Recommender systems have been widely deployed across various domains such as e-commerce and social media, and intelligently suggest items like products and potential friends to users based on their preferences and interaction history, which are often privacy-sensitive. Recent studies have revealed that recommender systems are prone to membership inference attacks (MIAs), where an attacker aims to infer whether or not a user’s data has been used for training a target recommender system. However, existing MIAs fail to exploit the unique characteristic of recommender systems, and therefore are only applicable to mixed recommender systems consisting of two recommendation algorithms. This leaves a gap in investigating MIAs against hybrid-based recommender systems where the same algorithm utilizing user-item historical interactions and attributes of users and items serves and produces personalised recommendations. To investigate how the personalisation in hybrid-based recommender systems influences MIA, we propose a novel metric-based MIA. Specifically, we leverage the characteristic of personalisation to obtain reference recommendation for any target users. Then, a relative membership metric is proposed to exploit a target user’s historical interactions, target recommendation, and reference recommendation to infer the membership of the target user’s data. Finally, we theoretically and empirically demonstrate the efficacy of the proposed metric-based MIA on hybrid-based recommender systems.

Sequential recommendation has emerged as a fundamental task in various domains, aiming to predict a user's next interaction based on historical behavior. Recent advances in deep sequence models, particularly Transformer-based architectures and the more recent Mamba, have substantially pushed the boundaries of sequential modeling performance. However, existing methods still face two critical challenges. First, many current approaches overlook the hierarchical structures and high-order dependencies among items, typically restricting representation learning to conventional Euclidean spaces, which limits their capacity to capture complex relational information. Second, although Mamba excels at long-range dependency modeling, its reliance on static Feed-Forward Networks (FFNs) hinders its ability to dynamically adapt to evolving user preferences across diverse contexts. To address these limitations, we propose a Hyperbolic-Enhanced Mixture-of-Experts Mamba recommender (HM2Rec) for sequential recommendation. HM2Rec first encodes user-item relationships through hyperbolic graph convolution to exploit hierarchical structure more effectively. Then, a Variational Graph Auto-Encoder (VGAE) is employed to reconstruct node embeddings, improving structural robustness. To further enhance sequential modeling, we integrate Rotary Positional Encoding (RoPE) into Mamba to better capture relative position dependencies, and replace the FFN with Mixture-of-Expert (MOE) module, enabling dynamic and personalized expert selection for each token. Our extensive experiments on four widely-used public datasets demonstrate that HM2Rec outperforms several advanced baseline models.

Large Language Models (LLMs) have revolutionized intelligent interactions, enabling mobile applications such as personal assistants on edge devices for local execution. Speculative decoding (SD) has emerged as a promising paradigm to accelerate LLM inference without compromising generation quality, employing a draft-then-verify manner. However, due to the constrained computing and memory resources on edge devices, existing SD works heavily rely on an auxiliary draft model that incurs additional memory burden and hinders the adaptability, as well as static token trees that yield suboptimal inference performance. To this end, we propose DIAA, a Decoding-efficient Inference Acceleration Approach for on-device LLMs. DIAA achieves plug-and-play and model-agnostic inference speedup with memory and computation efficiency for edge devices. Specifically, a pair of lightweight look-up tables (LUTs) is constructed by Top-K token sampling to cache historical tokens and probabilities for rapid candidate drafting. DIAA integrates a dynamic token tree with prior LUTs enabling paralleled verification, updated during decoding process, to adapt the online context. A computation overlap is then employed to pipeline the update operations of token tree, LUTs, and KV cache to improve the computational efficiency. Finally, through extensive experiments implemented on edge platform NVIDIA Jetson, DIAA outperforms existing baselines in generation speed and inference wall-clock time, while incurring minimal memory overhead.

With rapid urbanization in the modern era, traffic signals from various sensors have been playing a significant role in monitoring the states of cities, which provides a strong foundation in ensuring safe travel, reducing traffic congestion and optimizing urban mobility. Most existing methods for traffic time series modeling often rely on the original data modality, i.e., numerical direct readings from the sensors in cities. However, this unimodal approach overlooks the semantic information existing in multimodal heterogeneous urban data in different perspectives, which hinders a comprehensive understanding of traffic signals and limits the accurate prediction of complex traffic dynamics. To address this problem, we propose a novel Multimodal framework, MTP, for urban Traffic Profiling, which learns multimodal features through numeric, visual, and textual perspectives in the frequency domain. The three branches drive a multimodal perspective of traffic signal learning for augmentation, while the frequency learning strategies delicately refine the information for extraction. Specifically, we first conduct the visual augmentation for the traffic time series, which transforms the original modality into periodicity images and frequency images for visual learning. Also, we augment descriptive texts for the traffic time series based on the specific topic, background information and item description for textual learning. To complement the numeric information, we utilize frequency multilayer perceptrons for learning on the original modality. We design a hierarchical contrastive learning on the three branches to fuse the three modalities. Finally, extensive experiments on six real-world datasets demonstrate superior performance compared with the state-of-the-art approaches.

Recent advances in large language models (LLMs) have enabled promising progress in diagnosis prediction from electronic health records (EHRs). However, existing LLM-based approaches tend to overfit to historically observed diagnoses, often overlooking novel yet clinically important conditions that are critical for early intervention. To address this, we propose EviCare, an in-context reasoning framework that integrates deep model guidance into LLM-based diagnosis prediction. Rather than prompting LLMs directly with raw EHR inputs, EviCare performs (1) deep model inference for candidate selection, (2) evidential prioritization for set-based EHRs, and (3) relational evidence construction for novel diagnosis prediction. These signals are then composed into an adaptive in-context prompt to guide LLM reasoning in an accurate and interpretable manner. Extensive experiments on two real-world EHR benchmarks (MIMIC-III and MIMIC-IV) demonstrate that EviCare achieves significant performance gains, which consistently outperforms both LLM-only and deep model-only baselines by an average of 20.65% across precision and accuracy metrics. The improvements are particularly notable in challenging novel diagnosis prediction, yielding average improvements of 30.97%.

Full fine-tuning of large vision-language models (VLMs) for cross-modal retrieval is computationally expensive and prone to overfitting. Adapter-based parameter-efficient transfer learning offers a practical alternative, but existing designs often suffer from structural redundancy and the loss of fine-grained visual details critical for accurate matching. These limitations are particularly detrimental for retrieval, which demands fine-grained perceptual discrimination beyond semantic alignment. To address these challenges, we propose B-HFA, a parameter-efficient framework for vision-language retrieval. B-HFA introduces a Block-wise Shared Adapter (B-Adapter) to reduce redundancy through structured parameter sharing, and a Hierarchical Feature Aggregation (HFA) module that dynamically integrates intermediate visual features guided by textual semantics. This design enables efficient adaptation while preserving visual fidelity essential for retrieval. Extensive experiments on multiple retrieval benchmarks demonstrate that B-HFA achieves competitive performance with only 0.13% of trainable parameters. Moreover, its competitive results on visual question answering suggest the generality of the proposed framework beyond retrieval tasks.

Sequential recommendation has achieved remarkable success across various application domains due to its ability to capture dynamic user preferences. Therefore, its effectiveness significantly diminishes in user cold-start scenarios, where new users have limited or no interaction history. Current solutions typically design specialized model architectures to infer cold-start user preferences from auxiliary information, such as user attributes or social networks. However, such methods overlook compatibility with advanced sequential recommender models, preventing the efficient extraction of sequential features. To address this limitation, we propose CDMRec, a Causal Diffusion Preference Model for user cold-start sequential recommendation. CDMRec generates diffusion-based preference representations for cold-start users, which can be directly utilized by existing sequential recommendation models. The framework first constructs a Preference-Dominant Sequence (PDS) by isolating interactions most indicative of user interests, mitigating noise from irrelevant behaviors. Then, leveraging causal inference, CDMRec identifies key causal variables from PDS to condition the diffusion process, enabling the generation of personalized behavioral preferences. Extensive experiments on three public datasets demonstrate that CDMRec can be seamlessly integrated into mainstream sequential recommender models, yielding substantial performance gains in cold-start settings.

Contrastive learning has emerged as a promising paradigm by inherently generating self-supervised signals and uncovering latent patterns from interaction data to enhance recommendation performance. However, most current graph contrastive learning-based recommendation methods rely on random augmentation strategies,which may disrupt graph structural information and compromise model robustness. In addition, long-tail items suffer from insufficient exposure, making it difficult to learn high-quality feature rep- resentations, ultimately degrading recommendation effectiveness.To overcome these limitations, this paper presents DDGCL, a dual diffusion-based graph contrastive learning method. A contrastive view optimization module is designed, which employs singular value decomposition to perform low-rank approximation on the interaction graph, efficiently extracting global structural features while accelerating the diffusion process. The diffusion model then performs noise addition and denoising on this basis to generate contrastive views that preserve graph structural information. In addition, a method for embedding augmentation designed for long-tail items is proposed. This module utilizes a conditional diffusion model, where global graph information serves as conditional con- straints to guide the denoising process of long-tail items, thereby improving their representation learning. A comprehensive evaluation on multiple public benchmark datasets demonstrates that DDGCL significantly outperforms various baseline models, validating the effectiveness of the proposed approach.

Sequential recommendation aims to predict the next user interaction by modeling historical behavior sequences. Recently diffusion models (DMs) have emerged as a promising generative approach due to their robustness and capacity for uncertainty modeling. However, existing diffusion-based recommendation approaches still encounter two major challenges: sample drift during the noise injection process, which compromises the stability of generation; and limited adaptability to noisy data, which hampers the effectiveness of personalized recommendations. To address these issues, we propose GSDiffRec, a novel generative sequential recommendation approach that integrates two core modules: (i) Semantic-Targeted Guidance Module (STG) built upon an enhanced Transformer backbone equipped with shaped attention and convolutional components to improve representational efficiency and modeling capacity; and (ii) Geodesic Diffusion Module (GDM) enforcing manifold constraints through geodesic random walks, thereby preserving geometric consistency and enhancing denoising stability throughout the diffusion process. Extensive experiments on two public Amazon datasets demonstrate that GSDiffRec significantly outperforms a wide range of competitive baselines. Further ablation studies validate the complementary contributions and effectiveness of the GDM and STG modules.

Abnormal user detection has been a critical and widely studied research problem in social networks since these users can create significant risks to platform security and privacy leakage. Currently, graph-based models are commonly used for exploring the structured social network data and temporally dynamic user interactions, leading to significant advances in dynamic heterogeneous graph-based abnormal user detection. However, most existing approaches are correlation-driven and lack the ability to separate stable patterns from transient noise. Furthermore, these methods are highly dependent on inherent labels and fail to detect common few-shot anomalies in social networks. To address these issues, we propose CIFAD, a Causal-Invariant Few-shot Anomaly Detection method that improves few-shot anomaly detection with an active annotation strategy. Specifically, CIFAD first integrates a sparse lagged attention encoder to model multi-relational temporal interactions. Furthermore, it introduces causal-invariant subspace decomposition to disentangle stable causal signals from dynamic environmental noise and improve generalization. Finally, it designs an active annotation strategy based on influence functions and coverage optimization to maximize the utility of limited labels in a closed-loop process. Extensive experiments on multiple real-world social network datasets demonstrate that our method achieves higher accuracy than state-of-the-art methods, validating its robustness in abnormal user detection for social networks.

With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.

Multi-modal recommendation has become essential with the rapid expansion of online platforms such as e-commerce and video-sharing applications. In this work, we focus on the Multi-Modal New Item Recommendation (MMNIR) problem, where items with multi-modal content but newly introduced items lack interaction history. The MMNIR problem is particularly challenging in two aspects: (1) a large number of new items are created rapidly over time without any interaction data, (2) not all existing interactions are equally useful, and it is non-trivial to identify informative behaviors from users with similar preferences. However, previous methods fail to identify users with similar preferences and to capture informative behaviors from historical data. Furthermore, conventional models primarily rely on simple co-occurring signals, leading to spurious neighbors and neglecting the informative behaviors of truly similar users with consistent preferences. To fill this gap, we propose Joint Similar User Exploration and Informative Behavior Guidance (SuperG) for solving the MMNIR problem. SuperG first proposes a similar user exploration module to identify users with similar preferences to the target user. Then it incorporates an informative behavior mining module to retrieve informative behaviors from both the target user and similar users' histories to support new item recommendation. Finally, SuperG proposes a behavior-guided hybrid recommendation module to incorporate the retrieved behavioral signals to guide the recommendation of new items. Our empirical study on three real datasets demonstrates that SuperG outperforms the state-of-the-art models under the MMNIR setting.

Web-scale platforms and online services rely on log-based anomaly detection to safeguard availability, latency SLOs, and user experience. In real-world web interactions, system logs often exhibit irregular temporal intervals, bursty densities, and heterogeneous semantics, which pose significant challenges for log anomaly detection. Existing methods such as LSTM and Transformer assume a fixed input window, which conflicts with the inherently irregular nature of system logs. Moreover, most prior works build a single-view representation, overlooking the multi-relational nature of logs. To overcome these challenges, we propose DyLogNet, a dynamic multi-relational graph framework for log anomaly detection. Specifically, this framework constructs a density-aware dynamic graph with variable-length windows, and represents logs from three relational perspectives: temporal co-occurrence, semantic similarity, and anomaly tendency. Next, we design a cross-layer attention mechanism that integrates heterogeneous structures to highlight the most relevant relations and enhance event representations. Furthermore, a cross-snapshot memory injection module updates global memory through a recurrent unit and injects it into current graph representations via an affine transformation, enabling temporal continuity. Experiments on three public log datasets demonstrate that DyLogNet outperforms state-of-the-art methods, especially in few-shot scenarios.

Hash-based collaborative filtering (Hash-CF) approaches recently employ efficient Hamming distance of learned binary representations to accelerate recommendations. Benefiting from its probabilistic nature, Variational Autoencoder (VAE) enables robust Hash-CF with stronger generalization ability. However, VAE-based Hash-CF still faces two challenging problems: 1) Traditional VAE urges the latent variables of different users (or items) to fit a unified and monotonous prior distribution, and lacks considerations for distinctive characteristics of users (or items). The obtained representations of users and items with slight individual differentiation may further weaken the performance of Hash-CF for subsequent personalized recommendations. 2) Hash-CF under the VAE framework requires discrete optimization on latent Bernoulli distributions, which are discrete and NP-hard to optimize. In this paper, we propose a Dual Discrete Collaborative Filtering (DDCF) approach, including a cluster-enhanced representation generation module and a CNF-enabled discrete optimization module. The former module mainly develops cluster-aware latent space to generate discriminative representations for users or items with significantly different characteristics. The latter module employs Continuous Normalizing Flow (CNF) to achieve discrete optimization on latent Bernoulli distributions steadily and effectively. Extensive experiments conducted on multiple real-world datasets demonstrate the superiority of our DDCF compared with the state-of-art methods in terms of effectiveness and efficiency.

Trust relationships play a crucial role in various domains, such as social spam detection, retweet behavior analytics, and recommendation systems. Trust is often implicit and difficult to observe directly in the real world, as it is driven by people's underlying intentions and motivations. Therefore, when evaluating trust, it is critical to analyze not only user behavior data but also the intentions behind these behaviors that lead to trust. Existing trust evaluation methods often neglect the underlying reasons behind connections, such as shared hobbies or belonging to the same community. Therefore, these methods cannot differentiate the genuine intentions that lead to trust, resulting in an inaccurate evaluation of hidden trust relationships. To address this issue, we propose a novel Intent-based model for Trust Evaluation (INTRUST). This model can distinguish the intent behind high-order information in social communities using hypergraphs. Initially, we used hyperedges to represent high-order correlations between user-to-item and user-to-user interactions. Then, we construct K intent prototypes, which serve as foundational elements to build trust. Furthermore, we distinguish K-independent intent subgraphs from these high order correlations. To enhance the generalization and robustness of the model, we employ self-supervised learning and construct contrastive views at the node-level, hyperedge-level, and node hyperedge-level. Extensive experiments on real-world datasets demonstrate that our model outperforms state-of-the-art approaches in terms of trust evaluation accuracy and efficiency.

Efficient collaboration among Unmanned Aerial Vehicles (UAVs) has significant performance improvement for UAV-based applications. Task offloading is the typical collaboration form for UAV system. However, it still be a challenging problem for UAV system due to task dependencies and the UAV mobility which makes the traditional offloading approaches inefficiency. In this paper, we model the offloading problem as the Sequential Task Offloading Problem (sTOP), which takes the task spatiotemporal dependencies into account. We propose a Graph-based Spatiotemporal Reinforcement Learning (GSTRL) framework, where the environment is modeled as a heterogeneous graph to capture the diverse relationships among system entities. A spatiotemporal state extraction module is designed, which integrates a Heterogeneous Graph Neural Network (HGNN) for spatial dependency modeling and a Long Short-Term Memory (LSTM) network for temporal dynamics. Based on the extracted representations, a masked Proximal Policy Optimization (mPPO) algorithm is proposed to make valid and efficient offloading decisions under multiple system constraints. Extensive experiments using real UAV trajectory and building distribution datasets validate that the proposed method improves the average reward by approximately 25% over state-of-the-art DRL-based and heuristic baselines, by increasing task success rate and operational effectiveness ratio (OER) to 30–50%, while reducing execution time by up to 40% in complex multi-UAV systems.

API recommendation is a crucial task in code intelligence, aiming to suggest suitable APIs for programming queries. Recent efforts have integrated Large Language Models (LLMs) into this task. However, these methods overlook the compatibility between recommended APIs and fail to fully utilize the factual knowledge of APIs. Moreover, these prompting-only methods are limited by the insufficient domain-specific knowledge of LLMs. In this article, we propose a novel fine-tuning method, KDRAR, designed to leverage knowledge-driven reasoning with LLMs for compatible and interpretable API recommendation. To fully utilize the factual knowledge, we introduce a dual matching strategy that leverages both function descriptions and keyword matching to retrieve candidate APIs. To handle compatibility, we translate compatibility information into descriptive knowledge, which is integrated into the recommendation process. Furthermore, we adopt a distilled fine-tuning strategy: a student LLM is trained via distillation from a teacher LLM to perform step-by-step reasoning for enhanced recommendation and explanation. By considering both function matching and compatibility information, the knowledge-driven reasoning not only improves API recommendation accuracy but also provides reasonable explanations for the recommendations. Experimental results show that our method significantly outperforms baseline methods on API recommendation tasks across multiple API domains.

This is an erratum for the article “Knowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation” published in ACM Trans. Inf. Syst. 44, 1, Article 27 (December 2025), 30 pages.

Traditional methods for ensuring security and privacy face challenges in safeguarding multimedia data within the IoT-edge continuum, as their significant computational demands render them unsuitable for IoT devices with limited resources. Next, we find that the federated learning techique can naturally adapt to edge frameworks and provide effective data security and privacy protection. In this article, we propose FLiForest, an innovative anomaly detection approach that integrates federated learning with the isolation forest algorithm, tailored for the IoT-edge continuum. Specifically, our method designs a three-stage process, including data collection and sampling, model training, and data testing, to joint-train an isolation forest among clients and edge servers. FLiForest facilitates decentralized model training across IoT devices, enhancing data privacy and reducing computational burden, without necessitating the exchange of multimedia data. Through extensive experiments on a variety of multimedia datasets, the efficacy of our method is benchmarked against the state-of-the-art anomaly detection methods, showcasing its superior detection accuracy and robustness in ensuring data privacy and security.

Federated learning (FL) enables edge devices to collaboratively train a global model without sharing raw data. In the edge environment, resource constraints hinder efficient training and aggregation of FL. Although prior studies have established model pruning as a practical strategy to reduce resource demand, the parameter symmetry problem (i.e., permutation-equivalent parameter orderings in neural networks) remains underexplored. Without addressing this symmetry, pruning on heterogeneous clients results in aggregation mismatches and degraded accuracy. In this paper, we propose Attention-guided One-shot Pruning for Federated Learning (FedAOP) to address these challenges. First, we design an attention module that integrates spatial and channel attention to highlight critical spatial responses and evaluate channel importance. Then, leveraging these importance scores, we propose an attentive pruning algorithm to generate client-specific models, thereby reducing resource consumption. Furthermore, we introduce an aggregation algorithm with attention matching, thereby mitigating the adverse effects of parameter symmetry under heterogeneous pruning. We implementFedAOPon a benchmark FL platform. The experimental results on benchmark datasets demonstrate thatFedAOPconsistently outperforms state-of-the-art baselines by up to 11.3% in accuracy while reducing the average model footprint by 32%.

Graph Neural Networks (GNNs) are widely applied on graph-level tasks, such as node classification, link prediction and graph generation. Existing GNNs mostly adopt a message-passing mechanism to aggregate node information with their neighbors, which often makes node information similar after rounds of aggregations and leads to oversmoothing. Although recent works have made improvements by combining different message aggregation methods or introducing semantic encodings as priors, these message-passing based GNNs still fail to combat oversmoothing after multiple iterations of node aggregation. Besides, the feature extraction ability of these methods is restricted because of the graph sparsity that hinders the aggregation of node information. To deal with the above two issues, we propose Neighborhood-based and Label-enhanced Graph Transformer (NLGT), a novel and effective framework for graph learning. Specifically, we present a label-enhanced feature fusion mechanism that integrate the shallow node features and label embeddings as enhanced features. Moreover, we design a neighborhood-based mask attention mechanism to alleviate the negative effects caused by the sparsity of the graph. In the predicting stage, we aggregate the prediction results from multiple sampled sub-graphs and apply voting mechanisms to enhance the accuracy and robustness of our framework. Finally, extensive experiments are conducted on four open benchmark datasets, which demonstrate the effectiveness and robustness of our proposed framework compared with existing state-of-the-art methods.

