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.

Recent advances in large language models (LLMs) have enabled realistic user simulators for developing and evaluating recommender systems (RSs). However, existing LLM-based simulators for RSs face two major limitations: (1) static and single-step prompt-based inference that leads to inaccurate and incomplete user profile construction; (2) unrealistic and single-round recommendation-feedback interaction pattern that fails to capture real-world scenarios. To address these limitations, we propose DGDPO (Diagnostic-Guided Dynamic Profile Optimization), a novel framework that constructs user profile through a dynamic and iterative optimization process to enhance the simulation fidelity. Specifically, DGDPO incorporates two core modules within each optimization loop: firstly, a specialized LLM-based diagnostic module, calibrated through our novel training strategy, accurately identifies specific defects in the user profile. Subsequently, a generalized LLM-based treatment module analyzes the diagnosed defect and generates targeted suggestions to refine the profile. Furthermore, unlike existing LLM-based user simulators that are limited to single-round interactions, we are the first to integrate DGDPO with sequential recommenders, enabling a bidirectional evolution where user profiles and recommendation strategies adapt to each other over multi-round interactions. Extensive experiments conducted on three real-world datasets demonstrate the effectiveness of our proposed framework.

Hypergraph-based distillation methods have been proposed to mitigate the high computational cost of Hypergraph Neural Networks (HGNNs) in modeling high-order relationships. However, most existing methods use static and uniform distillation strategies for all nodes and hyperedges, ignoring their individual characteristics. In addition, they neglect the student model's capability to independently extract useful internal features. As a result, they are not effective in transferring higher-order structural knowledge from the teacher. To overcome these limitations, we propose ARCHER, an Adaptive and Reinforcement-Guided Contrastive HypER graph Distillation framework that enables a lightweight MLP student model to outperform its HGNN teacher model. First, we design an adaptive strategy that leverages node- and hyperedge-level confidence to mediate error guidance from the teacher model. Second, we introduce a contrastive learning module that guides the student to learn from both the teacher's outputs and its own internal representations, producing more expressive embeddings. Finally, we propose a multi-armed bandit-based reinforcement learning module that dynamically balances multiple loss objectives during training. Experiments on six benchmark datasets demonstrate that our method outperforms existing hypergraph distillation methods.

Graph unlearning (GU), which removes nodes, edges, or features from trained graph neural networks (GNNs), is crucial in Web applications where graph data may contain sensitive, mislabeled, or malicious information. However, existing GU methods lack a clear understanding of the key factors that determine unlearning effectiveness, leading to three fundamental limitations: (1) impractical and inaccurate GU difficulty assessment due to test-access requirements and invalid assumptions, (2) ineffectiveness on hard-to-unlearn tasks, and (3) misaligned evaluation protocols that overemphasize easy tasks and fail to capture true forgetting capability. To address these issues, we establish GNN memorization as a new perspective for understanding graph unlearning and propose MGU, a Memorization-guided Graph Unlearning framework. MGU achieves three key advances: it provides accurate and practical difficulty assessment across different GU tasks, develops an adaptive strategy that dynamically adjusts unlearning objectives based on difficulty levels, and establishes a comprehensive evaluation protocol that aligns with practical requirements. Extensive experiments on ten real-world graphs demonstrate that MGU consistently outperforms state-of-the-art baselines in forgetting quality, computational efficiency, and utility preservation.

Graph self-supervised learning (GSSL) alleviates the graph data labeling bottleneck without supervision, enabling wide application in domains like recommendation systems and social network analysis. High-frequency signals are valuable in GSSL for capturing local structural preferences, thereby enriching graph representations and boosting model performance. However, in practical applications, two critical problems hinder the efficient and robust use of these signals. First, the locality of high-frequency signals limits their full utilization by the model. Second, over-reliance on specific high-frequency signals will affect the model's generalization. To address the above problems, we propose the Frequency-Corrupt Based Graph Self-Supervised Learning (FC-GSSL) algorithm. Specifically, we generate corrupted graphs biased toward high-frequency signals by corrupting nodes and edges according to their low-frequency contributions. These corrupted graphs are fed as input to an autoencoder, with low-frequency and general features serving as the supervision. This compels the model to effectively fuse high- and low-frequency signals, thereby integrating and utilizing more valuable high-frequency information. Additionally, we design multiple sampling strategies and form diverse corrupted graphs based on the intersections and union between the results obtained from these strategies. By aligning the node representations from these views, the model can identify valuable frequency combinations, which helps reduce the negative impact of specific high-frequency components and improve generalization. FC-GSSL optimizes the design of GSSL for web applications, significantly improving model performance on complex web-related graphs, such as social networks and citation networks. This work makes a direct contribution to advancing the ''Graph Algorithms and Modeling for the Web'' research track. Experimental results on 14 datasets across multiple tasks illustrate the superiority of the proposed approach.

