provider. The results show that PA-Cache outperforms existing popular caching algorithms and approximates the optimal algorithm with only a 3.8% performance gap when the cache percentage is 1.0%. PA-Cache also significantly reduces the computational cost compared to conventional DNN-based approaches.

Cloud computing is applied in various domains, among which social recommender systems are well-received because of their effectivity to provide suggestions for users. Social recommender systems perform well in alleviating cold start problem, but it suffers from shilling attack due to its natural openness. Shilling attack is an injection attack mainly acting on the training process of machine learning, which aims to advance or suppress the recommendation ranking of target items. Some researchers have studied the influence of shilling attacks in two perspectives simultaneously, which are user-item's rating and user-user's relation. However, they take more consideration into user-item's rating, and up to now, the construction of user-user's relation has not been explored in depth. To explore shilling attacks with complex relations, in this paper, we propose two novel attack models based on triangle relations in social networks. Furthermore, we explore the influence of these models on five social recommendation algorithms. The experimental results on three datasets show that the recommendation can be affected by the triangle relation attacks. The attack model combined with triangle relation has a better attack effect than the model only based on rating injection and the model combined with random relation. Besides, we compare the functions of triangle relations in friend recommendation and product recommendation.

With the tremendous growth of mobile data traffic generated by various devices such as smartphones, smartpads and wearable devices, it is necessary for mobile network operators to introduce revolutionary networking techniques, thereby satisfying service requirements of mobile users. Recently, mobile edge computing (MEC) has been regarded as an effective technique to alleviate the traffic burden on backhaul networks. In this paper, we investigate the issue of mobility-aware content caching and user association for ultra-dense MEC networks by minimizing the system costs. The problem is formulated as a complex pure integer nonlinear programming, which is NP-hard. To address the original long-term optimization problem, we decompose it into a series of one-slot subproblems, and then optimize the short-term subproblem in two phases (i.e., content caching and user association). We further propose a mobility-aware online caching algorithm to achieve content caching, and a lazy re-association algorithm to determine user association based on matching theory. Trace-driven evaluation results demonstrate that the proposed framework has superior performance on reducing system costs.

Service discovery aims to address the problem of service information explosion and find and locate services that meet the needs of service requesters. Because service description information is mostly composed of short text with noise and has the characteristics of semantic sparseness, it is difficult to extract the implied context information of service description. This paper proposes a service discovery framework based on Knowledge graphs and neural Similarity Network (KSN). Which uses knowledge graphs to connect entities to obtain rich external information to enhance the semantic information of service descriptions. convolutional neural network and similarity network is utilized to extract context information. Through extensive experiments on a real service data set show that KSN is superior to existing web service discovery methods in terms of multiple evaluation metrics.

Traffic flow prediction is an important foundation for intelligent transportation systems. The traffic data are generated from a traffic network and evolved dynamically. So spatio-temporal relation exploration plays a support role on traffic data analysis. Most researches focus on spatio-temporal information fusion through a convolution operation. To the best of our knowledge, this is the first work to suggest that it is necessary to distinguish the two aspects of spatial correlations and propose the two types of spatial graphs, named as geographic graph and semantic graph. Then two novel stereo convolutions with irregular acceptive fields are proposed. The geographic-semantic-temporal contexts are dynamically jointly captured through performing the proposed convolutions on graph sequences. We propose a geographic-semantic-temporal graph convolutional network (GST-GCN) model that combines our graph convolutions and GRU units hierarchically in a unified end-to-end network. The experiment results on the Caltrans Performance Measurement System (PeMS) dataset show that our proposed model significantly outperforms other popular spatio-temporal deep learning models and suggest the effectiveness to explore geographic-semantic-temporal dependencies on deep learning models for traffic flow prediction.

Recently, mobile edge computing has received widespread attention, which provides computing infrastructure via pushing cloud computing, network control, and storage to the network edges. To improve the resource utilization and Quality of Service, we investigate the issue of task offloading for End-EdgeCloud orchestrated computing in mobile networks. Particularly, we jointly optimize the server selection and resource allocation to minimize the weighted sum of the average cost. A cost minimization problem is formulated underjoint the constraints of cache resource and communication/computation resource of edge servers. The resultant problem is a Mixed-Integer Non-linear Programming, which is NP-hard. To tackle this problem, we decompose it into simpler subproblems for server selection and resource allocation, respectively. We propose a low-complexity hierarchical heuristic approach to achieve server selection, and a Cauchy-Schwards Inequality based closed-form approach to efficiently determine resource allocation. Finally, simulation results demonstrate the superior performance of the proposed scheme on reducing the weighted sum of the average cost in the network.