Graph Contrastive Learning (GCL), as a primary paradigm of graph self-supervised learning, spurs a fruitful line of research in tackling the data sparsity issue by maximizing the consistency of user/item embeddings between different augmented views with random perturbations. However, diversity, as a crucial metric for recommendation performance and user satisfaction, has received rather little attention. In fact, there exists a challenging dilemma in balancing accuracy and diversity. To address these issues, we propose a new Graph Contrastive Learning (DivGCL) model for diversifying recommendations. Inspired by the excellence of the determinant point process (DPP), DivGCL adopts a DPP likelihood-based loss function to achieve an ideal trade-off between diversity and accuracy, optimizing it jointly with the advanced Gaussian noise-augmented GCL objective. Extensive experiments on four popular datasets demonstrate that DivGCL surpasses existing approaches in balancing accuracy and diversity, with an improvement of 23.47% at T@20 (abbreviation for trade-off metric) on ML-1M.

Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. It is challenging to timely prevent such model-stealing attacks to achieve strong protection and maintain utility. In this paper, we propose a novel non-parametric detector called Account-aware Distribution Discrepancy (ADD) to recognize queries from malicious users by leveraging account-wise local dependency. We formulate each class as a Multivariate Normal distribution (MVN) in the feature space and measure the malicious score as the sum of weighted class-wise distribution discrepancy. The ADD detector is combined with random-based prediction poisoning to yield a plug-and-play defense module named D-ADD for image classification models. Results of extensive experimental studies show that D-ADD achieves strong defense against different types of attacks with little interference in serving benign users for both soft and hard-label settings.

Incomplete multi-view multi-label classification aims to accurately predict labels for each sample in the face of some missing views. Due to its widespread presence in real-world scenarios, it has become an extensively researched topic. In addition to the challenges brought by missing views, it also encounters issues caused by redundant views, whose inclusion fails to make a positive contribution to performance. In this paper, we make the first attempt to take advantage of diffusion models to address the missing view problem and design a strategy to identify and remove redundant views. Specifically, we train a diffusion model conditioned on the pseudo-labels to recover information of missing views. The learned diffusion model can carry data distribution knowledge in training split to the data. Regarding redundant identification strategy, it is designed by considering both the additional information of views and the classification difficulty level of samples, thereby adaptively identifying and removing redundant views. We conduct extensive experiments on five datasets, and the proposed method achieves favorable performance against several state-of-the-art methods on the multi-view multi-label classification task.

Sequential recommendation aims to capture the temporal dependencies of items in a user's historical interactions and make recommendations based on this. Previous generative methods addressed the issue of data not directly reflecting user preference uncertainty by modeling the distribution of latent item representations. Diffusion model (DM)-based methods have achieved significant success due to their high-quality generation and stable training. However, they lack satisfactory user sequence representations to guide the generation process, impacting recommendation performance. Moreover, these methods overlook the drawback of slow inference speed, severely limiting their practical value. To obtain effective generative guidance signals and accelerate the recommendation process, we propose DAE4Rec. In this approach, a Graph Auto-Encoder (GAE) is used to obtain interpretable item node representations, revealing global transitions of items that previous methods struggled to uncover. Then, we use it to construct a generative guidance signal with lower coupling and variance for the diffusion model. Additionally, by employing a non-Markov chain derived from the forward diffusion process, it is the first to implement a 'skip-step' reverse process in diffusion model-based methods. And a creatively designed compensator is used to bridge the performance gap caused by 'skip-step'. Extensive experiments on three real-world datasets demonstrate that DAE4Rec outperforms other state-of-the-art generative sequential recommenders.

The emerging reasoning ability of large language models (LLMs) and accompanying commercial applications offer a promising path for service providers to deploy intelligent agents on their own products through API calls. However, the black-box nature of LLMs has driven providers to try prompt tuning to improve reasoning quality for competitiveness, while the generated reasoning logic results in additional service costs. Although some works have proposed collaborating LLMs and Small Language Models (SLMs) to reduce the frequency of LLM calls, most overlook the actual number of tokens interacting with the LLMs, which results in a potentially high cost still. Furthermore, directly compressing the prompt to reduce tokens often leads to a significant accuracy loss. To address the above challenges, we propose a cost-aware approach for collaborating LLMs and SLMs, named Coco. In our method, a confidence-based task assignment method is designed which leverages the result confidence of SLMs to assess task complexity and determine whether LLM involvement is necessary. For complex tasks, the SLM adapts the input by compressing unnecessary information according to confidence. Considering the potential loss of accuracy, prompt tuning-based reasoning optimization methods are introduced to guide the LLM in generating both the reasoning logic sketch and the final result. Finally, logic alignment is applied to fuse sketches from both models, ensuring the rationality of the reasoning logic. Experimental results on three open-source datasets demonstrate that our approach effectively reduces the cost of API calls to LLMs while ensuring the reasoning accuracy and the reasonableness of generated logic.

Time series forecasting has significant applications across various domains, including industry, agriculture, and finance. Transformer-based models have shown significant promise in enhancing time series forecasting over the past few years. However, existing methods struggle to simultaneously capture local details and global semantics under single-view architectures. They also find it difficult to dynamically adapt to time-varying and multi-scale temporal patterns while accurately modeling the complex, time-varying relationships between multiple variables. To address these challenges, we propose HRCformer, a novel Transformer-based framework that introduces two key innovations: the Hierarchical Recursive Interaction Convolution (HRIC) and the Triad Adaptive Recalibration Module (TARM). HRIC achieves joint modeling of fine-grained short-term fluctuations and high-order cross-period dependencies in time series by integrating Divide-and-Process Convolution for local processing with Recursive Channel Interaction Convolution for global processing. TARM further enhances dynamic modeling via Dynamic Variance Attention, which amplifies critical temporal deviations through 3D attention, and the Adaptive Multivariate Recalibration, which uses a two-layer fully connected network with nonlinear activation to learn the dynamic relationships between channels, suppresses noise, and emphasizes informative multivariate interactions. Comprehensive experiments conducted on seven real-world datasets highlight the superiority of HRCformer compared to prior state-of-the-art methods.

Document-level relation extraction (RE) aims to extract comprehensive correlations between entities and relations from documents. Most of existing works conduct transfer learning on pre-trained language models (PLMs), which allows for richer contextual representation to improve the performance. However, such PLMs-based methods suffer from incorporating structural knowledge, such as entity-entity interactions. Moreover, current works struggle to infer the implicit relations between entities across different sentences, which results in poor prediction. To deal with the above issues, we propose a novel and effective framework, named DocKS-RAG, which introduces extra structural knowledge and semantic information to further enhance the performance of document-level RE. Specifically, we construct a Document-level Knowledge Graph from the observable documentation data to better capture the structural information between entities and relations. Then, a Sentence-level Semantic Retrieval-Augmented Generation mechanism is designed to consider the similarity in different sentences by retrieving the relevant contextual semantic information. Furthermore, we present a hybrid-prompt tuning method on large language models (LLMs) for specific document-level RE tasks. Finally, extensive experiments conducted on two benchmark datasets demonstrate that our proposed framework enhances all the metrics compared with state-of-the-art methods.

While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervision of a reward model learned from preference data. One major challenge of RLHF is the inaccuracy of the intermediate reward model, especially in the tasks that requires complex reasoning for the reward model to score a response. We find that the reliability of the reward model varies across responses assigned with different rewards. This motivates us to filter the samples whose rewards may be unreliable to improve the signal-to-noise ratio during policy learning, resulting in Policy Filtration for Proximal Policy Optimization (PF-PPO). To choose a proper policy filtering strategy, we use the coefficient of determination ($R^2$) between the rewards and actual scores on filtered samples as the metrics to help us find promising strategies since it measures how well the rewards filtered by PF-PPO indicate real performance. We provide extensive experiments to validate the effectiveness of PF-PPO in code generation and math reasoning tasks. In code generation, PF-PPO achieves the state-of-the-art performance of 7-billion-parameter models on HumanEval (+7.9%), MBPP (+0.7%), and LeetCode Contest (+10.0%) which is a more challenging benchmark created by us. In math reasoning, PF-PPO yields performance increase using different reward models and benchmarks (Ape210K and CMATH).

Contrastive Learning (CL) has recently achieved significant progress in the field of recommender systems, as it leverages supervision signals from raw data to mitigate the issue of data sparsity. However, most existing methods rely on random or heuristic data augmentation strategies, which often disrupt the intrinsic structural relationships in the graph and introduce spurious connections, leading to suboptimal representations for recommendation tasks. To address these challenges, we propose a novel graph contrastive learning model based on Large Language Model (LLM), named LLMGCL, which leverages LLM for both embedding augmentation and graph augmentation, and incorporates inter-layer contrastive learning to improve recommendation performance. Specifically, the proposed method first designs an LLM-driven embedding augmentation strategy, where item embeddings pre-trained by LLM are aggregated to construct user embeddings, enabling contrastive views to retain richer semantic relationships. Furthermore, to enhance the structural integrity of the graph while minimizing noise, we develop two targeted graph augmentation strategies powered by LLM: one leverages LLM to identify high-confidence user-item interactions from historical behaviors to refine observed preferences, while the other infers potential but unobserved interactions to reinforce graph connectivity. Finally, we design an inter-layer contrastive learning module that aligns representations across different Graph Neural Network layers, effectively mitigating the over-smoothing effect and enhancing feature discrimination. These combined strategies significantly improve recommendation quality, as demonstrated by extensive experiments on public datasets.

The rapid growth of multimedia content has driven the development of recommender systems. Most previous work focuses on uncovering latent relationships among items to learn better representations. However, this approach does not sufficiently account for user affinities, potentially leading to an imbalance in the structure modeling of users and items. Moreover, the sparsity and imbalance of user-item interactions further hinder effective representation learning. To address these challenges, we propose a framework called BLAST, which balances structures and interactions via large language models and optimal transport for multimodal recommendation. Specifically, we utilize large language models to summarize side information and generate user profiles. Based on these profiles, we design an intra- and inter-entity structure balancing module to capture item-item and user-user relationships, integrating these affinities into the final representations. Furthermore, we impose constraints on negative sample selection, augment the training data with false negative items and the optimal transport algorithm, thereby leading to smoother interactions. We evaluate BLAST on three real-world datasets, and the results demonstrate that our method significantly outperforms state-of-the-art baselines, which validates the superiority and effectiveness of BLAST.

Recommender systems play a critical role in many applications by providing personalized recommendations based on user interactions. However, it remains a major challenge to capture complex sequential patterns and address noise in user interaction data. While advanced neural networks have enhanced sequential recommendation by modeling high-order item dependencies, they typically assume that the noisy interaction data as the user's preferred preferences. This assumption can lead to suboptimal recommendation results. We propose a Variational Graph Auto-Encoder driven Graph Enhancement (VGAE-GE) method for robust augmentation in sequential recommendation. Specifically, our method first constructs an item transition graph to capture higher-order interactions and employs a Variational Graph Auto-Encoder (VGAE) to generate latent variable distributions. By utilizing these latent variable distributions for graph reconstruction, we can improve the item representation. Next, we use a Graph Convolutional Network (GCN) to transform these latent variables into embeddings and infer more robust user representations from the updated item embeddings. Finally, we obtain the reconstructed user check-in data, and then use a Mamba-based recommender to make the recommendation process more efficient and the recommendation results more accurate. Extensive experiments on five public datasets demonstrate that our VGAE-GE model improves recommendation performance and robustness.

As machine learning models become widely deployed in data-driven applications, ensuring compliance with the 'right to be forgotten' as required by many privacy regulations is vital for safeguarding user privacy. To forget the given data, existing re-labeling based unlearning methods employ a single-step adjustment scheme that revises the decision boundaries in one re-labeling phase. However, such single-step approaches lead to coarse-grained changes in decision boundaries among the remaining classes and impose adverse effects on the model utility. To address these limitations, we propose 'Self-Unlearning with Layered Iteration (SULI),' a novel unlearning approach that introduces a layered iteration strategy to re-label the forgetting data iteratively and refine the decision boundaries progressively. We further develop a 'Selective Probability Adjustment (SPA)' technique, which uses a soft-label mechanism to promote smoother decision-boundary transitions. Comprehensive experiments on three benchmark datasets demonstrate that SULI achieves superior performance in effectiveness, efficiency, and privacy compared to the state-of-the-art baselines in both class-wise and instance-wise unlearning scenarios. The source code is released at https://github.com/Hongyi-Lyu-MQ/SULI.

With the rapid urbanization in the modern era, smart traffic profiling based on multimodal sources of data has been playing a significant role in ensuring safe travel, reducing traffic congestion and optimizing urban mobility. Most existing methods for traffic profiling on the road level usually utilize single-modality data, i.e., they mainly focus on image processing with deep vision models or auxiliary analysis on the textual data. However, the joint modeling and multimodal fusion of the textual and visual modalities have been rarely studied in road traffic profiling, which largely hinders the accurate prediction or classification of traffic conditions. To address this issue, we propose a novel multimodal learning and fusion framework for road traffic profiling, named TraffiCFUS. Specifically, given the traffic images, our TraffiCFUS framework first introduces Vision Language Models (VLMs) to generate text and then creates tailored prompt instructions for refining this text according to the specific scene requirements of road traffic profiling. Next, we apply the discrete Fourier transform to convert multimodal data from the spatial domain to the frequency domain and perform a cross-modal spectrum transform to filter out irrelevant information for traffic profiling. Furthermore, the processed spatial multimodal data is combined to generate fusion loss and interaction loss with contrastive learning. Finally, extensive experiments on four real-world datasets illustrate superior performance compared with the state-of-the-art approaches.

Graph unlearning involves removing certain elements, such as edges and nodes, from a trained graph neural network. This research has significant practical implications, such as enabling users to enforce data removal requests in compliance with their "right to be forgotten". Additionally, it can help models regain utility by eliminating the impact of poisoned data. Although some graph unlearning algorithms, such as GNNDelete, assign forgotten samples to random negative samples to negate their impact on the model, using random samples is not the optimal choice as it may lead to decreased performance of the model on downstream tasks. Moreover, GNNDelete requires additional space to mark the forgotten samples and their neighborhoods, making this method inconvenient to implement and difficult to continue training. In light of this, we propose a novel graph unlearning framework called Adversarial Example-Based Graph Contrastive Unlearning (AEGCU). AEGCU generates adversarial examples through a straightforward method and utilizes contrastive learning to compare the features of the forgotten samples with those of the adversarial examples, thereby aiming to thoroughly erase edge information. Our experiments demonstrate that AEGCU effectively forgets edges in the graph while maximizing the retention of predictive capabilities. Our model improves performance on both the link prediction as well as the node classification tasks, especially on the node classification task, where we improve performance by approximately 11% over GNNDelete with taking 30% less time on average compared to the GNNDelete method.

Human activity recognition (HAR) is an evolving technique that offers innovative solutions across various domains, such as healthcare, sports training, and human-computer interactions. This paper addresses the novel challenge of video-based activity recognition, focusing on detecting and classifying athletes' actions to enable precision sports training. Conventional HAR methods based on direct video analysis incur excessive computational overhead and constrained applicability. In contrast, our novel transformer-based framework, namely RSFomer, converts videos into multivariate time series, and then detects and classifies the athletes' actions. However, sports videos often suffer from severe occlusion, which introduces significant noise to the converted time series and thus deteriorates recognition performance. To address this challenge, we implement several innovative strategies to improve the robustness of our framework. First, we propose a dual-scale filtering mechanism that leverages the unscented Kalman filter and kinematic constraints to reduce noise and outliers in the converted time series. Second, we incorporate the masking mechanism and temporal slicing mechanism to enhance the transformer's ability to handle anomalies and extract multi-scale features for accurate action recognition. We perform extensive evaluations on our Boxing dataset as well as the UEA and FineGym datasets. The results demonstrate that our RSFomer is effective, outperforming existing state-of-the-art methods with significant advantages.

Recent advancements in generative models have positioned them as one of the principal tools for sequential recommendation due to their exceptional sample diversity and generalization capabilities. Among these, diffusion model-based sequential recommenders have achieved remarkable success. However, most existing approaches still face critical challenges, resulting in suboptimal generation quality: (1) They fail to leverage multimodal knowledge for constructing item representations with well-structured distributional characteristics and semantically enriched information; (2) They predominantly rely on discrete diffusion processes, leading to high error accumulation, reduced time efficiency, and constrained controllability in generative sampling. To mitigate these challenges, we propose LSGM4Rec, a novel framework that integrates Large Language Models (LLMs) with advanced multimodal encoding models to establish multimodal fusion embeddings for items. This design ensures distinct distributional characteristics while enabling the incorporation of semantically rich modal features into guidance condition. Furthermore, we pioneer the stochastic differential equations (SDEs) for recommendation, facilitating smooth transitions between data distributions and enabling optimal trade-off between sampling efficiency and generation quality. Extensive experiments on three datasets demonstrate that LSGM4Rec outperforms existing state-of-the-art sequential recommendation methods.

Federated learning (FL) is a distributed machine learning paradigm that enables multiple clients to collaboratively train a shared model without exposing their raw data. However, existing FL research has primarily focused on optimizing learning performance based on the assumption of uniform client participation, with few studies delving into performance fairness under inconsistent client participation, particularly in model-heterogeneous FL environments. In view of this challenge, we propose PHP-FL, a novel model-heterogeneous FL method that explicitly addresses scenarios with varying client participation probabilities to enhance both model accuracy and performance fairness. Specifically, we introduce a Dual-End Aligned ensemble Learning (DEAL) module, where small auxiliary models on clients are used for dual-end knowledge alignment and local ensemble learning, effectively tackling model heterogeneity without a public dataset. Furthermore, to mitigate update conflicts caused by inconsistent participation probabilities, we propose an Importance-driven Selective Parameter Update (ISPU) module, which accurately updates critical local parameters based on training progress. Finally, we implement PHP-FL on a lightweight FL platform with heterogeneous clients across three different client participation patterns. Extensive experiments under heterogeneous settings and diverse client participation patterns demonstrate that PHP-FL achieves state-of-the-art performance in both accuracy and fairness. Our code is available at: https://github.com/Siyuan01/PHP-FL-main.

The long-tail problem in sequential recommender systems stems from imbalanced interaction data, resulting in suboptimal model performance for tail users and items. Recent studies have leveraged head data to enhance tail data for diminish the impact of the long-tail problem. However, these methods often adopt ad-hoc strategies to distinguish between head and tail data, which fails to capture the underlying distributional characteristics and structural properties of each category. Moreover, due to a substantial representational gap exists between head and tail data, head-to-tail enhancement strategies are susceptible to negative transfer, often leading to a decline in overall model performance. To address these issues, we propose a hierarchical partitioning and stepwise enhancement framework, called HPSERec, for long-tailed sequential recommendation. HPSERec partitions the item set into subsets based on a data imbalance metric, assigning an expert network to each subset to capture user-specific local features. Subsequently, we apply knowledge distillation to progressively improve long-tail interest representation, followed by a Sinkhorn optimal transport-based feedback module, which aligns user representations across expert levels through a globally optimal and softly matched mapping. Extensive experiments on three real-world datasets demonstrate that HPSERec consistently outperforms all baseline methods. The implementation code is available at https://anonymous.4open.science/r/HPSERec-2404.

Fast Gradient Sign Method (FGSM)-based ap proaches play a critical role in adversarial attacks, particularly in transfer-based attacks. Recent advancements aim to enhance adversarial transferability by refining the sign function in FGSMs using precise gradient information. However, due to the instability of gradient update directions, such precise gradient information may still converge to local minima, thereby limiting transferability. To address this issue, we propose Majority-vote Gradient Scaling (MVGS), a novel method designed to sta bilize gradient update directions. MVGS dynamically rescales momentum terms by evaluating the consistency of historical gradients at each pixel. Since MVGS operates solely through parameter-specific momentum rescaling, it can be seamlessly integrated with existing adversarial attack methods that lever age precise gradient information. Extensive comparative and ablation experiments demonstrate that MVGS significantly improves attack success rates (ASR), achieving up to a 6.1% increase over the state-of-the-art APAA method, confirming its effectiveness.

Next Point-of-Interest (POI) recommendation has become a crucial task in Location-Based Social Networks (LBSNs), which provide personalized recommendations by predicting the user's next check-in locations. Commonly used models including Recurrent Neural Networks (RNNs) and Graph Convolutional Networks (GCNs) have been widely explored. However, these models face significant challenges, including the difficulty of capturing the hierarchical and tree-like structure of POIs in Euclidean space and the sparsity problem inherent in POI recommendations. To address these challenges, we propose a Hyperbolic Variational Graph Auto-Encoder (HVGAE) for next POI recommendation. Specifically, we utilize a Hyperbolic Graph Convolutional Network (Hyperbolic GCN) to model hierarchical structures and tree-like relationships by converting node embeddings from euclidean space to hyperbolic space. Then we use Variational Graph Auto-Encoder (VGAE) to convert node embeddings to probabilistic distributions, enhancing the capture of deeper latent features and providing a more robust model structure. Furthermore, we combine the Mamba4Rec recommender and Rotary Position Embedding (RoPE) and propose Rotary Position Mamba (RPMamba) to effectively utilize POI embeddings rich in sequential information, which improves the accuracy of the next POI recommendation. Extensive experiments on three public datasets demonstrate the superior performance of the HVGAE model.