Recently, hypergraph knowledge distillation has been proposed to alleviate the high computational cost of Hypergraph Neural Networks (HGNNs) when modeling high-order relationships in Web-related graph tasks. Its effectiveness primarily depends on the quality of knowledge transferred from the teacher and the representation capability of the student. However, existing methods remain limited on both sides. On the teacher side, most methods typically rely on a single HGNN teacher, which provides limited structural and semantic knowledge, thereby constraining the upper bound of the student's performance. The potential of exploiting multiple teachers in HGNNs remains largely underexplored. On the student side, existing methods ignore the student's capability to capture high-order semantic and structural information beyond simply imitating teacher outputs, leading to limited representation learning. To address these limitations, we propose MARCH, a framework for Multi-TeAcheR Contrastive Hypergraph Distillation, which advances semantic modeling and distillation for Web-scale structured data. Specifically, MARCH proposes a multi-teacher distillation strategy that adaptively transfers complementary knowledge from multiple teachers at both node and hyperedge levels, empowering the student model to learn richer and more discriminative representations and even outperform its teachers. Extensive experiments on six benchmark datasets demonstrate the superior performance of MARCH.

Cross-domain fake news detection (CD-FND) transfers knowledge from a source domain to a target domain and is crucial for real-world fake news mitigation. This task becomes particularly important yet more challenging when the target domain is previously unseen (e.g., the COVID-19 outbreak or the Russia-Ukraine war). However, existing CD-FND methods overlook such scenarios and consequently suffer from the following two key limitations: (1) insufficient modeling of high-level semantics in news and user engagements; and (2) scarcity of labeled data in unseen domains. Targeting these limitations, we find that large language models (LLMs) offer strong potential for CD-FND on unseen domains, yet their effective use remains non-trivial. Nevertheless, two key challenges arise: (1) how to capture high-level semantics from both news content and user engagements using LLMs; and (2) how to make LLM-generated features more reliable and transferable for CD-FND on unseen domains. To tackle these challenges, we propose DAUD, a novel LLM-based Domain-Aware framework for fake news detection on Unseen Domains. DAUD employs LLMs to extract high-level semantics from news content. It models users' single- and cross-domain engagements to generate domain-aware behavioral representations. In addition, DAUD captures the relations between original data-driven features and LLM-derived features of news, users, and user engagements. This allows it to extract more reliable domain-shared representations that improve knowledge transfer to unseen domains. Extensive experiments on real-world datasets demonstrate that DAUD outperforms state-of-the-art baselines in both general and unseen-domain CD-FND settings.

Exact algorithms, known for high computational efficiency and stability, are among the mainstream methods for solving practical optimization problems, but their performance deteriorates significantly when tackling complex problems. Intelligent optimization algorithms with self-organizing, adaptability and self-learning characteristics are better suited for complex problems but have longer runtimes, which hinders rapid response. Given this, this paper proposes a data-driven constrained multi-objective dual-layer autonomous intelligent optimization method that utilizes the complementary advantages of exact and intelligent algorithms to solve constrained multi-objective optimization problems with different response time requirements. In the first layer, an evaluation rule based on preference information enables a unified comparison of the performance of exact and intelligent algorithms, thereby identifying algorithm categories suitable for solving problems based on their requirements. In the second layer, the most suitable algorithms are generated based on problem characteristics and response time requirements. The proposed method is applied to six benchmark test problems and the operation optimization problems of integrated coal mine energy systems, and the experimental results verify its effectiveness and feasibility.

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.

Content recommender systems (RSs), which recommend content (e.g., news, videos) to users, can inadvertently facilitate the spread of misinformation (e.g., fake news, inaccurate content) due to their ignorance of content credibility. The widespread misinformation can lead to serious consequences, including public confusion and social unrest. Despite the pressing need to mitigate misinformation in content RSs, only a few studies have attempted to tackle this. Moreover, they generally require retraining the entire model from scratch, which is time-consuming and impractical for real-world applications. To this end, we propose MisEraser , a novel misinformation unlearning framework that effectively mitigates misinformation in content RSs without retraining. Specifically, MisEraser consists of three key components: (1) A misinformation disentanglement network , which effectively separates misinformation-specific information from item content while preserving misinformation-free information to maintain recommendation accuracy; (2) A misinformation fusion network , which fuses misinformation-specific signals from both users’ interaction sequences and the entire misinformation item set to enhance the comprehensiveness of misinformation unlearning; and (3) A misinformation erasing network , which effectively removes the fused misinformation-specific signals from trained recommendation models, enabling them to generate misinformation-suppressed and more responsible recommendations. Extensive experiments demonstrate the effectiveness of MisEraser in mitigating misinformation while maintaining high recommendation accuracy and efficiency.

Sequential Recommenders (SRs) are trained to predict the next item as the target given its preceding items as the input, assuming every input-target pair is matched and is reliable for training. However, users can be induced by external distractions to click on items inconsistent with their true preferences, resulting in unreliable training instances with mismatched input-target pairs. To resist unreliable data, researchers attempt to develop Robust SRs (RSRs). However, our data analysis unveils that existing RSRs are data-driven. That is, for most instances formed by infrequently co-occurred items, existing RSRs are uncertain about their reliability. To fill this gap, we propose a generic framework -- LLM4RSR (Large Language Models for Robust Sequential Recommendation) to semantically complement data-driven RSRs by correcting uncertain instances into reliable ones based on LLMs' semantic comprehension of items beyond co-occurrence. In this way, RSRs can be re-trained with the corrected data for better accuracy. This is a selective knowledge distillation procedure, where the LLM acts as a teacher guiding student RSRs via uncertain instances. To align LLMs with the data correction task and mitigate inherent hallucinations, we equip the LLM with profile, plan, and memory modules, which are automatically optimized via textual gradient descent, eliminating the need for human effort and expertise. Experiments on four real-world datasets spanning eight backbones verify the generality, effectiveness, and efficiency of LLM4RSR.