Cloud computing has nowadays become a dominant technology to reduce the computation cost by elastically providing resources to users on a pay-per-use basis. More and more scientific and business applications represented by workflows have been moved or are in active transition to cloud platforms. Therefore, efficient cloud workflow scheduling methods are in high demand. This paper investigates how to simultaneously optimize makespan and economical cost for workflow scheduling in clouds and proposes a multiobjective evolutionary list scheduling (MOELS) algorithm to address it. It embeds the classic list scheduling into a powerful multiobjective evolutionary algorithm (MOEA): a genome is represented by a scheduling sequence and a preference weight and is interpreted to a scheduling solution via a specifically designed list scheduling heuristic, and the genomes in the population are evolved through tailored genetic operators. The simulation experiments with the real-world data show that MOELS outperforms some state-of-the-art methods as it can always achieve a higher hypervolume (HV) value. Note to Practitioners-This paper describes a novel method called MOELS for minimizing both costs and makespan when deploying a workflow into a cloud datacenter. MOELS seamlessly combines a list scheduling heuristic and an evolutionary algorithm to have complementary advantages. It is compared with two state-of-the-art algorithms MOHEFT (multiobjective heterogeneous earliest finish time) and EMS-C (evolutionary multiobjective scheduling for cloud) in the simulation experiments. The results show that the average hypervolume value from MOELS is 3.42% higher than that of MOHEFT, and 2.27% higher than that of EMS-C. The runtime that MOELS requires rises moderately as a workflow size increases.

With the rapid growth of music industry data, it is difficult for people to find their favorite songs in the music library. Therefore, people urgently need an efficient music recommendation system to help them retrieve music. Traditional collaborative filtering algorithms are applied to the field of music recommendation. However, collaborative filtering does not handle data sparse problems very well when new items are introduced. To solve this problem, some people use the logistic regression method as a classifier to predict the user's music preferences to recommend songs. Logistic regression is a linear model that does not handle complex non-linear data features. In this paper, we propose a hybrid LX recommendation algorithm by integrating logistic regression and eXtreme Gradient Boosting(xgboost). A series of experiments are conducted on a real music dataset to evaluate the effectiveness of our proposed LX model. Our results show that the error and AUC of our LX model are better than other methods.

Recommender systems usually make personalized recommendation for users by analyzing interaction ratings between users and items. In plenty of application domains, some implicit feedback, content text, and other additional auxiliary information are widely used for improving the performance of recommendation. Memory-based collaborative filtering approaches that are widely used like matrix factorization (MF) predicts a personalized ranking for an individual user by leveraging latent factor models to handle common problems in recommender systems. However, most of previous MF methods adopt only explicit ratings to make personalized recommendation, ignoring the importance of implicit feedback on both users and items in-formation. Latent factor model can be easily extended with content text by mapping text information into factors, therefore we propose an approach by using neural networks to acquire the latent factors. Meanwhile, recurrent neural networks (RNNs) are applied to convert the textual data to an auxiliary factor feature to promote the representation of items. The experimental results prove that our model is effective on two benchmark datasets, outperforming some state-of-art approaches.

Cloud services are cloud computing resources and applications deployed on the Internet or cloud computing platform, and users can access the required cloud services at any time. However, users face the diversity and complexity of quality of service (QoS) when evaluating and selecting cloud services. Therefore, it is important to study and establish an effective and objective trust model to improve user satisfaction and interaction success rate. In this paper, a model based on combining weights and gray correlation analysis is proposed. Firstly, direct trust, recommendation trust, and reputation together form a comprehensive trust, resulting in a more accurate overall trust. Second, rough set theory and analytic hierarchy process (AHP)-based method are used for the direct trust. Meanwhile, the degree of similarity recommendation trust is calculated by a gray relational analysis method. In order to ensure the accuracy of direct trust, this paper proposes a dynamic trust update mechanism. Finally, the simulation experiment is carried out to verify that the cloud services trust evaluation model (CSTEM) is more robust than the other three methods. It protects against malicious entities; at the same time, it can increase user satisfaction and interaction success rate.

Traffic flow prediction is a crucial task for the intelligent traffic management and control. Various machine learning based methods have been applied in this field. Most of these methods encounter three fundamental issues: feature representation of traffic patterns, learning from single location or network, and data quality. In order to address these issues, in this work we present a deep architecture for traffic flow prediction that learns deep hierarchical feature representation with spatio-temporal relations over the traffic network. Furthermore, we design an ensemble learning strategy via random subspace learning to make the model be able to tolerate incomplete data. The experimental results corroborate the effectiveness of the proposed approach compared with the state of the art methods.