Click-through rate (CTR) prediction is a crucial task in personalized information retrievals, such as industrial recommender systems, online advertising, and web search. Most existing CTR Prediction models utilize explicit feature interactions to overcome the performance bottleneck of implicit feature interactions. Hence, deep CTR models based on parallel structures (e.g., DCN, FinalMLP, xDeepFM) have been proposed to obtain joint information from different semantic spaces. However, these parallel subcomponents lack effective supervision and communication signals, making it challenging to efficiently capture valuable multi-views feature interaction information in different semantic spaces. To address these issues, we propose a simple yet effective novel CTR model: Contrast-enhanced Through Network (CETN). Drawing inspiration from sociology, CETN leverages the complementary nature of diversity and homogeneity to guide the model in acquiring higher-quality feature interaction information. Specifically, CETN employs product-based feature interactions and the augmentation (perturbation) concept from contrastive learning to segment different semantic spaces, each with distinct activation functions. This improves diversity in the feature interaction information captured by the model. Additionally, we introduce self-supervised signals and through connection within each semantic space to ensure the homogeneity of the captured feature interaction information. The experiments conducted on four real datasets demonstrate that our model consistently outperforms twenty baseline models in terms of AUC and Logloss.

Embedding-based recommender systems rely on historical interactions to model users, which poses challenges for recommending to new users, known as the user cold-start problem. Some approaches incorporate social networks to deduce preferences based on the social circles of cold-start users to solve the problem of sparse features. However, such methods have difficulty distinguishing between superficial correlations and causal relationships in social behaviors, leading to inaccuracies in predicting user preferences. To address the aforementioned issues, we propose the Causal Contrastive Learning Recommendation (C2lRec) framework. Specifically, we causally model the inference of hidden preferences from the feature and historical behavior of warm users and predict user interactions based on such preferences. The counterfactual inference is subsequently performed to intervene and extract interactions from historical behaviors of warm users that influence their preferences, designating as primary causal variables. Additionally, we utilize the primary causal variables from users within the social circle of cold-start users to substitute the missing historical interactions of cold-start users and employ a similar causal modeling approach to uncover hidden preferences as we do with warm users. Finally, we realize causal contrastive learning to enhance the distribution of cold-start users. Extensive experiments conducted on three public datasets demonstrate that the recommendation performance of C2lRec exceeds that of state-of-the-art methods.

In mobile edge computing (MEC) environments, with the increase in the number of web services possessing the same or similar functions, the prediction of nonfunctional quality of service (QoS) indicators turns increasingly vital in satisfying the diverse needs of different users. Despite the significant achievements of QoS prediction approaches such as collaborative filtering (CF), they often fail to obtain informative representations due to complex user-service-time QoS data. Moreover, changing network conditions and overlooked temporal factors lead to reduced accuracy. In response to these challenges, this paper proposes a novel deep learning to hash method for time-aware QoS prediction built on a VQ-VAE (namedPred$_{QoS}$QoS). In the proposedPred$_{QoS}$QoS, inspired by advanced CF approaches, we make QoS predictions at a specific moment for the target user through its similar timeslots. Specifically, we train a codebook to discretize the continuous latent representation obtained by the encoder based on vector quantization (VQ), which is motivated by the generative vector-quantized variational autoencoder (VQ-VAE) model, allowing us to derive compact binary codes representing the QoS data. Then, the similarities between QoS data are determined, helping to make effective and efficient predictions. Furthermore, the time-awarePred$_{QoS}$QoSapproach incorporates a temporal factor by training on multiple QoS data (including the user, service, and time dimensions). As a result, the discrete hash codes (i.e., QoS data representations) derived from the encoder can fully uncover the time factor’s dynamic impact on the QoS data, thereby yielding significantly improved prediction performance. In summary, thePred$_{QoS}$QoSapproach learns compact hash codes for original QoS data while taking time into account, enabling accurate predictions to be produced through similar timeslots for the target users. Finally, comprehensive experiments carried out on the real-world WS-DREAM dataset affirm the exceptional performance of thePred$_{QoS}$QoS.

In edge computing, end devices (EDs) containerize tasks with the necessary resources and offload subsets to a nearby high-capacity edge server (ES) to improve efficiency. Most existing research focuses on inseparable task offloading to minimize response times or resource allocation to reduce energy consumption. However, task execution can be speeded up with excessive computing and network resources, it will increase energy consumption and incur unnecessarily high costs. Besides, complex applications like autonomous driving often partition sequential tasks to improve performance, necessitating a joint optimization of sequential task offloading and multi-resource allocation. In this paper, we introduce a Stackelberg game-based framework to model the interplay between these elements.EDs, acting as leaders, determine the offloading breakpoints of sequential tasks and the locality for processing. TheES, as the follower, uses the Karush-Kuhn-Tucker (KKT) conditions and a Boundary-constrained quasi-Particle Swarm Optimization (Bc-qPSO) algorithm to refine computing and network resource allocation, aiming to reduce system costs effectively. Our simulations show that the proposed algorithms reduce cost by approximately 10%-20% compared to traditional methods, highlighting their potential for improving the efficiency of edge computing systems.

The usage of heterogeneous resources provisioned by edge nodes can be co-optimized through re-scheduling microservices. Current (re-)scheduling approaches typically treat the task of co-optimization as a single-objective optimization problem, which cannot address the issue of imbalanced usage of heterogeneous resources (e.g., CPU, memory, bandwidth) on a single edge node. More importantly, these approaches are inadequate in handling: (i) the adaptive co-optimization of heterogeneous resources, (ii) the fine-grained construction of micro service dependencies, and (iii) multi-step online mi croservice re-scheduling. To address these challenges, this paper proposes a Dependency-aware Online Microservice re-Scheduling (DOMS) approach. DOMS formulates microservice re-scheduling as a multi-knapsack optimization problem and solves it using a Double Dueling Deep Q-Network (D3QN) with prioritized experience replay. Specifically, an adaptive heterogeneous resources balancing detection algorithm is developed, incorporating a dynamic detection threshold mechanism. A fine-grained microservice performance metrics dependency graph is constructed by capturing causal relationships to represent sequential execution dependency. Based on this graph, a microservice multi-step scheduling partition algorithm is devised. Extensive experiments are conducted upon publicly-available datasets, and evaluation results demonstrate that DOMS outperforms the state-of-the-art techniques with improvements of at least 1.85%, 6.45%, 0.56%, and 3.18% in terms of latency, energy consumption, balance degree, and throughput. These results highlight the effectiveness and superiority of DOMS in maintaining a balanced usage of heterogeneous resources and improving network throughput, while satisfying latency and energy consumption constraints.

Federated Learning (FL) has emerged as a promising solution in Edge Computing (EC) environments to process the proliferation of data generated by edge devices. By collaboratively optimizing the global machine learning models on distributed edge devices, FL circumvents the need for transmitting raw data and enhances user privacy. Despite practical successes, FL still confronts significant challenges including constrained edge device resources, multiple tasks deployment, and data heterogeneity. However, existing studies focus on mitigating the FL training costs of each single task whereas neglecting the resource consumption across multiple tasks in heterogeneous FL scenarios. In this paper, we propose Heterogeneous Federated Learning with Local Parameter Sharing (FedLPS) to fill this gap. FedLPS leverages principles from transfer learning to facilitate the deployment of multiple tasks on a single device by dividing the local model into a shareable encoder and task-specific encoders. To further reduce resource consumption, a channel-wise model pruning algorithm that shrinks the footprint of local models while accounting for both data and system heterogeneity is employed in FedLPS. Additionally, a novel heterogeneous model aggregation algorithm is proposed to aggregate the heterogeneous predictors in FedLPS. We implemented the proposed FedLPS on a real FL platform and compared it with state-of-the-art (SOTA) FL frameworks. The experimental results on five popular datasets and two modern DNN models illustrate that the proposed FedLPS significantly outperforms the SOTA FL frameworks by up to 4.88% and reduces the computational resource consumption by 21.3%. Our code is available at: https://github.com/jyzgh/FedLPS.

With the rapid development of the mobile internet, there is an increasing demand for quick access to effective data. Consequently, more research is focusing on data processing and optimization of recommendation systems in edge computing environments. However, in traditional edge computing environments, recommendation systems typically depend on frequent data query interactions among all edge servers to obtain results, which increases time delays. This issue is further exacerbated by the need to process large amounts of data within edge storage systems. To address this challenge, we propose an efficient recommendation method based on data allocation. Specifically, during the data allocation process, we first extract similar features of users, ensuring that the characteristics of some user data align as closely as possible with the overall user feature distribution. Then, using an improved consistent hashing algorithm, we achieve a uniform data layout, allowing the recommendation system to efficiently and accurately provide recommendations by querying data from the nearest edge server to the user. Finally, extensive experiments on real datasets show that our method significantly reduces time delays and improves the accuracy of recommendation results.

Recently, patch-based transformer methods have demonstrated strong effectiveness in time series forecasting. However, the complexity of self-attention imposes demands on memory and compute resources. In addition, though patches can capture comprehensive temporal information while preserving locality, temporal information within patches remains important for time series prediction. The existing methods mainly focus on modeling long-term dependencies across patches, while paying little attention to the short-term dependencies within patches. In this paper, we propose the Global and Local Frequency-domain Network (GLFNet), a novel architecture that efficiently learns global time dependencies and local time relationships in the frequency domain. Specifically, we design a frequency filtering layer to learn the temporal interactions instead of self-attention. Then we devise a dual filtering block consisting of global filter block and local filter block which learns the global dependencies across patches and local dependencies within patches. Experiments on seven benchmark datasets demonstrate that our approach achieve superior performance with improved efficiency.

Trust plays an essential role in an individual's decision-making. Traditional trust prediction models rely on pairwise correlations to infer potential relationships between users. However, in the real world, interactions between users are usually complicated rather than pairwise only. Hypergraphs offer a flexible approach to modeling these complex high-order correlations (not just pairwise connections), since hypergraphs can leverage hyperedeges to link more than two nodes. However, most hypergraph-based methods are generic and cannot be well applied to the trust prediction task. In this paper, we propose an Adaptive Hypergraph Network for Trust Prediction (AHNTP), a novel approach that improves trust prediction accuracy by using higher-order correlations. AHNTP utilizes Motif-based PageRank to capture high-order social influence information. In addition, it constructs hypergroups from both node-level and structure-level attributes to incorporate complex correlation information. Furthermore, AHNTP leverages adaptive hypergraph Graph Convolutional Network (GCN) layers and multilayer perceptrons (MLPs) to generate comprehensive user embeddings, facilitating trust relationship prediction. To enhance model generalization and robustness, we introduce a novel supervised contrastive learning loss for optimization. Extensive experiments demonstrate the superiority of our model over the state-of-the-art approaches in terms of trust prediction accuracy.

Anomaly detection is a popular research topic in Artificial Intelligence and has been widely applied in network security, financial fraud detection, and industrial equipment failure detection. Isolation forest based methods are the base algorithms to detect anomalies in these scenarios for their simplicity and efficiency, which has been further exploited with multi-folk trees and learning mechanisms to realize the optimal isolation forest for high detection accuracy. However, the optimal isolation forest is time-consuming with the learning mechanisms, resulting in the task failing of time-constrained applications. Moreover, the original optimal isolation forest fails to construct the optimal tree structure restricted by the time complexity. To address the above challenges, we propose an efficient anomaly detection method called EEIF, which realizes the real e-folk structure of the optimal isolation forest in our practical algorithm design. Specifically, we design a distribution that perfectly matches the e-branch theory to construct the optimal isolation forest. Then, we design an FR clustering scheme to achieve fast training of the isolation forest with learning to hash and provide related proofs of accuracy and efficiency. Besides, a parallel algorithm is integrated into our method to reduce prediction time. Finally, extensive experiments are conducted on a large amount of real-world datasets and the results demonstrate that our method significantly improves efficiency while ensuring effectiveness, compared with the state-of-the-art methods.

By distributing computing and storage resources to edge servers (ESs), edge computing enables service execution closer to requests, alleviating high latency caused by long-distance data transmission. The communication between ESs facilitates collaborative service placement (CSP) on multiple ESs, leading to latency reduction and thereby improving the quality of service. However, the discrepancies in service request distributions among ESs pose challenge to effective CSP, while limited prior knowledge further increases the difficulty in policy formation. Additionally, the delayed awareness of placement strategies among other ESs exacerbates the influence of non-Markovian nature. To overcome above challenges, a leader-follower based multi-agent reinforcement learning for CSP scheme, named LFMCSP, is proposed in this paper. Specifically, a CSP model is formulated, with ESs abstracted as intelligent agents within it. Then, the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm is utilized to explore potential patterns in complex requests by experience sharing. To achieve transparency of global states for all agents, the leader-follower architecture is integrated into MADDPG. Through rigorous experiments and comparisons with various baseline schemes, LFMCSP demonstrates effectiveness in reducing service execution delays.

Recently, hyperbolic spaces have proven beneficial for service recommendation due to their exponentially growing spatial properties conforming to power-law distributed user-item networks. Among them, the combination of hyperbolic space with graph convolution has achieved great success. However, hyperbolic convolutional models still perform multi-layer convolution in tangent space (Euclidean space), leading to the still inevitable problem of over-smoothing arising from multi-layer convolution. In addition, most of these models randomly draw negative samples from items that users have not interacted with, so that some of the samples obtained may not be well suited for model optimization. To tackle the above challenges, we propose a new Hyperbolic GCN model based on Contrastive Learning and Second-order Reachable sampling for collaborative filtering (HG-CLSR), which improve high quality of representations by exploring the distribution of users and items in hyperbolic space. Specifically, We first introduce a root alignment approach to encourage embeddings to align with the tangent space, thereby reducing distortions during the embedding mapping process in space. Then, we perform contrastive learning in hyperbolic space to motivate the spatial distribution of nodes to better fit the hyperbolic space. Moreover, we sample in the user’s second-order reachable item set, which ensures that the negative sample is more similar to the positive sample, so that the negative node can provide better information for guiding model optimization. Extensive experiments on three real-world datasets demonstrate that the HG-CLSR is significantly superior compared to existing hyperbolic models.

Federated learning addresses privacy concerns in multimedia recommender systems by enabling collaborative model training without exchanging raw data. However, existing federated recommendation models are mainly based on basic backbones like Matrix Factorization (MF), which are inadequate to capture complex implicit interactions between users and multimedia content. Graph Convolutional Networks (GCNs) offer a promising method by utilizing the information from high-order neighbors, but face challenges in federated settings due to problems such as over-smoothing, data heterogeneity, and elevated communication expenses. To resolve these problems, we propose a Cluster-driven Personalized Federated Recommender System with Interest-aware Graph Convolution Network (CPF-GCN) for multimedia recommendation. CPF-GCN comprises a local interest-aware GCN module that optimizes node representations through subgraph-enhanced adaptive graph convolution operations, mitigating the over-smoothing problem by adaptively extracting information from layers and selectively utilizing high-order connectivity based on user interests. Simultaneously, a cluster-driven aggregation approach at the server significantly reduces communication costs by selectively aggregating models from clusters. The aggregation produces a global model and cluster-level models, combining them with the user's local model allows us to tailor the recommendation model for the user, achieving personalized recommendations. Moreover, we propose an adversarial optimization technique to further augment the robustness of CPF-GCN. Experiments on three datasets demonstrate that CPF-GCN significantly outperforms the state-of-the-art models.

Federated learning (FL) has emerged as a prominent machine learning paradigm in edge computing environments, enabling edge devices to collaboratively optimize a global model without sharing their private data. However, existing FL frameworks suffer from efficacy deterioration due to the system heterogeneity inherent in edge computing, especially in the presence of domain shifts across local data. In this paper, we propose a heterogeneous FL framework DapperFL, to enhance model performance across multiple domains. In DapperFL, we introduce a dedicated Model Fusion Pruning (MFP) module to produce personalized compact local models for clients to address the system heterogeneity challenges. The MFP module prunes local models with fused knowledge obtained from both local and remaining domains, ensuring robustness to domain shifts. Additionally, we design a Domain Adaptive Regularization (DAR) module to further improve the overall performance of DapperFL. The DAR module employs regularization generated by the pruned model, aiming to learn robust representations across domains. Furthermore, we introduce a specific aggregation algorithm for aggregating heterogeneous local models with tailored architectures and weights. We implement DapperFL on a real-world FL platform with heterogeneous clients. Experimental results on benchmark datasets with multiple domains demonstrate that DapperFL outperforms several state-of-the-art FL frameworks by up to 2.28%, while significantly achieving model volume reductions ranging from 20% to 80%. Our code is available at: https://github.com/jyzgh/DapperFL.

Sequential recommendation models generate embeddings for items through the analysis of historical user-item interactions and utilize the acquired embeddings to predict user preferences. Despite being effective in revealing personalized preferences for users, these models heavily rely on user-item interactions. However, due to the lack of interaction information, new users face challenges when utilizing sequential recommendation models for predictions, which is recognized as the cold-start problem. Recent studies, while addressing this problem within specific structures, often neglect the compatibility with existing sequential recommendation models, making seamless integration into existing models unfeasible.To address this challenge, we propose CMCLRec, a Cross-Modal Contrastive Learning framework for user cold-start RECommendation. This approach aims to solve the user cold-start problem by customizing inputs for cold-start users that align with the requirements of sequential recommendation models in a cross-modal manner. Specifically, CMCLRec adopts cross-modal contrastive learning to construct a mapping from user features to user-item interactions based on warm user data. It then generates a simulated behavior sequence for each cold-start user in turn for recommendation purposes. In this way, CMCLRec is theoretically compatible with any extant sequential recommendation model. Comprehensive experiments conducted on real-world datasets substantiate that, compared with state-of-the-art baseline models, CMCLRec markedly enhances the performance of conventional sequential recommendation models, particularly for cold-start users.

Explainable Artificial Intelligence (XAI) aims to make artificial intelligence (AI) systems transparent and understandable to humans, providing clear explanations for the decisions made by AI models. This paper presents a novel pipeline and a digital dashboard that provides a user-friendly platform for interpreting the results of machine learning algorithms using XAI technology. The dashboard utilizes evidence-based design principles to deliver information clearly and concisely, enabling users to better understand the decisions made by their algorithms. We integrate XAI services into the dashboard to explain the algorithm's predictions, allowing users to understand how their models function and make informed decisions. We demonstrate a motivating scenario in banking and present how the proposed system enhances transparency and accountability and improves trust in the technology.

Abstract Edge computing is regarded as an extension of cloud computing that brings computing and storage resources to the network edge. For some Industrial Internet of Things (IIoT) applications such as supply‐chain supervision and collaboration, Internet of Vehicles, real‐time video analysis and so forth, users should be authenticated before visiting the geographically distributed edge servers. Limited by the considerable latency between the cloud and edge servers, and the limited capacity of edge servers, it is infeasible to copy the authentication method from cloud servers when users are authenticated in edge servers. In view of this challenge, this paper proposes a novel token‐based authentication scheme, named EdgeAuth, that enables fast edge user authentication through collaboration among cloud servers and edge servers. Under the EdgeAuth scheme, edge servers can rapidly verify the credentials of users who have been authenticated by the cloud server. EdgeAuth can also protect users from a series of authentication attacks, for example, the replay attack, DoS attack and man‐in‐the‐middle attack. The results of experiments conducted on a simulated edge computing environment validate the usefulness of EdgeAuth through a comparison in latency and throughput against two baseline schemes.

Summary With the development of artificial intelligence, cloud‐edge computing and virtual reality, the industrial design that originally depends on human imagination and computing power can be transitioned to metaverse applications in smart manufacturing, which offloads the services of metaverse to cloud and edge platforms for enhancing quality of service (QoS), considering inadequate computing power of terminal devices like industrial sensors and access points (APs). However, large overhead and privacy exposure occur during data transmission to cloud, while edge computing devices (ECDs) are at risk of overloading with redundant service requests and difficult central control. To address these challenges, this paper proposes a minority game (MG) based cloud‐edge service offloading method named COM for metaverse manufacturing. Technically, MG possesses a distribution mechanism that can minimize reliance on centralized control, and gains its effectiveness in resource allocation. Besides, a dynamic control of cut‐off value is supplemented on the basis of MG for better adaptability to network variations. Then, agents in COM (i.e., APs) leverage reinforcement learning (RL) to work on MG history, offloading decision, QoS mapping to state, action and reward, for further optimizing distributed offloading decision‐making. Finally, COM is evaluated using a variety of real‐world datasets of manufacturing. The results indicate that COM has 5.38% higher QoS and 8.58% higher privacy level comparing to benchmark method.