Deep multi-view clustering methods utilize information from multiple views to achieve enhanced clustering results and have gained increasing popularity in recent years. Most existing methods typically focus on either inter-view or intra-view relationships, aiming to align information across views or analyze structural patterns within individual views. However, they often incorporate inter-view complementary information in a simplistic manner, while overlooking the complex, high-order relationships within multi-view data and the interactions among samples, resulting in an incomplete utilization of the rich information available. Instead, we propose a multi-scale approach that exploits all of the available information. We first introduce a dual graph diffusion module guided by a consensus graph. This module leverages inter-view information to enhance the representation of both nodes and edges within each view. Secondly, we propose a novel contrastive loss function based on hypergraphs to more effectively model and leverage complex intra-view data relationships. Finally, we propose to adaptively learn fusion weights at the sample level, which enables a more flexible and dynamic aggregation of multi-view information. Extensive experiments on eight datasets show favorable performance of the proposed method compared to state-of-the-art approaches, demonstrating its effectiveness across diverse scenarios.

Neural network-based Marked Temporal Point Process (MTPP) models have been widely adopted to model event sequences in high-stakes applications, raising concerns about the trustworthiness of outputs from these models. This study focuses on Explanation for MTPP, aiming to identify the minimal and rational explanation, that is, the minimum subset of events in history, based on which the prediction accuracy of MTPP matches that based on full history to a great extent and better than that based on the complement of the subset. This study finds that directly defining Explanation for MTPP as counterfactual explanation or factual explanation can result in irrational explanations. To address this issue, we define Explanation for MTPP as a combination of counterfactual explanation and factual explanation. This study proposes Counterfactual and Factual Explainer for MTPP (CFF) to solve Explanation for MTPP with a series of deliberately designed techniques. Experiments demonstrate the correctness and superiority of CFF over baselines regarding explanation quality and processing efficiency.

Graph unlearning, which deletes graph elements such as nodes and edges from trained graph neural networks (GNNs), is crucial for real-world applications where graph data may contain outdated, inaccurate, or privacy-sensitive information. However, existing methods often suffer from (1) incomplete or over unlearning due to neglecting the distinct objectives of different unlearning tasks, and (2) inaccurate identification of neighbors affected by deleted elements across various GNN architectures. To address these limitations, we propose AGU, a novel Adaptive Graph Unlearning framework that flexibly adapts to diverse unlearning tasks and GNN architectures. AGU ensures the complete forgetting of deleted elements while preserving the integrity of the remaining graph. It also accurately identifies affected neighbors for each GNN architecture and prioritizes important ones to enhance unlearning performance. Extensive experiments on seven real-world graphs demonstrate that AGU outperforms existing methods in terms of effectiveness, efficiency, and unlearning capability.

To enhance the reliability and credibility of graph neural networks (GNNs) and improve the transparency of their decision logic, a new field of explainability of GNNs (XGNN) has emerged. However, two major limitations severely degrade the performance and hinder the generalizability of existing XGNN methods: they (a) fail to capture the complete decision logic of GNNs across diverse distributions in the entire dataset's sample space, and (b) impose strict prerequisites on edge properties and GNN internal accessibility. To address these limitations, we propose OPEN, a novel cOmprehensive and Prerequisite-free Explainer for GNNs. OPEN, as the first work in the literature, can infer and partition the entire dataset's sample space into multiple environments, each containing graphs that follow a distinct distribution. OPEN further learns the decision logic of GNNs across different distributions by sampling subgraphs from each environment and analyzing their predictions, thus eliminating the need for strict prerequisites. Experimental results demonstrate that OPEN captures nearly complete decision logic of GNNs, outperforms state-of-the-art methods in fidelity while maintaining similar efficiency, and enhances robustness in real-world scenarios.

Marked Temporal Point Process (MTPP) has been well studied to model the event distribution in marked event streams, which can be used to predict the mark and arrival time of the next event. However, existing studies overlook that the distribution of event marks is highly imbalanced in many real-world applications, with some marks being frequent but others rare. The imbalance poses a significant challenge to the performance of the next event prediction, especially for events of rare marks. To address this issue, we propose a thresholding method, which learns thresholds to tune the mark probability normalized by the mark's prior probability to optimize mark prediction, rather than predicting the mark directly based on the mark probability as in existing studies. In conjunction with this method, we predict the mark first and then the time. In particular, we develop a novel neural Marked Temporal Point Process (MTPP) model to support effective time sampling and estimation of mark probability without computationally expensive numerical improper integration. Extensive experiments on real-world datasets demonstrate the superior performance of our solution against various baselines for the next event mark and time prediction. The code is available at https://github.com/undes1red/IFNMTPP.