Traffic flow prediction is a fundamental component in intelligent transportation systems. However, many existing prediction models endure several shortages. Most of the methods are constructed as a shallow model, which is difficult to reveal the intrinsic spatio-temporal relations embedded in traffic raw data. Moreover, the separation of feature learning and predictor learning brings a sacrifice of model performance. Then the hand designed features are difficult to be tuned appropriately. Finally, few existing methods consider the incomplete data problem which is in fact very severe for practical application. In this work, we develop a deep learning model to predict traffic flows. The main contribution is development of an architecture that integrates random subspace learning and ensemble learning on deep convolutional neural networks. The proposed model takes the traffic flow data as an image, and considers both exploring spatio-temporal correlations in the unified architecture and the incomplete data problem. The experimental results, using traffic data originated from the California Freeway Performance Measurement System (PeMS), corroborate the effectiveness of the proposed approach compared with the state of the art.

The new cyberattack pattern of advanced persistent threat (APT) has posed a serious threat to modern society. This paper addresses the APT defense problem, that is, the problem of how to effectively defend against an APT campaign. Based on a novel APT attack-defense model, the effectiveness of an APT defense strategy is quantified. Thereby, the APT defense problem is modeled as an optimal control problem, in which an optimal control stands for a most effective APT defense strategy. The existence of an optimal control is proved, and an optimality system is derived. Consequently, an optimal control can be figured out by solving the optimality system. Some examples of the optimal control are given. Finally, the influence of some factors on the effectiveness of an optimal control is examined through computer experiments. These findings help organizations to work out policies of defending against APTs.

Point of Interest (POI) recommendation aims to recommend places which users have not visited before. In this paper, we proposed a POI recommendation method using user similarity, which assumes that people may be interested in the places that others have been to but they have not visited before. In this paper, one day can be divided into 24 time-slots, thus each hour can be defined as a time slot. The novelty of the method we proposed lies in user features which adopted by the summation of user’s check-in times in each time slot. The check-in times for each user can be collected and then form a vector, and we can take advantage of the summation of these check-in times in each time slot to find out user characteristics. The similarity between any two users can be calculated by cosine similarity method. Then a sorted list of scores which includes all unvisited locations of each user can be obtained according to user similarity. Through these steps, a POI recommendation list can be produced according to the score from high to low. The experimental result indicates that the method we proposed in this paper is effective.

Prediction of Quality of Service (QoS) values plays an important role in service selection, discovery, and recommendation. Previous works show that the QoS values would be influenced by the location information. However, these researches do not consider the fact that some users may provide untrustworthy QoS values even though they are in the same location region. QoS values from these unreliable users could significantly affect the QoS prediction accuracy. To address this issue, this paper proposes an alternative and efficient approach to predict the missing QoS values, referred as the Location and Reputation aware Matrix Factorization based Location Information (LRMF). LRMF combines both the user's reputation and location information to achieve more accurate prediction results. Experiments are conducted on a real-world Web service QoS dataset, and results show that the proposed method outperforms many other existing QoS prediction methods.

Traditional recommender systems assume that all the users are independent, and they usually face the cold start and data sparse problems. To alleviate these problems, social recommender systems use social relations as an additional input to improve recommendation accuracy. Social recommendation follows the intuition that people with social relationships share some kinds of preference towards items. Current social recommendation methods commonly apply the Matrix Factorization (MF) model to incorporate social information into the recommendation process. As an alternative model to MF, we propose a novel social recommendation approach based on Euclidean Embedding (SREE) in this paper. The idea is to embed users and items in a unified Euclidean space, where users are close to both their desired items and social friends. Experimental results conducted on two real-world data sets illustrate that our proposed approach outperforms the state-of-the-art methods in terms of recommendation accuracy.

This paper proposes an operational planning framework for large-scale thermostatically controlled load (TCL) dispatch. The proposed framework consists of a day-ahead scheduling stage and a real-time operation stage. A thermal comfort model is employed to estimate the occupants' thermal comfort degree. A self-adaptive TCL grouping method is proposed to group the TCLs based on the similarity of the TCL model parameters. Then, a hierarchical day-ahead scheduling model is proposed to make the optimal dispatch plan for the TCL aggregators based on the day-ahead forecasted information. In the real-time operation stage, a predictive control model is proposed for the TCL aggregators to make the real-time TCL dispatch decision based on the updated real-time information. The simulation results prove the efficiency of the proposed framework.