Federated learning (FL) is a popular approach to facilitate privacy-aware machine learning since it allows multiple clients to collaboratively train a global model without granting others access to their private data. It is, however, known that FL can be vulnerable tomembership inference attacks(MIAs), where the training records of the global model can be distinguished from the testing records. Surprisingly, research focusing on the investigation of the source inference problem appears to be lacking. We also observe that identifying a training record's source client can result in privacy breaches extending beyond MIAs. For example, consider an FL application where multiple hospitals jointly train a COVID-19 diagnosis model, membership inference attackers can identify the medical records that have been used for training, and any additional identification of the source hospital can result the patient from the particular hospital more prone to discrimination. Seeking to contribute to the literature gap, we take the first step to investigate source privacy in FL. Specifically, we propose a new inference attack (hereafter referred to assource inference attack– SIA), designed to facilitate an honest-but-curious server to identify the training record's source client. The proposed SIAs leverage the Bayesian theorem to allow the server to implement the attack in a non-intrusive manner without deviating from the defined FL protocol. We then evaluate SIAs in three different FL frameworks to show that in existing FL frameworks, the clients sharing gradients, model parameters, or predictions on a public dataset will leak such source information to the server. We also conduct extensive experiments on various datasets to investigate the key factors in an SIA. The experimental results validate the efficacy of the proposed SIAs, e.g., an attack success rate of 67.1% (baseline 10%) can be achieved when the clients share model parameters with the server. Comprehensive ablation studies demonstrate that the success of an SIA is directly related to the overfitting of the local models.

The provision of privacy-preserving recommendations for geological tourist attractions is an important research area. The historical check-in data collected from location-based social networks (LBSNs) can be utilized to mine their preferences, thereby facilitating the promotion of the geological tourism industry. However, such check-ins often contain sensitive user information that poses privacy leakage risks. To address this issue, some methods have been proposed to develop privacy-preserving point-of-interest (POI) recommendation systems. These methods commonly rely on either perturbation-based or federated learning techniques to protect users’ privacy. However, the former can hinder preference capture, while the latter remains vulnerable to privacy breaches during the parameter-sharing process. To overcome these challenges, we propose a novel privacy-preserving POI recommendation model that incorporates users’ privacy preferences based on a simplified graph convolutional neural network. Specifically, we employ a generative model to create a subset of POIs that reflect users’ preferences but do not reveal their private information, and then we design a simplified graph convolutional network to analyze the high-order connectivity between users and POIs that are privacy-preserving. The resulting model enables efficient POI recommendation under strict privacy protection, which is particularly relevant to geological tourism. Experimental results on two public datasets demonstrate the effectiveness of our proposed approach.

Vehicle-based mobile crowdsensing has gained widespread attention due to its low cost and efficient data collection mode. One common method to improve the accuracy of sensing data in this context is truth discovery. However, the emergence of privacy leakage and data misuse has reduced users’ motivation to participate in sensing tasks. Meanwhile, existing solutions for privacy-preserving truth discovery generally suffer from low computational efficiency and frequent interactions between users and servers. Hence, this paper proposes a novel privacy-preserving truth discovery scheme based on secure multi-party computation. For the purpose of high efficiency and strong privacy protection, we utilize the Secret Sharing method to securely decompose data and construct a Secure Multi-party Computation protocol to compute the ground truth. In addition, the weight value generated by truth discovery is employed as a quantitative data quality indicator that dynamically adjusts the user’s rewards and constructs a data quality-driven incentive mechanism. Finally, we demonstrate the high performance of our method through a detailed analysis, showing its effectiveness even in scenarios with numerous users.

With the rapid development of deep neural network research, many deep neural network prediction services are provided for cloud service users. However, due to the untrusted nature of cloud computing, there are risks associated with this. To secure user data and cloud servers at the same time, we designed a secure prediction system, named SecDM (SecureDeepMove), which focuses on an attentional recurrent network for human mobility prediction. A neural network inference system that allows two parties to work together securely and efficiently without revealing any data is presented in this work. To design it, with the help of secret sharing technology, we first propose several secure, efficient, and lossless two-party protocols, which can securely calculate non-linear functions in the model, such as sigmoid, tanh, and softmax. In addition, a secure and effective strategy is introduced to maintain the accuracy of the calculation. Moreover, we also prove the security of our scheme in the semi-honest model. Finally, experimental results validate that the prediction result of our SecDM is not only as accurate as the non-privacy-preserving scheme but also highly efficient.

Inspired by the recent success of sequence modeling in RL and the use of masked language model for pre-training, we propose a masked model for pre-training in RL, RePreM (Representation Pre-training with Masked Model), which trains the encoder combined with transformer blocks to predict the masked states or actions in a trajectory. RePreM is simple but effective compared to existing representation pre-training methods in RL. It avoids algorithmic sophistication (such as data augmentation or estimating multiple models) with sequence modeling and generates a representation that captures long-term dynamics well. Empirically, we demonstrate the effectiveness of RePreM in various tasks, including dynamic prediction, transfer learning, and sample-efficient RL with both value-based and actor-critic methods. Moreover, we show that RePreM scales well with dataset size, dataset quality, and the scale of the encoder, which indicates its potential towards big RL models.

Exploring user-item interaction cues is crucial for the performance of recommender systems. Explicit investigation of interaction cues is made possible by using graph-based models, where each user-item relationship is described by an edge, and the introduction of user-user social network. While existing graph-based recommendation methods use only a single-value edge to define the relationship between a pair of user and item, which limits the ability to represent complex user-item interactions. Furthermore, some social recommendation methods overlook the heterogeneous user behavior patterns in social and interaction relationships, resulting in the suboptimal performance of existing systems. In this paper, we propose a novel Social-aware Multi-dimensional Edge Feature-based Graph Representation Learning method, called SMEF. It represents all users and items as a graph and deep learns a multi-dimensional edge feature to explicitly describe the task-specific relationships of each user-item pair. Specifically, the proposed SMEF focuses on two distinct user behavior patterns toward social friends and interactive items, which explore the underlying heterogeneous relationship cues within them. This way, the learned multi-dimensional edge features encode user information from both social and interaction aspects. The proposed SMEF is a plug-and-play module that can be combined with different recommendation frameworks and Graph Neural Networks (GNNs) backbones to generate high quality user representations. The experimental results achieved on three publicly accessible datasets show that our SMEF-based method outperforms strong baselines.

With the exponential growth of mobile devices and the increasing demand for personalized and context-aware services, service-oriented applications play a crucial role in alleviating information overload and improving user experience. At the same time, Edge-Cloud Intelligence (ECI) provides a distributed computing paradigm that leverages the computational capabilities of edge servers to bring services closer to end-users, enabling low-latency and high-bandwidth data processing. The convergence of service applications and ECI has emerged as a promising way to enhance the efficiency and quality of service provisioning in today's dynamic and resource-constrained mobile environment. This call for papers invites researchers and practitioners to contribute to the exploration of the synergy between service applications and ECI infrastructure.

Automatic detection of Cyberbullying is a challenging task due to the availability of limited trained data, which is usually noisy and inherently multimodal. Transfer learning over pre-trained BERT-based language models has succeeded in various complex use cases like sequence-to-sequence translation and text classification. These methods mainly utilize transformer models to learn the word and sentence-level relationships. While they have demonstrated promising results, they only focus on textual features without taking contextual and structural information into account. Moreover, due to the data-heavy nature of BERT-based models, they may fail to model all the desired relationships if not adequate training data is provided to them during the fine-tuning process. In this paper, we propose a novel Session-level Contextualized Transformer-based architecture for Cyberbullying Detection (SECTR-CD), which can leverage transfer learning for modeling word-level attention while also being able to model sentence-level relationships in large bodies of text. The model is also capable of utilizing other contextual features from various modalities like images and social information. Our experimental results indicate remarkable improvement in the Cyberbullying detection task even in the presence of limited training samples.

Text summarization aims to condense text documents into a concise textual summary, which improves the efficiency of people in comprehending information. While deep learning-based summarization methods for individual documents have achieved good performance, there is an increasing demand for summarizing multiple related documents of a topic or event can yield a more coherent and succinct summary of the document set. However, the characteristics of multiple documents with more information, longer texts, and different styles impose new challenges to existing methods in dealing with the multi-aspect of a topic or an event. Therefore, in this paper, we propose a novel multi-granularity model with entity recognition for better sentence ranking and capturing the key information of different documents with a comprehensive and accurate summary. Specifically, we use PRIMERA as a token encoder based on the encoder-decoder framework. Then, a named entity recognition model is trained to identify key elements in documents such as people, location, organization, etc. The proposed model will focus more on these key elements. Based on the named entity recognition results, we further devise a sentence ranking module that allows the model to assign different weights to different sentences based on the sum of the frequencies of the entities contained in the sentences. Finally, based on the results of the multi-granularity encoding vector, the decoder can generate a comprehensive and accurate summary. To evaluate the performance of our proposed model, we conducted experiments on CoNLL2003, DUC2003, and DUC2004, which demonstrated the performance improvement of our proposed method over four previous models.

The pickup and delivery problem (PDP) is considered one of the key optimization problems. PDP is an NP-Hard problem; consequently, researchers tried to solve it using evolutionary algorithms. In literature, different variations of the problem have been studied using evolutionary algorithms. In this paper, we consider the many-objective variation of the PDP known as MaOPDP with six objectives as it is similar to real-life PDP. To solve the problem, we considered 15 different low-level heuristics (LLHs) divided between perturbation and local search phases and optimized the search between LLHs using a cross-domain technique known as Hyper-heuristics (HHs). To effectively solve MaOPDP, a q-learning-based HH named Reinforcement learning-based Selection Hyper-heuristic (RL_SHH) is proposed. According to our knowledge, the considered version of MaOPDP has not been optimized using HHs in the literature. A high-level selection criterion covering exploration and exploitation is proposed to choose between LLHs. To prove the effectiveness of our approach, benchmark data sets have been taken in small, medium, and large sizes and contrasted with state-of-the-art HHs and meta-heuristics. RL-SHH has produced significantly better results on 69 out of 72 instances while using Hypervolume (HV). Additionally, $\mu$ norm mean values (a cross-domain indicator) have been taken into consideration, and RL-SHH has dominated a state-of-the-art HH known as HH-ILS by 646.7% and 100% using HV and Additive Epsilon Indicator (AEI) respectively.

Anomaly detection is one of the crucial research topics in artificial intelligence, encompassing various fields such as health monitoring, network intrusion detection, and fraud detection in financial transactions. Deep anomaly detection (DAD) methods are considered as the effective approaches for addressing complex anomaly detection problems. Among them, the deep isolation forest methods have gained rapid development recently due to their simplicity in parameter turning and efficiency in model training. The existing deep isolation forest approaches are all based on representation learning, while OptiForest theoretically proves the crucial role of the tree structure in isolation forest based methods. In this paper, we analyse the search space of isolation trees under specific data instances and address the challenges in finding optimal isolation forest. Based on the theoretical underpinning and genetic algorithm, we design a deep model DOIForest with two mutation schemes and solution selection, which learns the optimal isolation forest and optimises the parameters in data partitioning. Extensive experiments on both synthetic dataset and a series of real-world datasets demonstrate that our approach can achieve better detection accuracy and robustness than the state-of-the-arts.

Edge computing has emerged as a transformative paradigm with applications ranging from IoT to smart homes and transportation systems. However, its decentralized nature presents significant challenges in securing sensitive data, particularly in scenarios involving data sharing. To address these issues, this paper introduces a secure data access control system for edge computing by leveraging blockchain to foster mutual trust among edge servers and employing attribute-based encryption for secure data sharing. Our proposed solution seeks to enhance data security in distributed environments. We validate our method through practical experiments conducted on multiple edge servers, confirming its effectiveness in safeguarding data integrity and privacy.

With the development of modern technology, the application of various types of devices in life has become more extensive, especially with the emergence of the Internet of Things (IoT), which makes a large number of devices to be connected to the network. However, while bringing convenience to life, attacks against IoT devices have also begun to appear and become one of the most concerned issues. These IoT devices produce and transmit data containing important user information every second. Attackers are targeting this characteristic to initiate further malicious attacks on these valuable data. In order to protect users from such attacks, it is important that threats can be detected and identified in time before they cause damage. To address this issue, this paper first reviewed the current state-of-the-art anomaly detection methods and based on the finding of uncovered areas of existing methods, this paper proposed a new anomaly detection framework leveraging the combination of Federated Learning and Isolation Forest. The framework performs tree construction on the clients’ end and further uploads the encrypted data containing the nodes’ information of the trees to the central server for the forest construction, after multiple interactions, the abnormal behaviour in the clients could be able to be identified more effectively and ultimately improved the accuracy of the detection results while protecting the privacy of the client data.

Generative Pre-trained Transformer (GPT) is a state-of-the-art machine learning model capable of generating human-like text through natural language processing (NLP). GPT is trained on massive amounts of text data and uses deep learning techniques to learn patterns and relationships within the data, enabling it to generate coherent and contextually appropriate text. This position paper proposes using GPT technology to generate new process models when/if needed. We introduce ProcessGPT as a new technology that has the potential to enhance decision-making in data-centric and knowledge-intensive processes. ProcessGPT can be designed by training a generative pre-trained transformer model on a large dataset of business process data. This model can then be fine-tuned on specific process domains and trained to generate process flows and make decisions based on context and user input. The model can be integrated with NLP and machine learning techniques to provide insights and recommendations for process improvement. Furthermore, the model can automate repetitive tasks and improve process efficiency while enabling knowledge workers to communicate analysis findings, support evidence, and make decisions. ProcessGPT can revolutionize business process management (BPM) by offering a powerful tool for process automation and improvement. Finally, we demonstrate how ProcessGPT can be a powerful tool for augmenting data engineers in maintaining data ecosystem processes within large bank organizations. Our scenario highlights the potential of this approach to improve efficiency, reduce costs, and enhance the quality of business operations through the automation of data-centric and knowledge-intensive processes. These results underscore the promise of ProcessGPT as a transformative technology for organizations looking to improve their process workflows.

In the current era of information overload, service recommendations have emerged as a valuable tool for enhancing the user experience. Among them, social recommendation models have shown promising results by incorporating social relationships to improve representation learning. However, most of these models lack fine-grained modeling of social user behavior, leading to a unified representation of users and a loss of expressiveness in user representations. To address this issue, we propose DisenHGCF, a new social recommendation approach based on disentangled hypergraph collaborative filtering, to disentangle the representations of users and items at the granularity of social users’ intents. This approach aims to provide a more nuanced understanding of the user, leading to more accurate and personalized recommendations. To be specific, DisenHGCF leverages hypergraphs to represent the complex relationships among users, friends, and items. By using the hypergraph disentangling module based on attention, it is able to disentangle the user’s intents and generate users representations in cooperating their intents for recommendation tasks. Additionally, a contrastive learning task based on intent-weight perturbation is designed to enhance representational learning. The experimental results obtained from the BeiBei and Beidian datasets demonstrate the superiority of our proposed approach in comparison to previous baseline methods, as evidenced by higher Recall and NDCG scores.

Anomaly detection plays an increasingly important role in various fields for critical tasks such as intrusion detection in cybersecurity, financial risk detection, and human health monitoring. A variety of anomaly detection methods have been proposed, and a category based on the isolation forest mechanism stands out due to its simplicity, effectiveness, and efficiency, e.g., iForest is often employed as a state-of-the-art detector for real deployment. While the majority of isolation forests use the binary structure, a framework LSHiForest has demonstrated that the multi-fork isolation tree structure can lead to better detection performance. However, there is no theoretical work answering the fundamentally and practically important question on the optimal tree structure for an isolation forest with respect to the branching factor. In this paper, we establish a theory on isolation efficiency to answer the question and determine the optimal branching factor for an isolation tree. Based on the theoretical underpinning, we design a practical optimal isolation forest OptIForest incorporating clustering based learning to hash which enables more information to be learned from data for better isolation quality. The rationale of our approach relies on a better bias-variance trade-off achieved by bias reduction in OptIForest. Extensive experiments on a series of benchmarking datasets for comparative and ablation studies demonstrate that our approach can efficiently and robustly achieve better detection performance in general than the state-of-the-arts including the deep learning based methods.

Summary Recommender systems are important applications in big data analytics because accurate recommendation items or high‐valued suggestions can bring high profit to both commercial companies and customers. To make precise recommendations, a recommender system often needs large and fine‐grained data for training. In the current big data era, data often exists in the form of isolated islands, and it is difficult to integrate the data scattered due to privacy security concerns. Moreover, privacy laws and regulations make it harder to share data. Therefore, designing a privacy‐preserving recommender system is of paramount importance. Existing privacy‐preserving recommender system models mainly adapt cryptography approaches to achieve privacy preservation. However, cryptography approaches have heavy overhead when performing encryption and decryption operations and they lack a good level of flexibility. In this paper, we conduct privacy analysis on the existing locality sensitive hashing (LSH) approach based privacy‐preserving recommender system and show how an attacker can retrieve user's information under such a recommender system. Given such privacy risks, we propose differentially private LSH approach to build recommender system that can offer differential privacy guarantees for users. Our proposed efficient and scalable federated recommender system can make full use of multiple source data from different data owners while guaranteeing privacy preservation of users' data in contributing parties. Extensive experiments on real‐world benchmark datasets show that our approach can achieve both high time efficiency and accuracy under small privacy budgets.

Digital-twin-enabled cloud-centric architecture is a promising evolution trend of sixth generation (6G) network, which brings new opportunities and challenges for mobile video streaming-related services requiring the exponentially increasing traffic demands. Device-to-Device (D2D) communication paradigm is an attractive technique to alleviate the problem. However, the previous research work on D2D built on individuals’ random mobility or position snapshot and cannot guarantee the stable communication flow. In this paper, we leverage the cybertwin as a centric controller and take advantages of crowdsourcing technology to attract mobile users to follow the specified path and share their network resources with other users. The design of the specified path is formulated as a problem of user recruitment optimization with cost constraint, which is a NP-Hard problem. Firstly, we investigate a special case of only one mobile user to offer the network resource and present a pseudo-polynomial time algorithm. Secondly, we present a graph-partition-based approach to solve the more complex case of multiple mobile users. Thirdly, we discuss the least expected budget to achieve the maximum utility in an ideal model. Fourthly, we perform extensive experiments to evaluate and compare the performance with the typical ones in simulated digital-twin-enabled 6G networks.

Lots of non-additive cost assignment methods designed for image steganography have improved the security of stego images, but surprisingly there are only a few such non-additive cost assignment methods for video steganography. In this paper, we first analyze the distortion propagation by decomposing it into inner-block, inter-block, and inter-frame distortion drifts. Then, we determine the inner-block distortion drift (caused by the embedding modifications) that induces the inter-block and the inter-frame distortion drifts, using prediction. Based on the findings, we compose a joint distortion for all transform coefficients in each transform block. Finally, we propose a joint distortion-based non-additive cost assignment (NACA) method to reduce the inner-block distortion drift by distortion compensation. This allows us to further reduce both intra-frame (inter-block) and inter-frame distortion drifts, and achieve enhanced security. We conduct extensive experiments to evaluate the performance of NACA, in terms of security and coding performance. The evaluation results demonstrate that NACA achieves improved security and visual stego video quality, and maintains a very marginal increase in bit-rate, in comparison to four other competing additive cost assignment approaches.

Although obstructive sleep apnea and hypopnea syndrome (OSAHS) is a common sleep disease, it is sometimes difficult to be detected in time because of the inconvenience of polysomnography (PSG) examination. Since snoring is one of the earliest symptoms of OSAHS, it can be used for early OSAHS prediction. With the recent development of wearable and IoT sensors, we proposed a deep learning-based accurate snore detection model for long-term home monitoring of snoring during sleep. To enhance the discriminability of features between snoring and non-snoring events, an auditory receptive field (ARF) net was proposed and integrated into the feature extraction network. Based on the feature maps derived by the feature extraction network, the detection model predicted a series of candidate boxes and corresponding confidence scores for each candidate box, which denoted whether the candidate box contained a snore event from the input sound waveforms. A snore detection dataset with a total duration of more than 4600 min was developed to evaluate the proposed model. The experimental results on this dataset revealed that the proposed model outperformed other traditional approaches and deep learning models.

Using Web APIs registered in service sharing communities for mobile APP development can not only reduce development period and cost, but also fully reuse state-of-the-art research outcomes in broad domain so as to ensure up-to-date APP development and applications. However, the big volume of available APIs in Web communities as well as their differences make it difficult for APIs selection considering compatibility, preferred partial APIs and expected APIs functions which are often of high variety. Accordingly, how to recommend a set of functional-satisfactory and compatibility-optimal APIs based on the APP developer's multiple function expectation and pre-chosen partial APIs is on demand as a significant challenge for successful APP development. To address this challenge, we first construct a Web APIs correlation graph that incorporates functional descriptions and compatibility information of Web APIs, and then propose a correlation graph-based approach for personalized and compatible Web APIs recommendation in mobile APP development. Finally, through extensive experiments on a real dataset crawled from Web APIs websites, we prove the feasibility of our proposed recommendation approach.