Cross-domain fake news detection aims to mitigate domain shift and improve detection performance by transferring knowledge across domains. Existing approaches transfer knowledge based on news content and user engagements from a source domain to a target domain. However, these approaches face two main limitations, hindering effective knowledge transfer and optimal fake news detection performance. Firstly, from a micro perspective, they neglect the negative impact of veracity-irrelevant features in news content when transferring domain-shared features across domains. Secondly, from a macro perspective, existing approaches ignore the relationship between user engagement and news content, which reveals shared behaviors of common users across domains and can facilitate more effective knowledge transfer. To address these limitations, we propose a novel macro- and micro- hierarchical transfer learning framework (MMHT) for cross-domain fake news detection. Firstly, we propose a micro-hierarchical disentangling module to disentangle veracity-relevant and veracity-irrelevant features from news content in the source domain for improving fake news detection performance in the target domain. Secondly, we propose a macro-hierarchical transfer learning module to generate engagement features based on common users' shared behaviors in different domains for improving effectiveness of knowledge transfer. Extensive experiments on real-world datasets demonstrate that our framework significantly outperforms the state-of-the-art baselines.

Dynamic multiobjective evolutionary algorithms (DMOEAs) have gained great popularity in dealing with the dynamic multiobjective optimization problems (DMOPs). However, the existing studies have difficulties in tackling DMOPs subject to (dynamic) constraints. In this article, we propose a prediction and weak coevolutionary multiobjective optimization algorithm (PWDCMO) to handle the dynamic constrained multiobjective optimization problems (DCMOPs), where a prediction strategy is employed to forecast potential optimal regions under the new environment, with a weak coevolutionary constrained multiobjective optimization (CCMO) as the optimizer aiming at balancing exploration and convergence. The proposed method is compared with the four popular dynamic constrained multiobjective evolutionary algorithms (DCMOEAs) on six test instances from two various test suites with their convergence and the overall performance being discussed. Furthermore, the performance of the proposed prediction strategy is also investigated to observe its impact on the final results. Additionally, the PWDCMO is employed in the optimization of an integrated coal mine energy system (ICMES) to validate the proficiency in addressing real world problems. Experimental results demonstrate the superiority of PWDCMO.

To address the issue of label sparsity in heterogeneous graphs (HGs), heterogeneous graph few-shot learning (HGFL) has recently emerged. HGFL aims to extract meta-knowledge from source HGs with rich-labeled data and transfers it to a target HG, facilitating learning new classes with few-labeled training data and improving predictions on unlabeled testing data. Existing methods typically assume the same distribution across the source HG, training data, and testing data. However, in practice, distribution shifts in HGFL are inevitable due to (1) the scarcity of source HGs that match the target HG's distribution, and (2) the unpredictable data generation mechanism of the target HG. Such distribution shifts can degrade the performance of existing methods, leading to a novel problem of out-of-distribution (OOD) generalization in HGFL. To address this challenging problem, we propose COHF, aCausalOODHeterogeneous graphFew-shot learning model. In COHF, we first adopt a bottom-up data generative perspective to identify the invariance principle for OOD generalization. Then, based on this principle, we design a novel variational autoencoder-based heterogeneous graph neural network (VAE-HGNN) to mitigate the impact of distribution shifts. Finally, we propose a novel meta-learning framework that incorporates VAE-HGNN to effectively transfer meta-knowledge in OOD environments. Extensive experiments on seven real-world datasets have demonstrated the superior performance of COHF over the state-of-the-art methods.

Disentanglement techniques used in collaborative filtering uncover interaction intents between nodes, improving the interpretability of node representations and enhancing recommendation performance. However, existing disentanglement methods still face the following two problems. 1) They focus on local structural features derived from direct node interactions, overlooking the comprehensive graph structure, which limits disentanglement accuracy. 2) The disentanglement process depends on backpropagation signals derived from recommendation tasks, lacking direct supervision, which may lead to biases and overfitting. To address the issues, we propose theIntentPropagationContrastiveCollaborativeFiltering (IPCCF) algorithm. Specifically, we design a double helix message propagation framework to more effectively extract the deep semantic information of nodes, thereby improving the model's understanding of interactions between nodes. An intent message propagation method is also developed that incorporates graph structure information into the disentanglement process, thereby expanding the consideration scope of disentanglement. In addition, contrastive learning techniques are employed to align node representations derived from the structure and intents, providing direct supervision for the disentanglement process, mitigating biases, and enhancing the model's robustness to overfitting. The experiments on three real data graphs illustrate the superiority of the proposed approach.

The sparse portfolio optimization (SPO) problem is increasingly crucial in portfolio management, focusing on selecting a few stocks with the potential for strong market performance. However, sparse portfolio strategies often face significant short-term drawdowns during periods of market volatility. To this end, a news-driven portfolio strategy offers valuable insights to capture sudden market changes. Nevertheless, it encounters two main challenges:how to reasonably map the relationships between news and stocksandhow to effectively utilize the irregular timing of news releases. To tackle the SPO problem in fluctuating markets while addressing these challenges, we propose a novel news-driven sparse portfolio strategy, named SPIN. Specifically, SPIN not only leverages industry-specific group structures existing among stocks for a more reasonable news-stock mapping and models news sequential patterns based on our devised novel news-driven forecaster to handle the irregularity of news releases. We rigorously prove that SPIN achieves a sub-linear regret. Extensive experiments on three real-world datasets demonstrate SPIN's superiority over state-of-the-art portfolio strategies in terms of cumulative wealth and short-term drawdowns.