Quality of service (QoS) has been playing an increasingly important role in today's Web service environment. Many techniques have been proposed to recommend personalized Web services to customers. However, existing methods only utilize the QoS information at the client-side and neglect the contextual characteristics of the service. Based on the fact that the quality of Web service is affected by its context feature, this paper proposes a new QoS-aware Web service recommendation system, which considers the contextual feature similarities of different services. The proposed system first extracts the contextual properties from WSDL files to cluster Web services based on their feature similarities, and then utilizes an improved matrix factorization method to recommend services to users. The proposed framework is validated on a real-world dataset consisting of over 1.5 million Web service invocation records from 5825 Web services and 339 users. The experimental results prove the efficiency and accuracy of the proposed method.

Nowadays it is becoming more and more attractive to execute workflow applications in the cloud because it enables workflow applications to use computing resources on demand. Meanwhile, it also challenges traditional workflow scheduling algorithms that only concentrate on optimizing the execution time. This paper investigates how to minimize execution cost of a workflow in clouds under a deadline constraint and proposes a metaheuristic algorithm L-ACO as well as a simple heuristic ProLiS. ProLiS distributes the deadline to each task, proportionally to a novel definition of probabilistic upward rank, and follows a two-step list scheduling methodology: rank tasks and sequentially allocates each task a service which meets the sub-deadline and minimizes the cost. L-ACO employs ant colony optimization to carry out deadline-constrained cost optimization: the ant constructs an ordered task list according to the pheromone trail and probabilistic upward rank, and uses the same deadline distribution and service selection methods as ProLiS to build solutions. Moreover, the deadline is relaxed to guide the search of L-ACO towards constrained optimization. Experimental results show that compared with traditional algorithms, the performance of ProLiS is very competitive and L-ACO performs the best in terms of execution costs and success ratios of meeting deadlines.

With the development of information technology, more and more web services have emerged, thereby making it difficult for customers to find their favorite services quickly and accurately. To overcome this difficulty, recently the collaborative filtering (CF) technique has been widely employed for personalized service recommendation, meanwhile improving the profits of service providers. Although the CF-based web service recommender systems have shown their potential, they appear to be vulnerable to shilling attack problems. Therefore, in this paper we analyze a general form of web service shilling attacks and four kinds of classical attack models, e.g., average attack, bandwagon attack, random attack, and segment attack are thoroughly investigated. Furthermore, we also study the impact of distribution-aware Pareto attack models. To demonstrate how shilling attacks alter the recommendation results, this paper analyzes 1) the variation of Quality-of-Service (QoS) prediction values of target services, 2) the QoS value prediction shifts of services with short response time which are more likely recommended, and 3) the comparison of prediction shift caused by classical attack models and Pareto attack models. The experimental results on WS-DREAM dataset revealed several interesting findings about the predictions of QoS values of target service correlated to different attack models. It is expected that this work can provide some insight for future vulnerability analysis of CF-based web service recommender systems.

While massive open online courses (MOOCs) have gained increasing popularity in recent years, dropout prediction has been an important task to solve due to the high rates of dropout students found in MOOCs. Current methods normally apply supervised learning methods to dropout prediction, using general features extracted from behavior records without the concern of behavior types. However, student learning behavior is diverse and there are no sufficient labeled data to train a model because it is a time-costing task to label enormous data in practice. To solve these problems, in this work, we proposed a novel multi-view semi-supervised learning model based on behavior features for the dropout prediction task. Specifically, we derived features from each type of learning behavior to form multi-view behavior features. In addition, based on these features, we proposed a new multi-view semi-supervised learning method to make use of a large number of unlabeled data to assist insufficient labeled data for improving prediction performance. We conducted experiments on KDD Cup 2015 dataset, and the results show that our proposed method achieves better prediction of student dropouts as compared to state-of-the-art approaches.

Software developers often find answers to their programming issues on the Internet. Q&A (Question & Answer) websites has been becoming more and more popular. Among the available technical Q&A sites, the most prevalent one is the Stack Overflow, it has been becoming one of the invaluable knowledge repositories. The development trends of language and mainstream operation systems are discussed by using the SVD (Singular Value Decomposition) and K-means algorithm in this paper. Some key findings include: Traditional programming languages such as C#, C++, C develop slowly and the light script languages such as Php, JavaScript and Python develop rapidly, traditional operation systems such as Windows and Linux develop slowly and the mobile devices operation systems such as IOS and Android develop rapidly. Through studying and analyzing the development of mainstream technology, people can grasp the dynamic situation of the software field, which has important and far-reaching significance to guide the work of software engineering.