In the era of smart healthcare tremendous growth, plenty of smart devices facilitate cognitive computing for the purposes of lower cost, smarter diagnostic, etc. Android system has been widely used in the field of IoMT, and as the main operating system. However, Android malware is becoming one major security concern for healthcare, by the serious threat for our medical software assets, like the leakage of private information, the abusing of critical operations, etc. Unfortunately, the existing methods focus on building sustainable classification models, without fully considering system API which is the key to model aging. Compared to the traditional methods, we apply the lifeCycle of API as temporal metric. In addition to the temporal view, the “sizes” of the APPs are utilized as spatial metric in the spatial view. Based on this, we firstly discuss the temporal and spatial metrics together in terms of clustering, and then propose our novel framework-TSDroid. In this framework, we use TS-based clustering algorithm to obtain clustering subsets to enhance the detection capability. We have carried out an experimental verification on three existing excellent methods (i.e., Drebin, HinDroid, and DroidEvolver) and obtain good promotion effects by our framework.

We consider the problem of imitation learning from suboptimal demonstrations that aims to learn a better policy than demonstrators. Previous methods usually learn a reward function to encode the underlying intention of the demonstrators and use standard reinforcement learning to learn a policy based on this reward function. Such methods can fail to control the distribution shift between demonstrations and the learned policy since the learned reward function may not generalize well on out-of-distribution samples and can mislead the agent to highly uncertain states, resulting in degenerated performance. To address this limitation, we propose a novel algorithm called Outperforming demonstrators by Directly Extrapolating Demonstrations(ODED). Instead of learning a reward function, ODED trains an ensemble of extrapolation networks that generate extrapolated demonstrations, i.e., demonstrations that may be induced by a good agent, based on provided demonstrations. With these extrapolated demonstrations, we can use an off-the-shelf imitation learning algorithm to learn a good policy. Guided by extrapolated demonstrations, the learned policy avoids visiting highly uncertain states and therefore controls the distribution shift. Empirically, we show that ODED outperforms suboptimal demonstrators and achieves better performance than state-of-the-art imitation learning algorithms on the MuJoCo and DeepMind Control Suite tasks.

The skyrocketing market value of cryptocurrencies has prompted more investors to pour funds into cryptocurrencies to seek asset hedging. However, the anonymity of blockchain makes cryptocurrency naturally a tool of choice for criminals to commit smart contract scams. Consequently, smart contract scam detection is particularly critical for investors to avoid economic loss. Previous methods mainly leverage specific code logic of smart contracts and/or design rules based on abnormal transaction behaviors for scam detection. Although these methods gain success at detecting particular scams, they perform worse when applied to scams with highly similar codes. Besides, well-designed decision rules rely on expert knowledge and tedious data collection steps, which causes poor flexibility. To combat these challenges, we consider the problem of smart contract scam detection via mining topological features of account interaction information that dynamically evolves. We adopt interactive features extracted from dynamic interaction information of accounts and propose a framework named TTG-SCSD to utilize the features and Topological Data Analysis for smart contract scams detection. The TTG-SCSD constructs discrete dynamic interaction graphs for each contract and designs interactive features that characterize account behaviors. The features are modeled combined with a topology quantification mechanism to capture contract intentions in transactions. Experimental results on real-world transaction datasets from Ethereum show that TTG-SCSD obtains better generalizability and improves the performance of the bare versions of the comparison methods.

Recently, spoken dialogue systems have been widely deployed in a variety of applications, serving a huge number of end-users. A common issue is that the errors resulting from noisy utterances, semantic misunderstandings, or lack of knowledge make it hard for a real system to respond properly, possibly leading to an unsatisfactory user experience. To avoid such a case, we consider a proactive interaction mechanism where the system predicts the user satisfaction with the candidate response before giving it to the user. If the user is not likely to be satisfied according to the prediction, the system will ask the user a suitable question to determine the real intent of the user instead of providing the response directly. With such an interaction with the user, the system can give a better response to the user. Previous models that predict the user satisfaction are not applicable to DuerOS which is a large-scale commercial dialogue system. They are based on hand-crafted features and thus can hardly learn the complex patterns lying behind millions of conversations and temporal dependency in multiple turns of the conversation. Moreover, they are trained and evaluated on the benchmark datasets with adequate labels, which are expensive to obtain in a commercial dialogue system. To face these challenges, we propose a pipeline to predict the user satisfaction to help DuerOS decide whether to ask for clarification in each turn. Specifically, we propose to first generate a large number of weak labels and then train a transformer-based model to predict the user satisfaction with these weak labels. Moreover, we propose a metric, contextual user satisfaction, to evaluate the experience under the proactive interaction mechanism. At last, we deploy and evaluate our model on DuerOS, and observe a 19% relative improvement on the accuracy of user satisfaction prediction and 2.3% relative improvement on user experience.

Artificial intelligence (AI) enables machines to learn from human experience, adjust to new inputs, and perform intelligent tasks without human intervention. AI is progressing rapidly and is transforming the way businesses operate, from process automation to cognitive augmentation of tasks and intelligent process/data analytics. However, the main challenge for the AI system users is to comprehend and trust the result of AI algorithms and methods. To address this challenge, we first study the recent techniques in the area of eXplainable Artificial Intelligence (XAI). Then, we introduce a novel XAI process to facilitate producing explainable models while maintaining a high level of learning performance. We present an interactive evidence-based approach to assist the users in comprehending and trusting the results and outputs generated by AI-enabled algorithms, resulting in developing a digital dashboard to facilitate inter-acting with the algorithm. Lastly, we discuss how the proposed XAI method can significantly improve the confidence of data scientists in understanding the result of AI-enabled algorithms with an application in the banking domain for analyzing customer transactions.

Mental health disorders may cause severe consequences for countries’ economies and health. Identifying early signs of these disorders is vital. The state-of-the-art research in identifying mental health disorder patterns from textual data, uses hand-labeled training sets, especially when a domain expert’s knowledge is required to analyze various symptoms in a patient. This task could be time-consuming and expensive. To address this challenge, in this paper, we study and analyze the various clinical and non-clinical approaches to identifying mental health disorders. We leverage the domain knowledge and expertise in cognitive science to build a domain-specific Knowledge Base for the mental health disorder concepts and patterns. We present a weaker form of supervision by facilitating and generating training data from a domain-specific Knowledge Base. We adopt a typical scenario for analyzing social media to identify depression symptoms from the textual content generated by social users.

Social trust relationship prediction targets using attributes to quantify the interrelationships in trust between users. Most of the existing algorithms do not consider the heterogeneity and semantics of information included in online social networks, leading to low adaptability in capturing user preferences. What’s more, they only focus on directly connected nodes, and treat all the information propagation paths equally, leading to the lack of structure context information. Given the incomplete graph structure on online social networks constructed by existing algorithms, they can hardly have good performance in the trust prediction. In order to solve the above-mentioned problems, we propose a novel Attention-aware Multi-hop Trust Inference (AMTI) model which could capture different features on both nodes and paths adaptively based on the complex contexts and take multi-hop neighbors into account. Specifically, in our model, we construct a heterogeneous graph of three types of nodes: User, Interest, and Relationship as well as two different meta-paths: User-Interest-User, and User-Relative-User. Then, we adopt a two-level attention mechanism to obtain the attention value on both the node level and path level. To incorporate the multi-hop neighbors’ information, we develop a 2-hop attention diffusion to aggregate the information from the indirectly connected nodes. The experimental results on real-world datasets have demonstrated that AMTI outperforms the state-of-the-art methods in terms of the accuracy of social trust prediction.

We consider an offline reinforcement learning (RL) setting where the agent needs to learn from a dataset collected by rolling out multiple behavior policies. There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies. Previous methods fail to handle this by only controlling the global trade-off. 2) For a given state, the action distribution generated by different behavior policies may have multiple modes. The BC regularizers in many previous methods are mean-seeking, resulting in policies that select out-of-distribution (OOD) actions in the middle of the modes. In this paper, we address both challenges by using adaptively weighted reverse Kullback-Leibler (KL) divergence as the BC regularizer based on the TD3 algorithm. Our method not only trades off the RL and BC signals with per-state weights (i.e., strong BC regularization on the states with narrow action coverage, and vice versa) but also avoids selecting OOD actions thanks to the mode-seeking property of reverse KL. Empirically, our algorithm can outperform existing offline RL algorithms in the MuJoCo locomotion tasks with the standard D4RL datasets as well as the mixed datasets that combine the standard datasets.

With the great success of deep neural networks (DNNs) in a variety of fields, deep learning gains a pioneering development in anomaly detection. Although deep learning achieves good accuracy in anomaly detection, it is troubled with long execution time and high memory consumption. These problems are associated with the inherent drawbacks of deep learning, such as too many parameters and deep training layers. To remedy the above drawbacks, we try to explore an unsupervised non-neural network deep model for anomaly detection based on the experience of the deep forest. In this paper, we propose a deep anomaly detection framework with hashing based isolation forest (DeepiForest) to achieve effective and robust anomaly detection. Specifically, DeepiForest utilizes hashing based isolation forest and tree-embedding scheme to provide enhanced features and apply multi-layer cascaded architecture to establish a deep framework. DeepiForest inherits the advantages of deep forests, i.e., the framework holds fewer hyper-parameters and smaller model complexity than DNNs, simultaneously producing robust accuracy on anomaly detection. Extensive experiments on different-scale datasets illustrate the efficiency of DeepiForest and its comparable effectiveness to the state-of-the-art deep anomaly detection (DAD) methods.

The Intelligent Meteorological System (IMS) with cloud computing (CC) provides users with various meteorological services, but the long-distance communication of CC often brings high latency, which makes the IMS perform poorly in the series of real-time services for meteorological emergency decision-making. Considering the shortcomings of CC, edge computing is adopted to the IMS to process most service requests. In the IMS with cloud-edge computing, the commonly used contents of services is cached on edge servers (ESs) to reduce resource scheduling, thus avoiding high time costs. Due to the storage and computing resource limitations of ESs, the massive types of services and the changing service requests, how to determine the caching contents is still a challenge. In this paper, a service caching scheme based on deep reinforcement learning, named SCDR, is proposed. Specifically, a service caching framework for IMS with cloud-edge computing is designed. Then, the distributed distributional deep deterministic policy gradient (D4PG) is leveraged to realize the optimization of the service caching strategy with the highest service coverage rate and low processing latency. Besides, the performance of the generated caching strategy is evaluated through simulation experiments.

Recently issued data privacy regulations like GDPR (General Data Protection Regulation) grant individuals the right to be forgotten. In the context of machine learning, this requires a model to forget about a training data sample if requested by the data owner (i.e., machine unlearning). As an essential step prior to machine unlearning, it is still a challenge for a data owner to tell whether or not her data have been used by an unauthorized party to train a machine learning model. Membership inference is a recently emerging technique to identify whether a data sample was used to train a target model, and seems to be a promising solution to this challenge. However, straightforward adoption of existing membership inference approaches fails to address the challenge effectively due to being originally designed for attacking membership privacy and suffering from several severe limitations such as low inference accuracy on well-generalized models. In this paper, we propose a novel membership inference approach inspired by the backdoor technology to address the said challenge. Specifically, our approach of Membership Inference via Backdooring (MIB) leverages the key observation that a backdoored model behaves very differently from a clean model when predicting on deliberately marked samples created by a data owner. Appealingly, MIB requires data owners' marking a small number of samples for membership inference and only black-box access to the target model, with theoretical guarantees for inference results. We perform extensive experiments on various datasets and deep neural network architectures, and the results validate the efficacy of our approach, e.g., marking only 0.1% of the training dataset is practically sufficient for effective membership inference.

[J1C2 Presentation Abstract at IEEE SERVICES 2022 for IEEE Transactions on Services Computing DOI 10.1109/TSC.2022.3142265]

With the ever-increasing popularity of microservice architecture, a considerable number of enterprises or organizations have encapsulated their complex business services into various lightweight functions as published them accessible APIs (Application Programming Interfaces). Through keyword search, a software developer could select a set of APIs from a massive number of candidates to implement the functions of a complex mashup, which reduces the development cost significantly. However, traditional keyword search methods for APIs often suffer from several critical issues such as functional compatibility and limited diversity in search results, which may lead to mashup creation failures and lower development productivity. To deal with these challenges, this paper designs DAWAR, a diversity-aware Web APIs recommendation approach that finds diversified and compatible APIs for mashup creation. Specifically, the APIs recommendation problem for mashup creating is modelled as a graph search problem that aims to find the minimal group Steiner trees in a correlation graph of APIs. DAWAR innovatively employs the determinantal point processes to diversify the recommended results. Empirical evaluation is performed on commonly-used real-world datasets, and the statistic results show that DAWAR is able to achieve significant improvements in terms of recommendation diversity, accuracy, and compatibility.

The widespread use of mobile devices propels the development of new-fashioned video applications like 3D (3-Dimensional) stereo video and mobile cloud game via web or App, exerting more pressure on current mobile access network. To address this challenge, we adopt the crowdsourcing paradigm to offer some incentive for guiding the movement of recruited crowdsourcing users and facilitate the optimization of the movement control decision. In this paper, based on a practical 4G (4th-Generation) network throughput measurement study, we formulate the movement control decision as a cost-constrained user recruitment optimization problem. Considering the intractable complexity of this problem, we focus first on a single crowdsourcing user case and propose a pseudo-polynomial time complexity optimal solution. Then, we apply this solution to solve the more general problem of multiple users and propose a graph-partition-based algorithm. Extensive experiments show that our solutions can improve the efficiency of real-time D2D communication for mobile videos.

The Corona Virus Disease 2019 has a great impact on public health and public psychology. People stay at home for a long time and rarely go out. With the improvement of the epidemic situation, people began to go to different places to check in. To maintain public mental health, it is necessary to propose a point-of-interest (POI) prediction model which can mine users' interests. However, the current techniques suffer from lower precision during prediction and the practical value is poor, which is due to the sparse data of users' check-in. Faced with this challenge, we propose an attention-based bidirectional gated recurrent unit (GRU) model for POI category prediction (ABG_poic). We regard the user's POI category as the user's interest preference because the fuzzy POI category is easier to reflect the user's interest than the POI. This method can alleviate the data sparsity, and protect users' location privacy. Since users' preferences are variable, we utilize a bidirectional GRU to capture the dynamic dependence of users' check-ins. Furthermore, since the neural network is similar to a “black box” in feature learning, the decision-making stage is opaque. Thus, we combine the attention mechanism with bidirectional GRU to selectively focus on historical check-in records, which can improve the interpretability of the model. Considering the time impact on users' check-in, we utilize the time sliding window in the ABG_poic model. Experiments on two data sets demonstrate that our ABG_poic outperforms the comparison models for POI category prediction on sparse check-in data.

The ever-increasing popularity of web APIs allows app developers to leverage a set of existing web APIs to achieve their sophisticated objectives. The heavily fragmented distribution of web APIs makes it challenging for an app developer to find appropriate and compatible web APIs. Currently, app developers usually have to manually discover candidate web APIs, verify their compatibility and select appropriate and compatible ones. This process is cumbersome and requires detailed knowledge of web APIs which is often too demanding. It has become a major obstacle to further and broader applications of web APIs. To address this issue, we first propose a web API correlation graph built on extensive data about the compatibility between web APIs. Then, we propose WAR (WebAPIsRecommendation), the first data-driven approach for web APIs recommendation that integrates web API discovery, verification and selection operations based on keywords search over the web API correlation graph. WAR assists app developers without detailed knowledge of web APIs in searching for appropriate and compatible web APIs by typing a few keywords that represent the tasks required to achieve app developers’ objectives. WAR can significantly save app developers’ time and effort in searching for web APIs. We conducted large-scale experiments on 18,478 real-world web APIs and 6,146 real-world apps to demonstrate the usefulness and efficiency of WAR.

Scalable data processing platforms built on cloud computing becomes increasingly attractive as infrastructure for supporting big data applications. But privacy concerns are one of the major obstacles to making use of public cloud platforms. Multidimensional anonymisation, a global-recoding generalisation scheme for privacy-preserving data publishing, has been a recent focus due to its capability of balancing data obfuscation and usability. Existing multidimensional anonymisation methods suffer from scalability problems when handling big data due to the impractical serial I/O cost. Given the recursive feature of multidimensional anonymisation, parallelisation is an ideal solution to scalability issues. However, it is still a challenge to use existing distributed and parallel paradigms directly for recursive computation. In this paper, we propose a scalable approach for big data multidimensional anonymisation based on MapReduce, a state-of-the-art data processing paradigm. Our basic idea is to partition a data set recursively into smaller partitions using MapReduce until all partitions can fit in the memory of a computing node. A tree indexing structure is proposed to achieve recursive computation. Moreover, we show the applicability of our approach to differential privacy. Experimental results on real-life data demonstrate that our approach can significantly improve the scalability of multidimensional anonymisation over existing methods.

Cost assignment plays a key role in coding performance and security of video steganography. Existing cost assignment methods (for adaptive video steganography) are designed for specific transform coefficients rather than all transform coefficients. In addition, existing video steganographic frameworks do not allow Syndrome-Trellis Codes (STCs) to modify all transform coefficients in both intra-coded and inter-coded frames at the same time. To address these limitations, in this article, we first propose a novel video steganographic framework. Then, we give a theoretical analysis of distortion drift in both intra- and inter-coding procedures. Based on the analysis, we design a Distortion Drift-Based Cost Assignment method, hereafter referred to as DDCA. DDCA considers the inner-block, inter-block and inter-frame distortion costs in order to improve the coding performance and the security of stego videos when the embedding payload is fixed. We conducted extensive experiments using two video datasets to evaluate the proposed video steganographic framework and DDCA, in terms of the coding performance and the security. Our experiments show that the proposed framework outperforms three recent state-of-the-art methods, for example the coding performance and the security of stego videos can benefit from DDCA by making full use of all nonzero transform coefficients.

Due to resource constraints and working surroundings, many IIoT nodes are easily hacked and turn into zombies from which to launch attacks. It is challenging to detect such networked zombies rooted behind the Internet for any individual defender. In this article, we combine federated learning (FL) and fog/edge computing to combat malicious codes. Our protocol trains a global optimized model based on distributed datasets of collaborators while removing the data and communication constraints. The FL-based detection protocol maximizes the values of distributed data samples, resulting in an accurate model timely. On top of the protocol, we place mitigation intelligence in a distributed and collaborative manner. Our approach improves accuracy, eliminates mitigation time, and enlarges attackers’ expense within a defense alliance. Comprehensive evaluations confirm that the cost incurred is 2.7 times larger, the mitigation response time is 72% lower, and the accuracy is 47% higher on average. Besides, the protocol evaluation shows the detection accuracy is approximately 98% in the FL, which is almost the same as centralized training.

Through the collaboration of cloud and edge, cloud-edge computing allows the edge that approximates end-users undertakes those non-computationally intensive service processing of the cloud, reducing the communication overhead and satisfying the low latency requirement of Internet of Vehicle (IoV). With cloud-edge computing, the computing tasks in IoV is able to be delivered to the edge servers (ESs) instead of the cloud and rely on the deployed services of ESs for a series of processing. Due to the storage and computing resource limits of ESs, how to dynamically deploy partial services to the edge is still a puzzle. Moreover, the decision of service deployment often requires the transmission of local service requests from ESs to the cloud, which increases the risk of privacy leakage. In this article, a method for privacy-aware IoV service deployment with federated learning in cloud-edge computing, named PSDF, is proposed. Technically, federated learning secures the distributed training of deployment decision network on each ES by the exchange and aggregation of model weights, avoiding the original data transmission. Meanwhile, homomorphic encryption is adopted for the uploaded weights before the model aggregation on the cloud. Besides, a service deployment scheme based on deep deterministic policy gradient is proposed. Eventually, the performance of PSDF is evaluated by massive experiments.

Currently, the world is experiencing the rapid spread of Coronavirus Disease 2019 (COVID-19). Since the epidemic continues to take a devastating impact on the society, economy, and healthcare, the real-time detection of COVID-19 is essential for fast and cost-effective diagnosis services. Fortunately, deep learning (DL), as a promising technology, enables the COVID-19 diagnosis services on chest X-ray (CXR) images. The training task of DL model is generally implemented at the centralized cloud. However, due to the geo-distributed data sources and the transmission of large amounts of raw data to the centralized cloud, the transmission latency becomes a bottleneck of the COVID-19 diagnosis model training. In this paper, we propose aDistributedCOVID-19 detection model training method on CXR images with edge-cloud collaboration, named DisCOV. Specifically, to improve the training efficiency and guarantee the model accuracy, a distributed lightweight model-based training algorithm is designed with the cooperation of edge computing and cloud computing. In addition, a resource allocation algorithm is developed during the training to jointly minimize the time cost and energy consumption. Extensive experiments based on real-world CXR image datasets demonstrate that DisCOV is better performed and more promising than the existing baselines.

Abstract Anomaly detection plays a crucial role in many Internet of Things (IoT) applications such as traffic anomaly detection for smart transportation and medical diagnosis for smart healthcare. With the explosion of IoT data, anomaly detection on data streams raises higher requirements for real-time response and strong robustness on large-scale data arriving at the same time and various application fields. However, existing methods are either slow or application-specific. Inspired by the edge computing and generic anomaly detection technique, we propose an isolation forest based framework with dynamic Insertion and Deletion schemes (IDForest), which can incrementally update the forest to detect anomalies on data streams. Besides, IDForest is deployed on edge servers in parallel through packing each tree into a subtask, which facilitates the fast anomaly detection on data streams. Extensive experiments on both synthetic and real-life datasets demonstrate the efficiency and robustness of our framework for anomaly detection.