In recent years, dual-target Cross-Domain Recommendation (CDR) has been proposed to capture comprehensive user preferences in order to ultimately enhance the recommendation accuracy in both data-richer and data-sparser domains simultaneously. However, in addition to users’ true preferences, the user–item interactions might also be affected by confounders (e.g., free shipping, sales promotion). As a result, dual-target CDR has to meet two challenges: (1) how to effectively decouple observed confounders, including single-domain confounders and cross-domain confounders, and (2) how to preserve the positive effects of observed confounders on predicted interactions, while eliminating their negative effects on capturing comprehensive user preferences. To address the above two challenges, we propose a Causal Deconfounding Framework via Confounder Disentanglement for Dual-Target Cross-Domain Recommendation (CD2CDR) . In CD2CDR, we first propose a confounder disentanglement module to effectively decouple observed single-domain and cross-domain confounders. We then propose a causal deconfounding module to preserve the positive effects of such observed confounders and eliminate their negative effects via backdoor adjustment, thereby enhancing the recommendation accuracy in each domain. Extensive experiments conducted on seven real-world datasets demonstrate that CD2CDR significantly outperforms the state-of-the-art methods.

Large language model-based explainable recommendation (LLM-based ER) systems can provide remarkable human-like explanations and have widely received attention from researchers. However, the original LLM-based ER systems face three low-quality problems in their generated explanations, i.e., lack of personalization, inconsistency, and questionable explanation data. To address these problems, we propose a novel LLM-based ER model denoted as LLM2ER to serve as a backbone and devise two innovative explainable quality reward models for fine-tuning such a backbone in a reinforcement learning paradigm, ultimately yielding a fine-tuned model denoted as LLM2ER-EQR, which can provide high-quality explanations. LLM2ER-EQR can generate personalized, informative, and consistent high-quality explanations learned from questionable-quality explanation datasets. Extensive experiments conducted on three real-world datasets demonstrate that our model can generate fluent, diverse, informative, and highly personalized explanations.

Recommendation systems aim to provide users with relevant suggestions, but often lack interpretability and fail to capture higher-level semantic relationships between user behaviors and profiles. In this paper, we propose a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs. These graphs link a user's profile and behavioral sequences through causal and logical inferences, representing the user's interests in an interpretable way. Our approach, LLM reasoning graphs (LLMRG), has four components: chained graph reasoning, divergent extension, self-verification and scoring, and knowledge base self-improvement. The resulting reasoning graph is encoded using graph neural networks, which serves as additional input to improve conventional recommender systems, without requiring extra user or item information. Our approach demonstrates how LLMs can enable more logical and interpretable recommender systems through personalized reasoning graphs. LLMRG allows recommendations to benefit from both engineered recommendation systems and LLM-derived reasoning graphs. We demonstrate the effectiveness of LLMRG on benchmarks and real-world scenarios in enhancing base recommendation models.

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased representations and rely solely on steering prompts. However, the representations learned from pre-training can introduce semantic biases that influence the steering process, leading to suboptimal results. We propose LLMGuardrail, a novel framework that incorporates causal analysis and adversarial learning to obtain unbiased steering representations in LLMs. LLMGuardrail systematically identifies and blocks the confounding effects of biases, enabling the extraction of unbiased steering representations. Experiments demonstrate LLMGuardrail's effectiveness in steering LLMs toward desired attributes while mitigating biases. Our work contributes to developing safe and reliable LLMs that align with desired attributes.

Transfer of knowledge across domains is the focus for cross-domain and multi-domain fake news detection. However, most of the existing methods based on cross-domain knowledge transfer have two issues: (1) they usually ignore domain-specific features; (2) they are less effective in handling the imbalanced data distribution across domains. Targeting these two issues, we focus on how to effectively leverage user-news engagements in both data-richer and data-sparser domains. This is because not only users' engagement characteristics closely relate to the veracity of the engaged news, but also there are consistent patterns in common users' engagements with news across domains. Considering these two insights, this work aims to perform dual-target cross-domain fake news detection via well modeling users' engagement patterns. In particular, it aims to transfer knowledge based on user-news engagements for handling the imbalanced data distribution across domains, which is novel but challenging. To this end, in this paper, we propose a novel framework to mine User-news engagement Patterns for DuAl-TargEt cross-domain fake news detection (UPDATE). In UPDATE, we first mine user-news engagement patterns as the key auxiliary information for cross-domain knowledge transfer. In such a way, it avoids the necessity to remove the domain-specific news information, and thereby, better preserve useful news information. Then, we combine engagement features of common users in both data-richer and data-sparser domains. By doing so, UPDATE improves the information richness in each of the two domains, thus improving detection performance in both domains when detecting news from domains with imbalanced data distribution. Extensive experiments conducted on real-world datasets demonstrate that UPDATE significantly outperforms state-of-the-art cross-domain and multi-domain methods as well as large language models (LLMs), such as GPT-3.5-turbo in terms of AUC and Fl-score for fake news detection.