Personalized recommendation system (PRS) is an effective tool to automatically extract meaningful information from the big data of the users. Collaborative filtering is one of the most widely used personalized recommendation techniques to recommend the personalized products for users. In this paper, a PRS model based on the support vector machine (SVM) is proposed. The proposed model not only considers the items’ content information, but also the users’ demographic and behavior information to fully capture the users’ interests and preferences. Meanwhile, an improved particle swarm optimization (PSO) algorithm is applied to optimize the SVM’s learning parameters. The efficiency of the proposed method is verified by multiple benchmark datasets.

The open nature of recommender systems makes them vulnerable to shilling attacks. Biased ratings are introduced in order to affect recommendations, have been shown to cause great harm to collaborative filtering algorithms. Most of previous research focuses on the differences between genuine profiles and attack profiles, ignoring the group characteristics in an attack. There exists class unbalance problems in SVM based detecting methods, that is, the detecting performance is not good when the amount of samples of attack profiles in training set is small. In this paper, we study the use of SVM based method and group characteristics in attack profiles to detect attack profiles. Based on this, a two phase detecting method SVM-TIA is proposed. In the first phase, Borderline-SMOTE method is used to alleviate the class unbalance problem in classification; a rough detecting result is obtained in this phase; the second phase is a fine-tuning phase whereby the target items in the potential attack profiles set are analysed. We conduct experiments on the MovieLens 100K Dataset and compare the performance of SVM-TIA with other shilling detecting methods to demonstrate the effectiveness of the proposed approach.

Recommender systems are highly vulnerable to attacks. Attackers who introduce biased ratings in order to affect recommendations, have been shown to be effective against collaborative filtering algorithms. In this paper, we study the use of statistical metrics to detect rating patterns of attackers. Two metrics, Rating Deviation from Mean Agreement (RDMA) and Degree of Similarity with Top Neighbors (DegSim), are used for analysing rating patterns between malicious profiles and genuine profiles in shilling attacks. Building upon this, we propose and evaluate an algorithm for detecting shilling attacks in recommender systems using a statistical approach. We look at two attack models: random attack and average attack. The experimental results show that our detection technique based on target item analysis is an effective approach in detecting shilling attacks for both the random and average attack model.

Recommender systems using Collaborative Filtering techniques are capable of make personalized predictions. However, these systems are highly vulnerable to profile injection attacks. Group attacks are attacks that target a group of items instead of one, and there are common attributes among these items. Such profiles will have a good probability of being similar to a large number of user profiles, making them hard to detect. We propose a novel technique for identifying group attack profiles which uses an improved metric based on Degree of Similarity with Top Neighbors (DegSim) and Rating Deviation from Mean Agreement (RDMA). We also extend our work with a detailed analysis of target item rating patterns. Experiments show that the combined methods can improve detection rates in user-based recommender systems.

Current existing representative works to semi-supervised incremental learning prefer to select unlabeled instances predicted with high confidence for model retraining. However, this strategy may degrade the classification performance rather than improve it, because relying on high confidence for data selection can lead to an erroneous estimate to the true distribution, especially when the confidence annotator is highly correlated with the confidence annotator. In this paper, a new semi-supervised incremental learning algorithm was proposed, which selected the high confidence unlabeled instances with symmetrical distribution from unlabeled data, it can reduce the bias in the estimation in some degree. In detail, expectation maximization algorithm was used to estimate the confidence of each instance, and Gaussian function was used to calculate the data distribution, then the selected unlabeled data was used for retraining model with classifier algorithm. The experimental results based on a large number of UCI data sets show that our algorithm can effectively exploit unlabeled data to enhance the learning performance.

Self-organizing feature maps (SOFM) can learn both the distribution and topology of the input vectors they are trained on. According to this characteristic, we construct neural networks with a family of self-organizing feature maps to cluster the input data space. The proposed algorithm in this paper defines a novel similarity measure, topological similarity, and employs some new concepts, such as SOFM family, UsageFactor. The clustering algorithm handles the clusters with arbitrary shapes and avoid the limitations of the conventional clustering algorithms. We conclude our paper by several experiments with synthetic and standard data set of different characteristics, which show good performance of the proposed algorithm.