With the number of users in crowdsourcing increasing rapidly, task matching service is attracting more and more attention. However, it also causes many security concerns, one of which is the leakage of sensitive information. Privacy-preserving task matching techniques can protect the private information of task requesters and workers. Whereas existing privacy-preserving task matching schemes are constructed on a central server, and thereby they may suffer from potential wrongdoings of a malicious server. In addition, most of them only provide accurate task matching, which means that they cannot tolerate keyword spelling errors, leading to the decline of task matching accuracy. In this paper, we propose a Reliable and Privacy-preserving Task Matching scheme (RPTM) for crowdsourcing. To guarantee the reliability of task matching results, RPTM employs smart contracts to ensure that operations of RPTM are faithfully performed. However, it may still disclose the privacy of users due to the transparency of the blockchain. In order to deal with this problem, RPTM can perform task matching service without compromising the privacy of task requesters and workers by leveraging a novel integer vector encryption scheme. Moreover, RPTM supports multi-keyword fuzzy matching by exploiting locality sensitive hashing and Bloom filter, which can tolerate keyword spelling errors and different expression formats. Extensive analysis and experiments based on a test net of EOS show that RPTM is efficient and secure.

While being a lasting theme, privacy, security, and trust (PST) has been increasingly important in recent days due to the pervasive (but more prone) computation infrastructure and deep (but more intrusive) data analytics, and has been hugely demanded from governments, companies, and individuals. This workshop aims at providing a forum for researchers, practitioners and developers from different background areas such as computational intelligence, data privacy and cyber security, trust management, cloud computing, edge computing, Internet of Things, big data analytics, machine learning and data mining, knowledge discovery to exchange the latest experience, research ideas and synergic research and development on fundamental issues and applications about privacy, security and trust issues in computational intelligence.

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership inference attacks (MIAs) that can distinguish the training members of the given model from the non-members. However, existing MIAs ignore the source of a training member, i.e., the information of the client owning the training member, while it is essential to explore source privacy in FL beyond membership privacy of examples from all clients. The leakage of source information can lead to severe privacy issues. For example, identification of the hospital contributing to the training of an FL model for the COVID-19 pandemic can render the owner of a data record from this hospital more prone to discrimination if the hospital is in a high risk region. In this paper, we propose a new inference attack called source inference attack (SIA), which can derive an optimal estimation of the source of a training member. Specifically, we innovatively adopt the Bayesian perspective to demonstrate that an honest-but-curious server can launch an SIA to steal non-trivial source information of the training members without violating the FL protocol. The server leverages the prediction loss of local models on the training members to achieve the attack effectively and non-intrusively. We conduct extensive experiments on one synthetic and five real datasets to evaluate the key factors in an SIA, and the results show the efficacy of the proposed source inference attack.

With the development of the vehicular network (VN), emerging driver assistance applications are adhibited in daily life. Commonly, edge computing is adopted to satisfy the timeliness requirements of these applications, as the vehicular devices are usually insufficient in computation resources. Nevertheless, the increasing volume of service requests (SRs) are potential to overload the edge servers (ESs), thus increasing the task execution time. Besides, the randomness and the diversity of the SRs also challenge the dynamic resource allocation for the users. To deal with these challenges, a task offloading and resource allocation scheme based on game theory and reinforcement learning (RL) named TORA is proposed. Specifically, game theory is leveraged to determine the optimal task offloading strategy for improving the quality of service (QoS). Meanwhile, RL is applied to implement the dynamic resource allocation of the ES. Finally, the robust performance of the proposed method is validated by comparative experiments.

With the powerful computing capability, cloud computing (CC) is employed to accommodate services execution for the Internet of vehicles (IoV), but the long-distance communication of CC often brings high latency. Considering the shortcomings of CC, edge computing (EC) shifts service execution to the edge, which decreases the execution delay. Due to the storage and computing resource limits of edge servers (ESs), how to dynamically deploy partial services to the edge is still a puzzle. Moreover, the single resource-constrained ES is more vulnerable to attacks, which increases the leakage risk of vehicle privacy. In this article, a method for intelligent IoV service deployment and execution with privacy preservation in cloud-edge computing, named GoDeep, is proposed. Specifically, homomorphic encryption is adopted to construct a privacy-aware mechanism for IoV service execution. Besides, a service deployment scheme based on deep deterministic policy gradient (DDPG) is proposed. Eventually, the performance of GoDeep is evaluated by the simulation experiments.

Membership inference attacks on a machine learning model aim to determine whether a given data record is a member of the training set. They pose severe privacy risks to individuals, e.g., identifying an individual's participation in a hospital's health analytic training set reveals that this individual was once a patient in that hospital. Adversarial regularization (AR) is one of the state-of-the-art defense methods that mitigate such attacks while preserving a model's prediction accuracy. AR adds membership inference attacks as a new regularization term to the target model during the training process. It is an adversarial training algorithm that is trained on a defended model which is essentially the same as training the generator of generative adversarial networks (GANs). We observe that many GAN variants are able to generate higher quality samples and offer more stability during the training phase than GANs. However, whether these GAN variants are available to improve the effectiveness of AR has not been investigated. In this paper, we propose an enhanced adversarial regularization (EAR) method based on Least Square GANs (LSGANs). The new EAR surpasses the existing AR in offering more powerful defensive ability while preserving the same prediction accuracy of the protected classifiers. We systematically evaluate EAR on five datasets with different target classifiers under four different attack methods and compare it with four other defense methods. We experimentally show that our new method performs the best among other defense methods.

Model inference is the final stage in machine/deep learning application deployments in practical applications. Hardware-implemented or accelerated model inferences find significant attractions as they offer faster inference than those implemented as programs. This is especially attractive for real-time applications. In this paper, we address models that serve for parking occupancy prediction based on historical time-series parking records. We use the Keras library to build and train software DNN and LSTM models, then compare their prediction performances in terms of accuracy. While the software-implemented inference models indicate advantages of LSTM, we still opted to select only DNN-based models for additional hardware acceleration as the current advanced tool-chains leveraged for automatic software-to-hardware model converting do not allow the creation of LSTM hardware- implemented models. We create, explore and compare the inference performances of hardware (FPGA)-implemented models on relatively low-cost FPGAs. For this, we create an FPGA-accelerated Fog-layer cluster by adding two additional Xilinx FPGA boards of different performances into our existing cluster of four Raspberry Pi (RPi) computers.

Summary With an increasing number of public WiFi hotspots have been constructed in metropolitan areas, citizens can leverage these WiFi hotspots to surf the Internet with their smart devices almost everywhere. Compared to cellular networks, most people prefer using WiFi because this can not only save money by reducing the cellular data traffic but also save energy to prolong the battery lifetime of mobile devices. Mobile offloading techniques give the opportunity for smart devices to offload cellular data traffic to WiFi networks whenever they are connected WiFi networks. Although offloading to WiFi networks can cause communication delay, many delay‐tolerant applications still prefer doing so in order to save the cellular data traffic. Existing offloading approaches only take the application delay tolerance into consideration and therefore easy to induce some tasks missing deadlines. In this paper, we propose a novel WiFi‐aware method for mobile data offloading through WiFi networks with deadline constraints. Specifically, it takes the WiFi distribution in city areas into consideration while making offloading decision. The simulation results on real‐world data have shown that our method improves the percentage of tasks that can meet their deadlines, and reduces the average task completion time by comparing with other outstanding methods.

With the continuous accumulation of users' check-in data, we can gradually capture users' behavior patterns and mine users' preferences. Based on this, the next point-of-interest (POI) recommendation has attracted considerable attention. Its main purpose is to simulate users' behavior habits of check-in behavior. Then, different types of context information are used to construct a personalized recommendation model. However, the users' check-in data are extremely sparse, which leads to low performance in personalized model training using recurrent neural network. Therefore, we propose a category-aware gated recurrent unit (GRU) model to mitigate the negative impact of sparse check-in data, capture long-range dependence between user check-ins and get better recommendation results of POI category. We combine the spatiotemporal information of check-in data and take the POI category as users' preference to train the model. Also, we develop an attention-based category-aware GRU (ATCA-GRU) model for the next POI category recommendation. The ATCA-GRU model can selectively utilize the attention mechanism to pay attention to the relevant historical check-in trajectories in the check-in sequence. We evaluate ATCA-GRU using a real-world data set, named Foursquare. The experimental results indicate that our ATCA-GRU model outperforms the existing similar methods for next POI recommendation.

In this article, we propose a comprehensive multilayer (IoT-device, edge, fog, and cloud) streaming analytics platform with two-tier fog layer, which comprises streaming and analytics tiers. The approach, functionally validated on a testbed of clusters of low-cost off-the-shelf components, demonstrates that both real-time streaming processing and large-scale data analytics are feasible, with even completely avoiding the use of cloud layer. The fog layer uses advanced streaming and analytics paradigms, such as Apache Kafka, Apache Spark, and Hadoop, to support the effective development of applications that use streaming, long-term data storage and analytics. As such, the platform is suitable for and is affordable for “private” users. Furthermore, we add to the platform intelligent edge layer that abstracts and can simulate the operation of the IoT-device layer in real time or can be directly connected to the IoT-device layer. The experiments on a real-life IoT-based smart parking application show that our two-tier approach is cost effective and scalable, and can handle simultaneously streaming processing and analytics tasks successfully.

The concepts of sequential pattern mining have become a growing topic in data mining, finding a home most recently in the Internet of Things (IoT) where large volumes of data are presented by the second for analysis and knowledge extraction. One key topic within the realm of sequential pattern mining in high-utility sequential pattern mining (HUSPM), short form for high-utility sequential pattern mining. HUSPM takes into account the fusion of utility and sequence factors to assist in the determination of sequential patterns of high utility from databases and data sources. That being said, almost all current existing literature focus on only using a single machine to increase mining performance. In this work, we present a four-stage MapReduce framework that is solely based on the well-known Spark platform for use in HUSPM. This framework is shown to create a more efficient and faster mining performance for dealing with large data sets. It consists of four phases such as initialization, mining, updating, and generation phases to handle the big data sets based on the MapReduce framework running on the Spark platform. Experiments indicated that the designed model is capable of handling the very big data sets while state-of-the-art algorithms can only achieve good performance in small data sets.

Summary Edge computing (EC) emerges as a novel computing paradigm to offload computing tasks from user equipments (UEs) to edge notes (ENs) in fifth‐generation networks, which definitely breaks the resource limitation of UEs to a certain degree. However, it is troublesome to guarantee the overall operating performance of ENs due to the uneven distributed resource demands of UEs, the resulting transmission delay and the data loss for computation offloading between the covered EN and the deployed destination EN. In view of this challenge, a blockchain‐based computation offloading method, named BCO, is proposed in this paper. Technically, since blockchain is a promising technique for the decentralized system, a blockchain‐based EC framework is designed to degrade the data loss possibility by integrating blockchain and EC. Then, the nondominated sorting genetic algorithm, the third version (NSGA‐III), is leveraged to acquire the balanced offloading strategies. Furthermore, by taking advantage of Simple Additive Weighting and Multiple Criteria Decision Making, the optimal offloading strategy is identified. Finally, systematic experiments and analyses on the comparative experiment are conducted to verify the efficiency of our proposed method BCO.

Summary Currently, smart farming has been established to realize agriculture automation by leveraging sensors to gather the growth and environmental data for crops, and realizing multiple intelligent controls, such as irrigation, fertilization, and so on, to increase the crop yields. To support real‐time intelligent controls, edge computing is introduced to smart farming by endowing computing and storage capacities to edge devices nearby the geographically distributed sensors. However, the farmers are relatively willing to purchase and deploy a small quantity of edge servers (ESs) in the farm from the perspective of expenditure saving, thereby leading to a key challenge to guarantee the performance of the real‐time controls and the overall edge services. In view of this challenge, a service offloading‐oriented ES placement method for supporting smart farming, called SOP, is proposed to optimize the data transmission delay from sensors to ESs and the load balance among ESs. More precisely, the corresponding service range of a certain ES is ascertained according to the specific analysis of the farming service requirements. Subsequently, the layout policies for the trade‐offs of the ES performance and service efficiency are acquired. Then the most balanced policy is determined as the final ES placement strategy. Eventually, we evaluate the performance of the whole ES system and the service execution efficiency with SOP.

With the ever-increasing maturity and popularization of the Internet of Things (IoT), tremendous business applications developed by distinct enterprises or organizations have been encapsulated into lightweight web services that can easily be accessed or invoked remotely. However, the big volume of candidate web services places a heavy burden on the users' service selection decision-making process. Under the circumstance, a variety of intelligent recommendation solutions have been developed to reduce the high decision-making cost. Traditional resolutions usually challenge in two aspects. First, the recommendation parameters, i.e., the quality of services (QoS), usually relies on user/service location heavily; therefore, low-quality recommended results may be returned to users if user/service location information is overlooked. Second, historical QoS data often contain partial sensitive information of users; therefore, it becomes a necessity to protect the sensitive QoS data while making accurate recommendation decisions. To tackle the above challenges, we introduce the concepts of user/service location information and locality-sensitive hashing (LSH) in the domain and propose a location-aware recommendation approach with privacy-preservation capability. A wide range of experiments is set up based on the popular WS-DREAM data set, whose results prove the effectiveness and efficiency of our approach.

As one of the most successful recommendation techniques, neighborhood-based collaborative filtering (CF), which recommends appropriate items to a target user by identifying similar users or similar items, has been widely applied to various recommender systems. Although many neighbor-based CF methods have been put forward, there are still some open issues that have remained unsolved. First, the ever-increasing volume of user–item rating data decreases the recommendation efficiency significantly as a recommender system needs to analyze all the rating data when searching for similar neighbors or similar items. In this situation, users’ requirements on quick response may not be met. Second, in neighbor-based CF methods, more attention is paid to the recommendation accuracy while other key indicators of recommendation performances are often ignored, i.e., recommendation diversity (RD), which probably produces similar or redundant items in the recommended list and decreases users’ satisfaction. Considering these issues, a diversified and scalable recommendation method (called DR_LT) based on locality-sensitive hashing and cover tree is proposed in this article, where the item topic information is used to optimize the final recommended list. We show the effectiveness of our proposed method through a set of experiments on MovieLens data set that clearly shows the feasibility of our proposal in terms of item recommendation accuracy, diversity, and scalability.

The industrial control and automation systems have played an increasingly important role in critical manufacturing processes. In such systems, many Internet of Things devices continuously collect large number of streaming data for real-time processing. Verifiable data streaming (VDS) addresses such authenticity issue for streaming data, but most VDS schemes are not efficient and lightweight, do not support range querying, and cannot be used in practice. To improve the efficiency and achieve a verifiable range query in data streaming, we present here a new primitive, namely, a chameleon authentication tree with prefixes (PCAT), which is extended from the PBTree and chameleon authentication tree. Our scheme is not only lightweight but also supports dynamic expansion and verifiable range query in data streaming, making it more suitable for resource-constrained devices. We separate the PCAT's algorithms into the following phases: initialization, data appending, query, and verification. Our analyses prove that the PCAT satisfies all the security requirements of VDS. Moreover, an efficiency analysis and performance evaluation demonstrate that our scheme not only supports lightweight data streaming authentication but also has high efficiency, which means that the PCAT is easier to apply in the industrial control and automation systems.

As one of the cyber–physical–social systems that plays a key role in people's daily activities, a smart city is producing a considerable amount of industrial data associated with transportation, healthcare, business, social activities, and so on. Effectively and efficiently fusing and mining such data from multiple sources can contribute much to the development and improvements of various smart city applications. However, the industrial data collected from the smart city are often sensitive and contain partial user privacy such as spatial–temporal context information. Therefore, it is becoming a necessity to secure user privacy hidden in the smart city data before these data are integrated together for further mining, analyses, and prediction. However, due to the inherent tradeoff between data privacy and data availability, it is often a challenging task to protect users’ context privacy while guaranteeing accurate data analysis and prediction results after data fusion. Considering this challenge, a novel privacy-aware data fusion and prediction approach for the smart city industrial environment is put forward in this article, which is based on the classic locality-sensitive hashing technique. At last, our proposal is evaluated by a set of experiments based on a real-world dataset. Experimental results show better prediction performances of our approach compared to other competitive ones.

N/A

Currently, Edge computing (EC) paradigm is adopted to provision the low-latency resources for the massive real-time services in Internet of vehicles (IoV). To alleviate the QoE (Quality of Experience) degradation of the vehicular users due to the uncertainties (e.g., resource conflicts and communicating interruption), software-defined network (SDN) is involved in the EC-enabled IoV to manage the cooperative operation of distributed edge nodes (ENs). However, the increasing privacy leakage for the IoV service offloading causes the disclosure of the sensitive information, including driving location, personal information of the driver, etc. Moreover, the regulation of SDN is practically insufficient, as the general control is incompetent to maintain balanced operation with the premise of efficient service utility. In view of these challenges, a secure service offloading method, named SOME, is designed to promote IoV service utility and edge utility, meanwhile ensuring privacy security, in SDN-enabled EC. Specifically, an SDN-based framework for IoV service management is developed to address the inherent uncertainty of edge network by SDN controllers. Besides, the locality-sensitive-hash (LSH) is leveraged to realize utility- and privacy-aware service selection. Eventually, comparative experiments are implemented to verify the effectiveness of SOME.

With the ever-increasing prosperity of web Application Programming Interface (API) sharing platforms, it is becoming an economic and efficient way for software developers to design their interested mashups through web API re-use. Generally, a software developer can browse, evaluate, and select his or her preferred web APIs from the API's sharing platforms to create various mashups with rich functionality. The big volume of candidate APIs places a heavy burden on software developers’ API selection decisions. This, in turn, calls for the support of intelligent API recommender systems. However, existing API recommender systems often face two challenges. First, they focus more on the functional accuracy of APIs while neglecting the APIs’ actual compatibility. This then creates incompatible mashups. Second, they often require software developers to input a set of keywords that can accurately describe the expected functions of the mashup to be developed. This second challenge tests partial developers who have little background knowledge in the fields. To tackle the above-mentioned challenges, in this article we propose a compatibility-aware and text description-driven web API recommendation approach (named WAR text ). WAR text guarantees the compatibility among the recommended APIs by utilizing the APIs’ composition records produced by historical mashup creations. Besides, WAR text entitles a software developer to type a simple text document that describes the expected mashup functions as input. Then through textual description mining, WAR text can precisely capture the developers’ functional requirements and then return a set of APIs with the highest compatibility. Finally, through a real-world mashup dataset ProgrammableWeb, we validate the feasibility of our novel approach.

The Internet of Vehicles (IoV) connects vehicles, roadside units (RSUs) and other intelligent objects, enabling data sharing among them, thereby improving the efficiency of urban traffic and safety. Currently, collections of multimedia content, generated by multimedia surveillance equipment, vehicles, and so on, are transmitted to edge servers for implementation, because edge computing is a formidable paradigm for accommodating multimedia services with low-latency resource provisioning. However, the uneven or discrete distribution of the traffic flow covered by edge servers negatively affects the service performance (e.g., overload and underload) of edge servers in multimedia IoV systems. Therefore, how to accurately schedule and dynamically reserve proper numbers of resources for multimedia services in edge servers is still challenging. To address this challenge, a traffic flow prediction driven resource reservation method, called TripRes, is developed in this article. Specifically, the city map is divided into different regions, and the edge servers in a region are treated as a “big edge server” to simplify the complex distribution of edge servers. Then, future traffic flows are predicted using the deep spatiotemporal residual network (ST-ResNet), and future traffic flows are used to estimate the amount of multimedia services each region needs to offload to the edge servers. With the number of services to be offloaded in each region, their offloading destinations are determined through latency-sensitive transmission path selection. Finally, the performance of TripRes is evaluated using real-world big data with over 100M multimedia surveillance records from RSUs in Nanjing China.

Recently, biometric identification has been extensively used for border control. Some face recognition systems have been designed based on Internet of Things. But the rich personal information contained in face images can cause severe privacy breach and abuse issues during the process of identification if a biometric system has compromised by insiders or external security attacks. Encrypting the query face image is the state-of-the-art solution to protect an individual’s privacy but incurs huge computational cost and poses a big challenge on time-critical identification applications. However, due to their high computational complexity, existing methods fail to handle large-scale biometric repositories where a target face is searched. In this article, we propose an efficient privacy-preserving face recognition scheme based on clustering. Concretely, our approach innovatively matches an encrypted face query against clustered faces in the repository to save computational cost while guaranteeing identification accuracy via a novel multi-matching scheme. To the best of our knowledge, our scheme is the first to reduce the computational complexity from O(M) in existing methods to approximate O (√ M ), where M is the size of a face repository. Extensive experiments on real-world datasets have shown the effectiveness and efficiency of our scheme.

The recommender system is an important application in big data analytics because accurate recommendation items or high-valued suggestions can bring high profit to both commercial companies and customers. To make precise recommendations, a recommender system often needs large and fine-grained data for training. In the current big data era, data often exist in the form of isolated islands, and it is difficult to integrate the data scattered due to privacy security concerns. Moreover, privacy laws and regulations make it harder to share data. Therefore, designing a privacy-preserving recommender system is of paramount importance. Existing privacy-preserving recommender system models mainly adapt cryptography approaches to achieve privacy preservation. However, cryptography approaches have heavy overhead when performing encryption and decryption operations and they lack a good level of flexibility. In this paper, we propose a Locality Sensitive Hashing (LSH) based approach for federated recommender system. Our proposed efficient and scalable federated recommender system can make full use of multiple source data from different data owners while guaranteeing preservation of privacy of contributing parties. Extensive experiments on real-world benchmark datasets show that our approach can achieve both high time efficiency and accuracy under small privacy budgets.