Neural temporal point processes(TPPs) have shown promise for modeling continuous-time event sequences. However, capturing the interactions between events is challenging yet critical for performing inference tasks like forecasting on event sequence data. Existing TPP models have focused on parameterizing the conditional distribution of future events but struggle to model event interactions. In this paper, we propose a novel approach that leverages Neural Relational Inference (NRI) to learn a relation graph that infers interactions while simultaneously learning the dynamics patterns from observational data. Our approach, the Contrastive Relational Inference-based Hawkes Process (CRIHP), reasons about event interactions under a variational inference framework. It utilizes intensity-based learning to search for prototype paths to contrast relationship constraints. Extensive experiments on three real-world datasets demonstrate the effectiveness of our model in capturing event interactions for event sequence modeling tasks.

With neural networks growing deeper and feature maps growing larger, limited communication bandwidth with external memory (or DRAM) and power constraints become a bottle-neck in implementing network inference on mobile and edge devices. In this paper, we propose an end-to-end differentiable bandwidth efficient neural inference method with the activation compressed by neural data compression method. Specifically, we propose a transform-quantization-entropy coding pipeline for activation compression with symmetric exponential Golomb coding and a data-dependent Gaussian entropy model for arithmetic coding. Optimized with existing model quantization methods, low-level task of image compression can achieve up to 19× bandwidth reduction with 6.21× energy saving. The code implementation is available at https://github.com/xyzysz/Bandwidth_efficient_nic.

Crowdsourced Named Entity Recognition (CNER) is an effective method in social network data mining, enabling the swift identification and categorization of vast textual data, thereby enhancing the understanding and analysis of user behaviors and communication patterns. However, the diversity of such data often leads to inconsistent annotation quality, compromising recognition accuracy. We propose a novel framework that synergizes reinforcement learning with multi-source domain adaptation to bolster the accuracy of social CNER. By filtering out low-quality instances and considering annotator reliability in the multi-source domain adaptation crowdsourcing method, our framework not only adapts to the varied quality of annotations but also mitigates the impact of annotation noise. Validated on both the social network crowdsourced benchmark dataset FMKKM11 and the general-purpose CoNLL03, our method consistently outperforms state-of-the-art methods in terms of model accuracy and noise robustness.

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.

Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive models, making a significant impact in both academic and application communities. Despite the emergence of many powerful models in recent years, there hasn't been a central benchmark for these models and future research endeavors. This lack of standardization impedes researchers and practitioners from comparing methods and reproducing results, potentially slowing down progress in this field. In this paper, we present EasyTPP, the first central repository of research assets (e.g., data, models, evaluation programs, documentations) in the area of event sequence modeling. Our EasyTPP makes several unique contributions to this area: a unified interface of using existing datasets and adding new datasets; a wide range of evaluation programs that are easy to use and extend as well as facilitate reproducible research; implementations of popular neural TPPs, together with a rich library of modules by composing which one could quickly build complex models. We will actively maintain this benchmark and welcome contributions from other researchers and practitioners. Our benchmark will help promote reproducible research in this field, thus accelerating research progress as well as making more significant real-world impacts. The code and data are available at \url{https://github.com/ant-research/EasyTemporalPointProcess}.

In the era of information explosion, news recommender systems are crucial for users to effectively and efficiently discover their interested news. However, most of the existing news recommender systems face two major issues, hampering recommendation quality. Firstly, they often oversimplify users' reading interests, neglecting their hierarchical nature, spanning from high-level event (e.g., US Election) related interests to low-level news article-specifc interests. Secondly, existing work often assumes a simplistic context, disregarding the prevalence of fake news and political bias under the real-world context. This oversight leads to recommendations of biased or fake news, posing risks to individuals and society. To this end, this paper addresses these gaps by introducing a novel framework, the Hierarchical and Disentangling Interest learning framework (HDInt). HDInt incorporates a hierarchical interest learning module and a disentangling interest learning module. The former captures users' high- and low-level interests, enhancing next-news recommendation accuracy. The latter effectively separates polarity and veracity information from news contents and model them more specifcally, promoting fairness- and truth-aware reading interest learning for unbiased and true news recommendations. Extensive experiments on two real-world datasets demonstrate HDInt's superiority over state-of-the-art news recommender systems in delivering accurate, unbiased, and true news recommendations.

The goal of intent-aware session recommendation (ISR) approaches is to capture user intents within a session for accurate next-item prediction. However, the capability of these approaches is limited by assuming all sessions have a uniform and fixed number of intents. In reality, user sessions can vary, where the number of intentions may differ from one to another. Moreover, they can only learn user intents in the latent space, which further restricts the model's transparency. To ease these issues, we propose a simple yet effective paradigm for ISR motivated by the advanced reasoning capability of large language models (LLMs). Specifically, we first create an initial prompt to instruct LLMs to predict the next item by inferring varying user intents reflected in a session. Then, we propose an effective optimization mechanism to automatically optimize prompts with an iterative self-reflection. Finally, we leverage the robust generalizability of LLMs across diverse domains to efficiently select the optimal prompt for ISR. As such, the proposed paradigm effectively guides LLMs to identify varying user intents at a semantic level, thus delivering more accurate and comprehensible recommendations. Extensive experiments on three real-world datasets verify the superiority of our proposed method.