Anomaly detection is one of the most important data mining tasks in many real-life applications such as network intrusion detection for cybersecurity and medical diagnosis for healthcare. In the big data era, these applications demand fast and versatile anomaly detection capability to handle various types of increasingly huge-volume data. However, existing detection methods are either slow due to high computational complexity, or unable to deal with complicated anomalies like local anomalies. In this paper, we propose a novel anomaly detection method named OPHiForest with the use of the order preserving hashing based isolation forest. The core idea is to learn the information from data to construct better isolation forest structure than the state-of-the-art methods like iForest and LSHiForest, which can achieve robust detection of various anomaly types. We design a fast two-step learning process for the order preserving hashing scheme. This leads to stronger order preservation for better hashing, and therefore enhances anomaly detection robustness and accuracy. Extensive experiments on both synthetic and real-world data sets demonstrate that our method is highly robust and scalable.

The development of the Internet of Vehicles (IoV) enables numerous emerging in-vehicle applications to accommodate users with various contents, thus enhancing their traveling experiences. In IoV, content decoding tasks are typically offloaded to edge servers for implementation, as edge computing is an admirable paradigm to provide low-latency services. However, as different vehicular users may request the same contents, processing these contents repeatedly leads to the waste of storage, computation and bandwidth resources. Therefore, fine-grained computation offloading and content caching are demanded in IoV. In this paper, a joint optimization method for computation offloading and content caching based on traffic flow prediction, named COC, is proposed. Firstly, traffic flow covered by each edge server is predicted by a modified deep spatiotemporal residual network (ST-ResNet). Secondly, the non-dominated sorting genetic algorithm III (NSGA-III) is leveraged to realize the many-objective optimization to shorten the execution time and reduce the energy consumption of computation and transmission in IoV. Finally, evaluated by real-world big data from Nanjing China, COC shows a great reduction in execution time and energy consumption of transmission and computation compared to other methods.

With the advent of the Internet of Vehicles (IoV), drivers are now provided with diverse time-sensitive vehicular services that usually require a large scale of computation. As civilian vehicles are generally insufficient in computational resources, their service requests are offloaded to cloud data centers and edge computing devices (ECDs) with ample computational resources to enhance the quality of service (QoS). However, ECDs are often overloaded with excessive service requests. In addition, as the network conditions and service compositions are complicated and dynamic, the centralized control of ECDs is hard to achieve. To tackle these challenges, a dynamic task offloading method with minority game (MG) in cloud-edge computing, named DOM, is proposed in this paper. Technically, MG is an effective tool with a distributed mechanism which can minimize the dependency on centralized control in resource allocation. In the MG, reinforcement learning (RL) is applied to optimize the distributed decision-making of participants. Finally, with a real-world dataset of IoV services, the effectiveness and adaptability of DOM are evaluated.

Smart city is gradually forming a large scope of Internet of Things (IoT) networks with diffusely deployed IoT devices that produce quantities of services. Considering the large-scale and widely distributed features of IoT networks, edge computing is emerged as a powerful and suitable paradigm to provide computing abilities for the IoT devices at the edge of the networks. In edge computing, the IoT services could be placed on the edge computing units (ECUs) for execution, which provides low latency and eases the burden of bandwidth. However, it is still challenging to improve the overall ECU execution performance (i.e., the resource usage, the load balance levels, and the power consumption of ECUs) and meanwhile prevent privacy leakage of the IoT devices for service placement. To tackle this challenge, a trust-oriented IoT service placement method, abbreviated as TSP, is proposed for smart cities in edge computing. Technically, improving the strength Pareto evolutionary algorithm (SPEA2) is leveraged to acquire the balanced placement strategies for the tradeoffs among the execution performance metrics with privacy preservation. Additionally, the technique for order preference by similarity to ideal solution (TOPSIS) and multicriteria decision-making (MCDM) techniques are employed to identify the optimal placement strategy among the obtained service placement strategies. Eventually, systematic experiments are conducted to verify the efficiency and reliability of TSP.

Benefiting from the real-time processing ability of edge computing, computing tasks requested by smart devices in the Internet of Things are offloaded to edge computing devices (ECDs) for implementation. However, ECDs are often overloaded or underloaded with disproportionate resource requests. In addition, during the process of task offloading, the transmitted information is vulnerable, which can result in data incompleteness. In view of this challenge, a blockchain-enabled computation offloading method, named BeCome, is proposed in this article. Blockchain technology is employed in edge computing to ensure data integrity. Then, the nondominated sorting genetic algorithm III is adopted to generate strategies for balanced resource allocation. Furthermore, simple additive weighting and multicriteria decision making are utilized to identify the optimal offloading strategy. Finally, performance evaluations of BeCome are given through simulation experiments.

introduction Introduction to the Special Issue on Privacy and Security in Evolving Internet of Multimedia Things Share on Editors: Suraj Sharma View Profile , Xuyun Zhang View Profile , Hesham El-Sayed View Profile , Zhiyuan Tan View Profile Authors Info & Claims ACM Transactions on Multimedia Computing, Communications, and ApplicationsVolume 16Issue 3sOctober 2020 Article No.: 93pp 1–3https://doi.org/10.1145/3423955Online:17 December 2020Publication History 0citation77DownloadsMetricsTotal Citations0Total Downloads77Last 12 Months38Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Edge Computing provides mobile and Internet-of-Things (IoT) app vendors with a new distributed computing paradigm which allows an app vendor to deploy its app at hired edge servers distributed near app users at the edge of the cloud. This way, app users can be allocated to hired edge servers nearby to minimize network latency and energy consumption. A cost-effective edge user allocation (EUA) requires maximum app users to be served with minimum overall system cost. Finding a centralized optimal solution to this EUA problem is NP-hard. Thus, we propose EUAGame, a game-theoretic approach that formulates the EUA problem as a potential game. We analyze the game and show that it admits a Nash equilibrium. Then, we design a novel decentralized algorithm for finding a Nash equilibrium in the game as a solution to the EUA problem. The performance of this algorithm is theoretically analyzed and experimentally evaluated. The results show that the EUA problem can be solved effectively and efficiently.

The popularity of cloud computing has fueled the growth in multi-tenant service-based systems (SBSs) that are composed of selected cloud services. In the cloud environment, a multi-tenant SBS simultaneously serves multiple tenants that usually have differentiated QoS requirements. This unique characteristic further complicates the problems of QoS-aware service selection at build-time and system adaptation at runtime, and renders conventional approaches obsolete and inefficient. In the dynamic and volatile cloud environment, the efficiency of building and adapting a multi-tenant SBS is of paramount importance. In this paper, we present two service recommendation approaches for multi-tenant SBSs, one for build-time and one for runtime, based on K-Means clustering and Locality-Sensitive Hashing (LSH) techniques respectively, aiming at finding appropriate services efficiently. Extensive experimental results demonstrate that our approaches can facilitate fast multi-tenant SBS construction and rapid system adaptation.

Multiple multi-dimensional data streams are ubiquitous in the modern world, such as IoT applications, GIS applications and social networks. Detecting anomalies in such data streams in real-time is an important and challenging task. It is able to provide valuable information from data and then assists decision-making. However, exiting approaches for anomaly detection in multi-dimensional data streams have not properly considered the correlations among multiple multi-dimensional streams. Moreover, for multi-dimensional streaming data, online detection speed is often an important concern. In this paper, we propose a fast yet effective anomaly detection approach in multiple multi-dimensional data streams. This is based on a combination of ideas, i.e., stream pre-processing, locality sensitive hashing and dynamic isolation forest. Experiments on real datasets demonstrate that our approach achieves a magnitude increase in its efficiency compared with state-of-the-art approaches while maintaining competitive detection accuracy.

Due to the high demands of mobile video streaming, wireless networks have witnessed great pressure on increasing the transmitting rate. Crowdsourcing sets the trend of ensuring direct communication among the participants, thus expanding the bandwidth of networks, shunting the traffic volume of the core networks and improving the video service quality for mobile users. However, irregularly responding to the requestors poses a threat to the battery life of the mobile devices, and decreasing the service time and incomes of the providers remains challenging. To address this challenge, we propose a multi-objective crowdsourcing method, named MCM, for mobile video streaming. Technically, DBSCAN (Density-based Spatial Clustering for Applications with Noise) and IDP (Improved Dynamic Programming) are utilized to generate the service strategies. Consequently, experimental evaluations are conducted to demonstrate the efficiency of MCM.

Summary The fine‐grained access control has been proved to be a reliable tool to ensure preserving of privacy of end users. In fog computing, one of the challenges is to understand users' attitudes and behaviors toward personalized control. However, few of studies have given a clear view on users' perception of the burden of interactivity when they set complex privacy settings. To this end, we conducted a user study including a lab study with 26 participants and an evaluation with 223 participants. From the lab study, we found that participants were satisfied with improved privacy settings but did not adapt well to complex personalized interfaces. We proposed effective methods to assist users to balance between the full control and the additional interaction burden, including sorting, recommendations, and establishing profiles. After this lab study, we organized a survey evaluation additionally to explore users' current usage of privacy features. Results from the evaluation showed that the principle reason that users failed to use privacy features was that they were not appropriately aware of these features. A key conclusion is that privacy settings should not only let users take over the control of smartphones but also inform them of the knowledge on privacy practices.

We are pleased to announce the publication of the special issue focusing on intrusion detection and prevention in cloud, fog, and Internet of Things (IoT).Internet of Things (IoT), cloud, and fog computing paradigms are as a whole provision a powerful large-scale computing infrastructure for many data and computation intensive applications.Specifically, the IoT technologies and deployment can widely perceive our physical world at a fine granularity and generate sensing data for further insight extraction.The fog computing facilities can provide computing power near the IoT devices where data are generated, aiming to achieve fast data processing for time critical applications or save the amount of data transmitted into cloud for storage or further processing.The cloud computing platforms can offer big data storage and large-scale processing services for cheap long-term storage or data intensive analytics with more advanced data mining models.Hence, it can be seen that the IoT/fog/cloud computing infrastructures can support the whole lifecycle of large-scale applications where big data collection, transmission, storage, processing, and mining can be seamlessly integrated.However, these state-of-the-art computing infrastructures still suffer from severe security and privacy threats because of their built-in properties such as the ubiquitous-access and multitenancy features of

The increasing number of web APIs registered in service sharing communities (e.g., http://ProgrammableWeb.com that provides a platform benefiting the social interactions between different software developers) has provided a promising way to quickly build various apps with diverse functions. Generally, an app developer can manually discover, select, and compose a set of appropriate web APIs to build a new app satisfying the developer's functional and nonfunctional business requirements, economically and conveniently. However, the above manual web APIs selection process is usually time-consuming and cumbersome as most app developers often do not have much background knowledge of candidate web APIs. Moreover, the manually selected web APIs cannot always guarantee to be integrated successfully as the compatibilities between different web APIs are often varied and not validated. In view of these challenges, we define a weighted APIs correlation graph (W-ACG) in this paper to model the APIs functions and compatibilities. Furthermore, we propose a novel web APIs recommendation approach named Keywords-based and Compatibility-aware APIs Recommendation (K-CAR) based on the defined W-ACG. Through analyzing the input keywords describing the functions expected by an app developer, K-CAR can return the app developer a set of optimal APIs that are not only functional-qualified but also compatibility-guaranteed. Extensive experiments are deployed on 18 478 real-world web APIs and 6146 real-world apps to evaluate the usefulness and efficiency of K-CAR.

Crowdsourcing is a booming technique that enables participants to exchange data directly, thus making it possible to answer latency-sensitive service requests and relieve the burden of core networks. With some incentives, providers compete to furnish service requests, thus pledging the quality of experience (QoE) for requestors. However, the decentralized communication in crowdsourcing increases the probability of information tapering. Furthermore, providers' arbitrary selection of the requests poses great threat to the efficient and profitable service provision for the requestors. To deal with these challenges, we propose a blockchain-powered crowdsourcing method, named BPCM, while considering the privacy preservation in mobile environment. Specifically, a mobile crowdsourcing framework based on blockchain is designed first to preserve the privacy of the participants and keep the integrity of the service request and provision. Then, density-based spatial clustering of applications with noise (DBSCAN) and improved dynamic programming (IDP) are adopted to cluster the requestors and generate service strategies, respectively. Furthermore, simple additive weighting (SAW) and multiple criteria decision making (MCDM) are utilized to select the optimal strategy that achieves the tradeoffs among maximizing the service time, increasing the profits, and reducing the energy consumption for the providers. Finally, comprehensive experiments are conducted to verify the accuracy and effectiveness of BPCM.

As one of the hot issues in the research on complicated network, collaborative network traffic analysis plays a core role in improving network performance, analyzing network behaviors and predicting abnormal traffic, especially from large-scale network data sets. Several approaches on flow-level traffic data analysis have been proposed about analyzing the structure and situation of the network. Different from the state-of-the-art, we first propose a new decomposition model based on the alternating direction method of multipliers for packet-level traffic data. In addition, we present the iterative scheme of the algorithm for network anomaly detection problem, which is termed NTA-ADMM. Based on this approach, we can carry out intrusion detection for packet-level network traffic data, no matter whether it is polluted by noise or not. Finally, we design a prototype system for network anomaly detection such as unauthorized access from a remote machine to a local machine (R2L) attack and so on. The experiments have shown that our approach is effective in revealing the patterns of network traffic data and detecting attacks from large-scale network traffic. Moreover, the experiments have demonstrated the robustness of the algorithm even when the network traffic is polluted by the large volume anomalies and noise.

Recommending appropriate product items to the target user is becoming the key to ensure continuous success of E-commerce. Today, many E-commerce systems adopt various recommendation techniques, e.g., Collaborative Filtering (abbreviated as CF)-based technique, to realize product item recommendation. Overall, the present CF recommendation can perform very well, if the target user owns similar friends (user-based CF), or the product items purchased and preferred by target user own one or more similar product items (item-based CF). While due to the sparsity of big rating data in E-commerce, similar friends and similar product items may be both absent from the user-product purchase network, which lead to a big challenge to recommend appropriate product items to the target user. Considering the challenge, we put forward a Structural Balance Theory-based Recommendation (i.e., SBT-Rec) approach. In the concrete, (I) user-based recommendation: we look for target user's “enemy” (i.e., the users having opposite preference with target user); afterwards, we determine target user's “possible friends”, according to “enemy's enemy is a friend” rule of Structural Balance Theory, and recommend the product items preferred by “possible friends” of target user to the target user. (II) likewise, for the product items purchased and preferred by target user, we determine their “possibly similar product items” based on Structural Balance Theory and recommend them to the target user. At last, the feasibility of SBT-Rec is validated, through a set of experiments deployed on MovieLens-1M dataset.

Outlier detection is an important task in data mining. With the growing need to analyze high speed data streams, the task of outlier detection becomes even more challenging as traditional outlier detection techniques can no longer assume that all the data can be stored for processing. While the wellknown Local Outlier Factor (LOF) algorithm has an incremental version (called iLOF), it assumes unbounded memory to keep all previous data points. In this paper, we propose a memory efficient incremental local outlier (MiLOF) detection algorithm for data streams, and a more flexible version (MiLOF F), both have an accuracy close to iLOF but within a fixed memory bound. In addition MiLOF F is robust to changes in the number of data points, underlying clusters and dimensions in the data stream.

Anomaly or outlier detection is a major challenge in big data analytics because anomaly patterns provide valuable insights for decision-making in a wide range of applications. Recently proposed anomaly detection methods based on the tree isolation mechanism are very fast due to their logarithmic time complexity, making them capable of handling big data sets efficiently. However, the underlying similarity or distance measures in these methods have not been well understood. Contrary to the claims that these methods never rely on any distance measure, we find that they have close relationships with certain distance measures. This implies that the current use of this fast isolation mechanism is only limited to these distance measures and fails to generalise to other commonlyused measures. In this paper, we propose a generic framework named LSHiForest for fast tree isolation based ensemble anomaly analysis with the use of a Locality-Sensitive Hashing (LSH) forest. Being generic, the proposed framework can be instantiated with a diverse range of LSH families, and the fast isolation mechanism can be extended to any distance measures, data types and data spaces where an LSH family is defined. In particular, the instances of our framework with kernelised LSH families or learning based hashing schemes can detect complicated anomalies like local or surrounded anomalies. We also formally show that the existing tree isolation based detection methods are special cases of our framework with the corresponding distance measures. Extensive experiments on both synthetic and real-world benchmark data sets show that the framework can achieve both high time efficiency and anomaly detection quality.

With the advent of IoT (Internet of Things) age, considerable web services are emerging rapidly in service communities, which places a heavy burden on the target users' service selection decisions. In this situation, various techniques, e.g., collaborative filtering (i.e., CF) is introduced in service recommendation to alleviate the service selection burden. However, traditional CF-based service recommendation approaches often assume that the historical user-service quality data is centralized, while neglect the distributed recommendation situation. Generally, distributed service recommendation involves inevitable message communication among different parties and hence, brings challenging efficiency and privacy concerns. In view of this challenge, a novel privacy-preserving distributed service recommendation approach based on Locality-Sensitive Hashing (LSH), i.e., DistSRLSH is put forward in this paper. Through LSH, DistSRLSH can achieve a good tradeoff among service recommendation accuracy, privacy-preservation and efficiency in distributed environment. Finally, through a set of experiments deployed on WS-DREAM dataset, we validate the feasibility of our proposal in handling distributed service recommendation problems.

Summary Because of the strong demands of physical resources of big data, it is an effective and efficient way to store and process big data in clouds, as cloud computing allows on‐demand resource provisioning. With the increasing requirements for the resources provisioned by cloud platforms, the Quality of Service (QoS) of cloud services for big data management is becoming significantly important. Big data has the character of sparseness, which leads to frequent data accessing and processing, and thereby causes huge amount of energy consumption. Energy cost plays a key role in determining the price of a service and should be treated as a first‐class citizen as other QoS metrics, because energy saving services can achieve cheaper service prices and environmentally friendly solutions. However, it is still a challenge to efficiently schedule Virtual Machines (VMs) for service QoS enhancement in an energy‐aware manner. In this paper, we propose an energy‐aware dynamic VM scheduling method for QoS enhancement in clouds over big data to address the above challenge. Specifically, the method consists of two main VM migration phases where computation tasks are migrated to servers with lower energy consumption or higher performance to reduce service prices and execution time. Extensive experimental evaluation demonstrates the effectiveness and efficiency of our method. Copyright © 2016 John Wiley & Sons, Ltd.

To maximize the economic benefits, a cloud service provider needs to recommend its services to as many users as possible based on the historical user-service quality data. However, when a cloud platform (e.g., Amazon) intends to make a service recommendation decision, considering only its own user-service quality data is insufficient, because a cloud user may invoke services from multiple distributed cloud platforms (e.g., Amazon and IBM). In this situation, it is promising for Amazon to collaborate with other cloud platforms (e.g., IBM) to utilize the integrated data for the service recommendation to improve the recommendation accuracy. However, two challenges are present in the above-mentioned collaboration process, where we attempt to use multi-source data for the service recommendation. First, protecting users' privacy is challenging when IBM releases its own data to Amazon. Second, the recommendation efficiency and scalability are often low when the user-service quality data of Amazon and IBM update frequently. Considering these challenges, a privacy-preserving and scalable service recommendation approach based on distributed locality-sensitive hashing, i.e., SerRecdistri-LSH, is proposed in this paper to handle the service recommendation in a distributed cloud environment. Extensive experiments on the WS-DREAM data set validate the feasibility of our approach in terms of service recommendation accuracy, scalability, and privacy preservation.

Summary Traffic hotline discovery is necessary for rational and scientific urban transportation planning in the new living quarters and economic zones. Cloud of Things (CoT) is a newly emerging concept, involving with two advanced technologies, that is, Cloud Computing and Internet of Things (IoT). CoT provides promising opportunities for traffic hotline discovery. However, it is still a challenge to discover the traffic hotlines over CoT. In view of this challenge, a hotline discovery method over CoT by using big taxi GPS data is proposed in this paper. Specifically, a traffic hotline discovery principle is presented to provide a reference standard for the generalized traffic spots that need planning, and a corresponding hotline discovery method is proposed for traffic hotspot identification and hotline selection. To improve the scalability and efficiency of the proposed method in “Big Data” environment, the SAP HANA cloud is applied to implement the proposed method under two application scenarios. Finally, the experimental results demonstrate that the proposed method is both effective and efficient. Software—Practice and Experience. Copyright © 2016 John Wiley & Sons, Ltd.

With the fast growth of applications of service-oriented architecture (SOA) in software engineering, there has been a rapid increase in demand for building service-based systems (SBSs) by composing existing Web services. Finding appropriate component services to compose is a key step in the SBS engineering process. Existing approaches require that system engineers have detailed knowledge of SOA techniques which is often too demanding. To address this issue, we propose Keyword Search for Service-based Systems (KS3), a novel approach that integrates and automates the system planning, service discovery and service selection operations for building SBSs based on keyword search. KS3 assists system engineers without detailed knowledge of SOA techniques in searching for component services to build SBSs by typing a few keywords that represent the tasks of the SBSs with quality constraints and optimisation goals for system quality, e.g., reliability, throughput and cost. KS3 offers a new paradigm for SBS engineering that can significantly save the time and effort during the system engineering process. We conducted large-scale experiments using two real-world Web service datasets to demonstrate the practicality, effectiveness and efficiency of KS3.