Unmanned aerial vehicles (UAVs) equipped with high definition (HD) cameras, intelligent sensors, computing, and communication modules can be deployed to execute crowdsensing tasks by leveraging federated learning (FL), e.g., air quality perception and ground target detection. FL can reduce transmission stress and protect data privacy when training models, which is suitable for resource constrained Internet of UAVs. Nevertheless, the incentive issues about information asymmetry and bounded rationality impede the applications of FL-enabled Internet of UAVs. The existing FL incentive approaches focus on the risk-free condition, where task publishers are capable of making decisions with complete rationality by utilizing expected utility theory. In fact, task publishers under risk conditions are often bounded rational, whose risk-awareness makes the utility models more sophisticated. To overcome the above problems, we present a prospect theory (PT)-based incentive mechanism for FL-enabled Internet of UAVs. We first leverage PT to model the task publisher’s risk-awareness behavior and construct the subjective utility model. Thereafter, we utilize the framing effect of PT to design the optimal contract to maximize the subjective utility. Simulation results demonstrate that, compared with the baseline method, the proposed incentive mechanism has better performance.

Urban rail transit can alleviate traffic congestion if sufficient ridership is achieved. The accessibility to rail transit stations largely determines public willingness to utilize urban rail transit. The current studies on the accessibility to rail transit stations tend to concentrate solely on individual rail transit lines or stations, neglecting the impact of the external macro-environment. Consequently, the outcomes of these measurements cannot accurately reflect the overall accessibility level of the region, nor do they furnish decision-makers with references for devising plans for rail transit development. This study introduces a novel approach for evaluating the accessibility to urban rail transit stations from a macro-level standpoint, utilizing expert knowledge. The study conducts an analysis of the impact of political, economic, social, and technological factors on the accessibility to rail transit stations in urban areas. Subsequently, a comprehensive evaluation indicator system is developed based on the aforementioned analysis. Then, experts are summoned to provide their subjective evaluations for every indicator, which are depicted as probability distribution functions. The collective evaluation is derived through the aggregation of individual evaluations utilizing a bi-objective optimization approach that factors in both the collective fairness utility and the confidence level. Finally, the Quantile Average method is employed to consolidate the collective assessment outcomes of individual indicators, thereby deriving the level of accessibility to rail transit stations in urban areas. We design a small-scale application experiment and attempt to evaluate the accessibility to rail transit stations in Wuchang District, Wuhan with the proposed approach in order to demonstrate the feasibility of the approach.

Various real-world problems can be attributed to constrained multiobjective optimization problems (CMOPs). Although there are various solution methods, it is still very challenging to automatically select efficient solving strategies for CMOPs. Given this, a process knowledge-guided constrained multiobjective autonomous evolutionary optimization method is proposed. First, the effects of different solving strategies on population states are evaluated in the early evolutionary stage. Then, the mapping model of population states and solving strategies is established. Finally, the model recommends subsequent solving strategies based on the current population state. This method can be embedded into existing evolutionary algorithms, which can improve their performances to different degrees. The proposed method is applied to 41 benchmarks and 30 dispatch optimization problems of the integrated coal mine energy system. Experimental results verify the effectiveness and superiority of the proposed method in solving CMOPs.

The operation optimization problem of coal mine integrated energy system (CMIES) is characterized by multiobjective, strong constraints, large scale, and mixed variables. It is difficult for existing multiobjective evolutionary algorithms to obtain a set of nondominated solutions with good convergence and uniform distribution, primarily due to the absence of suitable constraint-handling techniques. This research proposes a multitask multiobjective operation optimization framework combining evolutionary algorithm and mathematical programming (MO-EAMP) to address this issue. Within this framework, the main task employs an evolutionary algorithm with global search capability to solve the multiobjective CMIES operation optimization problem. Meanwhile, auxiliary tasks utilize mathematical programming method with robust linear constraint handling capability to solve multiple weighted single-objective CMIES operation optimization problems. During the iteration process of MO-EAMP, the scale and form of auxiliary tasks are adjusted autonomously based on the current state of population, with the aim of guiding the population search toward more promising regions. Finally, the presented algorithm is applied to a coal mine in Shanxi Province, China, and the experimental results demonstrate that the proposed algorithm can obtain a set of optimal operation plans with better convergence and distribution in a shorter time, compared with 7 other existing algorithms.

Recommender systems (RSs) aim at helping users to effectively retrieve items of their interests from a large catalogue. For a quite long time, researchers and practitioners have been focusing on developing accurate RSs. Recent years have witnessed an increasing number of threats to RSs, coming from attacks, system and user generated noise, and various types of biases. As a result, it has become clear that the focus on RS accuracy is too narrow, and the research must consider other important factors, particularly trustworthiness. A trustworthy recommender system (TRS) should not only be accurate but also transparent, unbiased, fair, and robust to noise and attacks. These observations actually led to a paradigm shift of the research on RSs: from accuracy-oriented RSs to TRSs. However, there is a lack of a systematic overview and discussion of the literature in this novel and fast-developing field of TRSs. To this end, in this article, we provide an overview of TRSs, including a discussion of the motivation and basic concepts of TRSs, a presentation of the challenges in building TRSs, and a perspective on the future directions in this area. We also provide a novel conceptual framework to support the construction of TRSs.