While cloud computing has become an attractive platform for supporting data intensive applications, a major obstacle to the adoption of cloud computing in sectors such as health and defense is the privacy risk associated with releasing datasets to third-parties in the cloud for analysis. A widely-adopted technique for data privacy preservation is to anonymize data via local recoding. However, most existing local-recoding techniques are either serial or distributed without directly optimizing scalability, thus rendering them unsuitable for big data applications. In this paper, we propose a highly scalable approach to local-recoding anonymization in cloud computing, based on Locality Sensitive Hashing (LSH). Specifically, a novel semantic distance metric is presented for use with LSH to measure the similarity between two data records. Then, LSH with the MinHash function family can be employed to divide datasets into multiple partitions for use with MapReduce to parallelize computation while preserving similarity. By using our efficient LSH-based scheme, we can anonymize each partition through the use of a recursive agglomerative $k$-member clustering algorithm. Extensive experiments on real-life datasets show that our approach significantly improves the scalability and time-efficiency of local-recoding anonymization by orders of magnitude over existing approaches.

Summary Big data is one of the most referred key words in recent information and communications technology industry. As the new‐generation distributed computing platform, cloud environments offer high efficiency and low cost for data‐intensive storage and computation for big data applications. Cloud resources and services are available in pay‐as‐you‐go mode, which brings extraordinary flexibility and cost‐effectiveness as well as minimal investments in their own computing infrastructure. However, these advantages come at a price—people no longer have direct control over their own data. Based on this view, data security becomes a major concern in the adoption of cloud computing. Authenticated key exchange is essential to a security system that is based on high‐efficiency symmetric‐key encryptions. With virtualisation technology being applied, existing key exchange schemes such as Internet key exchange become time consuming when directly deployed into cloud computing environment, especially for large‐scale tasks that involve intensive user–cloud interactions, such as scheduling and data auditing. In this paper, we propose a novel hierarchical key exchange scheme, namely hierarchical key exchange for big data in cloud, which aims at providing efficient security‐aware scheduling and auditing for cloud environments. In this novel key exchange scheme, we developed a two‐phase layer‐by‐layer iterative key exchange strategy to achieve more efficient authenticated key exchange without sacrificing the level of data security. Both theoretical analysis and experimental results demonstrate that when deployed in cloud environments with diverse server layouts, efficiency of the proposed scheme is dramatically superior to its predecessors cloud computing background key exchange and Internet key exchange schemes. Copyright © 2014 John Wiley & Sons, Ltd.

Scientific workflows are often deployed across multiple cloud computing platforms due to their large-scale characteristic. This can be technically achieved by expanding a cloud platform. However, it is still a challenge to conduct scientific workflow executions in an energy-aware fashion across cloud platforms or even inside a cloud platform, since the cloud platform expansion will make the energy consumption a big concern. In this paper, we propose an Energy-aware Resource Allocation method, named EnReal, to address the above challenge. Basically, we leverage the dynamic deployment of virtual machines for scientific workflow executions. Specifically, an energy consumption model is presented for applications deployed across cloud computing platforms, and a corresponding energy-aware resource allocation algorithm is proposed for virtual machine scheduling to accomplish scientific workflow executions. Experimental evaluation demonstrates that the proposed method is both effective and efficient.

Outlier detection is an important task in data mining, with applications ranging from intrusion detection to human gait analysis. With the growing need to analyze high speed data streams, the task of outlier detection becomes even more challenging as traditional outlier detection techniques can no longer assume that all the data can be stored for processing. While the well-known Local Outlier Factor (LOF) algorithm has an incremental version, it assumes unbounded memory to keep all previous data points. In this paper, we propose a memory efficient incremental local outlier (MiLOF) detection algorithm for data streams, and a more flexible version (MiLOF_F), both have an accuracy close to Incremental LOF but within a fixed memory bound. Our experimental results show that both proposed approaches have better memory and time complexity than Incremental LOF while having comparable accuracy. In addition, we show that MiLOF_F is robust to changes in the number of data points, the number of underlying clusters and the number of dimensions in the data stream. These results show that MiLOF/MiLOF_F are well suited to application environments with limited memory (e.g., wireless sensor networks), and can be applied to high volume data streams.

Cloud computing that provides elastic computing and storage resource on demand has become increasingly important due to the emergence of “big data”. Cloud computing resources are a natural fit for processing big data streams as they allow big data application to run at a scale which is required for handling its complexities (data volume, variety and velocity). With the data no longer under users' direct control, data security in cloud computing is becoming one of the most concerns in the adoption of cloud computing resources. In order to improve data reliability and availability, storing multiple replicas along with original datasets is a common strategy for cloud service providers. Public data auditing schemes allow users to verify their outsourced data storage without having to retrieve the whole dataset. However, existing data auditing techniques suffers from efficiency and security problems. First, for dynamic datasets with multiple replicas, the communication overhead for update verifications is very large, because each update requires updating of all replicas, where verification for each update requires O(log n ) communication complexity. Second, existing schemes cannot provide public auditing and authentication of block indices at the same time. Without authentication of block indices, the server can build a valid proof based on data blocks other than the blocks client requested to verify. In order to address these problems, in this paper, we present a novel public auditing scheme named MuR-DPA. The new scheme incorporated a novel authenticated data structure (ADS) based on the Merkle hash tree (MHT), which we call MR-MHT. To support full dynamic data updates and authentication of block indices, we included rank and level values in computation of MHT nodes. In contrast to existing schemes, level values of nodes in MR-MHT are assigned in a top-down order, and all replica blocks for each data block are organized into a same replica sub-tree. Such a configuration allows efficient verification of updates for multiple replicas. Compared to existing integrity verification and public auditing schemes, theoretical analysis and experimental results show that the proposed MuR-DPA scheme can not only incur much less communication overhead for both update verification and integrity verification of cloud datasets with multiple replicas, but also provide enhanced security against dishonest cloud service providers.

Cloud computing provides promising scalable IT infrastructure to support various processing of a variety of big data applications in sectors such as healthcare and business. Data sets like electronic health records in such applications often contain privacy-sensitive information, which brings about privacy concerns potentially if the information is released or shared to third-parties in cloud. A practical and widely-adopted technique for data privacy preservation is to anonymize data via generalization to satisfy a given privacy model. However, most existing privacy preserving approaches tailored to small-scale data sets often fall short when encountering big data, due to their insufficiency or poor scalability. In this paper, we investigate the local-recoding problem for big data anonymization against proximity privacy breaches and attempt to identify a scalable solution to this problem. Specifically, we present a proximity privacy model with allowing semantic proximity of sensitive values and multiple sensitive attributes, and model the problem of local recoding as a proximity-aware clustering problem. A scalable two-phase clustering approach consisting of a t-ancestors clustering (similar to k-means) algorithm and a proximity-aware agglomerative clustering algorithm is proposed to address the above problem. We design the algorithms with MapReduce to gain high scalability by performing data-parallel computation in cloud. Extensive experiments on real-life data sets demonstrate that our approach significantly improves the capability of defending the proximity privacy breaches, the scalability and the time-efficiency of local-recoding anonymization over existing approaches.

Cloud computing promises a scalable infrastructure for processing big data applications such as medical data analysis. Cross-cloud service composition provides a concrete approach capable for large-scale big data processing. However, the complexity of potential compositions of cloud services calls for new composition and aggregation methods, especially when some private clouds refuse to disclose all details of their service transaction records due to business privacy concerns in cross-cloud scenarios. Moreover, the credibility of cross-clouds and on-line service compositions will become suspicional, if a cloud fails to deliver its services according to its “promised” quality. In view of these challenges, we propose a privacy-aware cross-cloud service composition method, named HireSome-II (History record-based Service optimization method) based on its previous basic version HireSome-I. In our method, to enhance the credibility of a composition plan, the evaluation of a service is promoted by some of its QoS history records, rather than its advertised QoS values. Besides, the k-means algorithm is introduced into our method as a data filtering tool to select representative history records. As a result, HireSome-II can protect cloud privacy, as a cloud is not required to unveil all its transaction records. Furthermore, it significantly reduces the time complexity of developing a cross-cloud service composition plan as only representative ones are recruited, which is demanded for big data processing. Simulation and analytical results demonstrate the validity of our method compared to a benchmark.

Big sensor data is prevalent in both industry and scientific research applications where the data is generated with high volume and velocity it is difficult to process using on-hand database management tools or traditional data processing applications. Cloud computing provides a promising platform to support the addressing of this challenge as it provides a flexible stack of massive computing, storage, and software services in a scalable manner at low cost. Some techniques have been developed in recent years for processing sensor data on cloud, such as sensor-cloud. However, these techniques do not provide efficient support on fast detection and locating of errors in big sensor data sets. For fast data error detection in big sensor data sets, in this paper, we develop a novel data error detection approach which exploits the full computation potential of cloud platform and the network feature of WSN. Firstly, a set of sensor data error types are classified and defined. Based on that classification, the network feature of a clustered WSN is introduced and analyzed to support fast error detection and location. Specifically, in our proposed approach, the error detection is based on the scale-free network topology and most of detection operations can be conducted in limited temporal or spatial data blocks instead of a whole big data set. Hence the detection and location process can be dramatically accelerated. Furthermore, the detection and location tasks can be distributed to cloud platform to fully exploit the computation power and massive storage. Through the experiment on our cloud computing platform of U-Cloud, it is demonstrated that our proposed approach can significantly reduce the time for error detection and location in big data sets generated by large scale sensor network systems with acceptable error detecting accuracy.

Cloud computing opens a new era in IT as it can provide various elastic and scalable IT services in a pay-as-you-go fashion, where its users can reduce the huge capital investments in their own IT infrastructure. In this philosophy, users of cloud storage services no longer physically maintain direct control over their data, which makes data security one of the major concerns of using cloud. Existing research work already allows data integrity to be verified without possession of the actual data file. When the verification is done by a trusted third party, this verification process is also called data auditing, and this third party is called an auditor. However, such schemes in existence suffer from several common drawbacks. First, a necessary authorization/authentication process is missing between the auditor and cloud service provider, i.e., anyone can challenge the cloud service provider for a proof of integrity of certain file, which potentially puts the quality of the so-called ‘auditing-as-a-service’ at risk; Second, although some of the recent work based on BLS signature can already support fully dynamic data updates over fixed-size data blocks, they only support updates with fixed-sized blocks as basic unit, which we call coarse-grained updates. As a result, every small update will cause re-computation and updating of the authenticator for an entire file block, which in turn causes higher storage and communication overheads. In this paper, we provide a formal analysis for possible types of fine-grained data updates and propose a scheme that can fully support authorized auditing and fine-grained update requests. Based on our scheme, we also propose an enhancement that can dramatically reduce communication overheads for verifying small updates. Theoretical analysis and experimental results demonstrate that our scheme can offer not only enhanced security and flexibility, but also significantly lower overhead for big data applications with a large number of frequent small updates, such as applications in social media and business transactions.

Service recommender systems have been shown as valuable tools for providing appropriate recommendations to users. In the last decade, the amount of customers, services and online information has grown rapidly, yielding the big data analysis problem for service recommender systems. Consequently, traditional service recommender systems often suffer from scalability and inefficiency problems when processing or analysing such large-scale data. Moreover, most of existing service recommender systems present the same ratings and rankings of services to different users without considering diverse users' preferences, and therefore fails to meet users' personalized requirements. In this paper, we propose a Keyword-Aware Service Recommendation method, named KASR, to address the above challenges. It aims at presenting a personalized service recommendation list and recommending the most appropriate services to the users effectively. Specifically, keywords are used to indicate users' preferences, and a user-based Collaborative Filtering algorithm is adopted to generate appropriate recommendations. To improve its scalability and efficiency in big data environment, KASR is implemented on Hadoop, a widely-adopted distributed computing platform using the MapReduce parallel processing paradigm. Finally, extensive experiments are conducted on real-world data sets, and results demonstrate that KASR significantly improves the accuracy and scalability of service recommender systems over existing approaches.

A large number of cloud services require users to share private data like electronic health records for data analysis or mining, bringing privacy concerns. Anonymizing data sets via generalization to satisfy certain privacy requirements such as k-anonymity is a widely used category of privacy preserving techniques. At present, the scale of data in many cloud applications increases tremendously in accordance with the Big Data trend, thereby making it a challenge for commonly used software tools to capture, manage, and process such large-scale data within a tolerable elapsed time. As a result, it is a challenge for existing anonymization approaches to achieve privacy preservation on privacy-sensitive large-scale data sets due to their insufficiency of scalability. In this paper, we propose a scalable two-phase top-down specialization (TDS) approach to anonymize large-scale data sets using the MapReduce framework on cloud. In both phases of our approach, we deliberately design a group of innovative MapReduce jobs to concretely accomplish the specialization computation in a highly scalable way. Experimental evaluation results demonstrate that with our approach, the scalability and efficiency of TDS can be significantly improved over existing approaches.

SUMMARY Workflow scheduling has been extensively studied to improve the system performance. However, existing approaches are usually built on predefined workflow graph structure, neglecting the possibility that a workflow graph itself may be changeable when certain conditions are satisfied. Therefore, in this paper, we propose the concept of graph refactoring that transforms certain types of sequential tasks to run in parallel without changing system's functionality. We first provide a classification for task dependencies in workflows and identify that previously sequential task ordering in loose control dependency can be scheduled to run in parallel as long as supporting services are trustworthy. With this concept, we present a refactoring algorithm to traverse, restructure, and parallelize loose control dependencies in the graph when the reputations of related executing services are above certain threshold. In addition, refactoring effects on common sub‐graph structures are analyzed and discussed. In practice, our algorithm can be integrated into existing workflow management systems as a preprocessor to generate a new functionally equivalent working graph with more concurrent branches for further scheduling. Experiments and analysis show that graph refactoring can improve the system performance scalably because of concurrent execution of previously sequential tasks. Copyright © 2013 John Wiley & Sons, Ltd.

SUMMARY Big data and cloud computing are two disruptive trends nowadays, provisioning numerous opportunities to the current information technology industry and research communities while posing significant challenges on them as well. Cloud computing provides powerful and economical infrastructural resources for cloud users to handle ever increasing data sets in big data applications. However, processing or sharing privacy‐sensitive data sets on cloud probably engenders severe privacy concerns because of multi‐tenancy. Data encryption and anonymization are two widely‐adopted ways to combat privacy breach. However, encryption is not suitable for data that are processed and shared frequently, and anonymizing big data and manage numerous anonymized data sets are still challenges for traditional anonymization approaches. As such, we propose a scalable and cost‐effective framework for privacy preservation over big data on cloud in this paper. The key idea of the framework is that it leverages cloud‐based MapReduce to conduct data anonymization and manage anonymous data sets, before releasing data to others. The framework provides a holistic conceptual foundation for privacy preservation over big data. Further, a corresponding proof‐of‐concept prototype system is implemented. Empirical evaluations demonstrate that scalable and cost‐effective framework for privacy preservation can anonymize large‐scale data sets and mange anonymous data sets in a highly flexible, scalable, efficient, and cost‐effective fashion. Copyright © 2013 John Wiley & Sons, Ltd.

Cloud computing provides massive computation power and storage capacity which enable users to deploy computation and data-intensive applications without infrastructure investment. Along the processing of such applications, a large volume of intermediate data sets will be generated, and often stored to save the cost of recomputing them. However, preserving the privacy of intermediate data sets becomes a challenging problem because adversaries may recover privacy-sensitive information by analyzing multiple intermediate data sets. Encrypting ALL data sets in cloud is widely adopted in existing approaches to address this challenge. But we argue that encrypting all intermediate data sets are neither efficient nor cost-effective because it is very time consuming and costly for data-intensive applications to en/decrypt data sets frequently while performing any operation on them. In this paper, we propose a novel upper bound privacy leakage constraint-based approach to identify which intermediate data sets need to be encrypted and which do not, so that privacy-preserving cost can be saved while the privacy requirements of data holders can still be satisfied. Evaluation results demonstrate that the privacy-preserving cost of intermediate data sets can be significantly reduced with our approach over existing ones where all data sets are encrypted.

Instead of purchasing and maintaining their own computing infrastructure, scientists can now run data-intensive scientific applications in cloud computing environment by facilitating its vast storage and computation capabilities. During the scheduling of such scientific applications for execution, various computation data flows will happen between the controller and computing server instances. Amongst various quality-of-service (QoS) metrics, data security is one of the greatest concerns to scientists because their data may be intercepted or stolen by malicious parties during those data flows. An existing typical method for addressing this issue is to apply Internet Key Exchange (IKE) scheme to generate and exchange session keys, and then to apply these keys for performing symmetric-key encryption which will encrypt those data flows. However, the IKE scheme suffers from low efficiency due to its low performance of asymmetric-key crypto logical operations over a large amount of data and high-density operations which are exactly the characteristics of scientific applications. In this paper, we propose Cloud Computing Background Key Exchange (CCBKE), a novel authenticated key exchange scheme that aims at efficient security-aware scheduling of scientific applications. Our scheme is designed based on randomness-reuse strategy and Internet Key Exchange (IKE) scheme. Theoretical analyses and simulation results demonstrate that, compared with the IKE scheme, our CCBKE scheme can significantly improve the efficiency by dramatically reducing time consumption and computation load without sacrificing the level of security.

Along with more and more data intensive applications have been migrated into cloud environments, storing some valuable intermediate datasets has been accommodated in order to avoid the high cost of re-computing them. However, this poses a risk on data privacy protection because malicious parties may deduce the private information of the parent dataset or original dataset by analyzing some of those stored intermediate datasets. The traditional way for addressing this issue is to encrypt all of those stored datasets so that they can be hidden. We argue that this is neither efficient nor cost-effective because it is not necessary to encrypt ALL of those datasets and encryption of all large amounts of datasets can be very costly. In this paper, we propose a new approach to identify which stored datasets need to be encrypted and which not. Through intensive analysis of information theory, our approach designs an upper bound on privacy measure. As long as the overall mixed information amount of some stored datasets is no more than that upper bound, those datasets do not need to be encrypted while privacy can still be protected. A tree model is leveraged to analyze privacy disclosure of datasets, and privacy requirements are decomposed and satisfied layer by layer. With a heuristic implementation of this approach, evaluation results demonstrate that the cost for encrypting intermediate datasets decreases significantly compared with the traditional approach while the privacy protection of parent or original dataset is guaranteed.

In service selection, an end user often has his or her personal preferences imposing on a candidate service's non-functional properties. For a service selection process promoted by a group of users, candidate services are often evaluated by a group of end users who may have different preferences or priorities. In this situation, it is often a challenging effort to make a tradeoff among various preferences or priorities of the users. In view of this challenge, a multi-criteria decision-making method, named AHP (Analytic Hierarchy Process), is introduced to transform both qualitative personal preferences and users' priorities into numeric weights. Furthermore, a QoS-aware service evaluation method is presented for a shared service's co-selection taking advantage of AHP theory. At last, a case study is presented to demonstrate the feasibility of the method.

Abstract Batch processing in workflow schedules activity instances in multiple workflow cases of the same workflow type to run as a group. It can optimize business processes execution dynamically. To achieve this goal, it is necessary to define a dataflow operation language to group and ungroup the data in multiple cases of a workflow. Though our previous work has preliminarily investigated the model and its implementation, there is still lack of a formally defined model. In this paper, we first propose a method that is based on a partial vector space to model the dataflow in multiple workflow cases. Based on this model, the data operation primitives for batch processing are specified and defined formally. Since most WfMSs (Workflow Management Systems) use RDBMS (relational database management system) to store their data currently, an SQL (Structured Query Language)‐like implementation language, namely DBOL (Data Batch Operation Language), is proposed. Evaluation experiments have also been done to show its performance. Copyright © 2011 John Wiley & Sons, Ltd.

There exist so many web services that share same or similar functional properties, so it is often a challenging effort to select a credible and optimal web service based on their various history QoS records. In view of this challenge, in this paper, a novel QoS-aware web service selection method is put forward, based on credibility evaluation associated with negotiated QoS dimensions. More specifically, the historical empirical data, i.e., execution logs of a service, are used for evaluation purpose. At last, a case study is employed for illustration purpose, and the evaluations are presented to demonstrate the feasibility of our method.

Since non-functional properties play a more and more import role during the process of web service composition, the QoS issues for web service composition have obtained great interest in both research community and IT domain. Yet identifying the consumers¡¯ degree of satisfaction on QoS is a significant but challenging problem. This paper proposes a global QoS-driven evaluation strategy for web service composition on top of some previous work, aiming at improving some previous QoS frameworks. The executions of services are analyzed with the ACP (Algebra of Communication Process, a dialect of process algebra), and then the composite QoS values of a composite service are calculated by the ACP expressions. Finally, for the purpose that the composite service is evaluated via aggregating the criteria values into the degree of consumers¡¯ satisfaction, a synthetic method is formulated for comprehensively estimating the weights assigned to the criteria in terms of the consumers¡¯ preferences.