In recent years, to address the issue of networked data sparsity in node classification tasks, cross-network node classification (CNNC) leverages the richer information from a source network to enhance the performance of node classification in the target network, which typically has sparser information. However, in real-world applications, labeled nodes may be collected from multiple sources with multiple modalities (e.g., text, vision, and video). Naive application of single-source and single-modal CNNC methods may result in sub-optimal solutions. To this end, in this article, we propose a model called Multi-source and Multi-modal Cross-network Deep Network Embedding (M 2 CDNE) for cross-network node classification. In M 2 CDNE, we propose a deep multi-modal network embedding approach that combines the extracted deep multi-modal features to make the node vector representations network invariant. In addition, we apply dynamic adversarial adaptation to assess the significance of marginal and conditional probability distributions between each source and target network to make node vector representations label discriminative. Furthermore, we devise to classify nodes in the target network through the related source classifier and aggregate different predictions utilizing respective network weights, corresponding to the discrepancy between each source and target network. Extensive experiments performed on real-world datasets demonstrate that the proposed M 2 CDNE significantly outperforms the state-of-the-art approaches.

Federated Learning empowers data owners to collectively train an artificial intelligence model without exposing data. However, the heterogeneous resources and the self-interested users bring new challenges hindering the development of federated learning. To this end, we propose a Multi-attribute Auction-based Grouped Federated Learning scheme, called MAGFL, comprising a grouped federated learning framework and a multi-attribute auction-based group selection strategy. Initially, our grouped federated learning framework clusters clients into groups according to local characteristics. Then, we propose a quality assessment method to assess the quality of each group based on a fuzzy approach. Furthermore, the FL server distributes economic rewards to training clients to motivate more clients to join the FL system, which is likened to a multi-attribute auction market where each group agent bids for training opportunities. Moreover, we design a novel global model update method with added Adam (i.e., Adaptive Moment Estimation) operations into the global update stage, which can fully utilize the local and global update direction to accelerate the convergence rate of scheme MGAFL. Extensive experiments on real-world datasets demonstrate that the proposed scheme outperforms representative federated learning schemes (i.e., FedAvg, FedProx, and FedAvg-Adam) regarding the model's convergence rate and capacity to deal with heterogeneous systems.

Positive Unlabeled (PU) learning, which has a wide range of applications, is becoming increasingly prevalent. However, it suffers from problems such as data imbalance, selection bias, and prior agnostic in real scenarios. Existing studies focus on addressing part of these problems, which fail to provide a unified perspective to understand these problems. In this paper, we first rethink these problems by analyzing a typical PU scenario and come up with an insightful point of view that all these problems are inherently connected to one problem, i.e., positive distribution pollution, which refers to the inaccuracy in estimating positive data distribution under very little labeled data. Then, inspired by this insight, we devise a variational model named CoVPU, which addresses all three problems in a unified perspective by targeting the positive distribution pollution problem. CoVPU not only accurately separates the positive data from the unlabeled data based on discrete normalizing flows, but also effectively approximates the positive distribution based on our derived unbiased rebalanced risk estimator and supervises the approximation based on a novel prior-free variational loss. Rigorous theoretical analysis proves the convergence of CoVPU to an optimal Bayesian classifier. Extensive experiments demonstrate the superiority of CoVPU over the state-of-the-art PU learning methods under these problems.

In recent years, heterogeneous graph few-shot learning has been proposed to address the label sparsity issue in heterogeneous graphs (HGs), which contain various types of nodes and edges. The existing methods have achieved good performance by transferring generalized knowledge extracted from rich-labeled classes in source HG(s) to few-labeled classes in a target HG. However, these methods only consider the single-heterogeneity scenario where the source and target HGs share a fixed set of node/edge types, ignoring the more general scenario of cross-heterogeneity, where each HG can have a different and non-fixed set of node/edge types. To this end, we focus on the unexplored cross-heterogeneity scenario and propose a novel model for Cross-heterogeneity Graph Few-shot Learning, namely CGFL. In CGFL, we first extract meta-patterns to capture heterogeneous information and propose a multi-view heterogeneous graph neural network (MHGN) to learn meta-patterns across HGs. Then, we propose a score module to measure the informativeness of labeled samples and determine the transferability of each source HG. Finally, by integrating MHGN and the score module into a meta-learning mechanism, CGFL can effectively transfer generalized knowledge to predict new classes with few-labeled data. Extensive experiments on four real-world datasets have demonstrated the superior performance of CGFL over the state-of-the-art methods.

Predictive Autoscaling is used to forecast the workloads of servers and prepare the resources in advance to ensure service level objectives (SLOs) in dynamic cloud environments. However, in practice, its prediction task often suffers from performance degradation under abnormal traffics caused by external events (such as sales promotional activities and applications' re-configurations), for which a common solution is to re-train the model with data of a long historical period, but at the expense of high computational and storage costs. To better address this problem, we propose a replay-based continual learning method, i.e., Density-based Memory Selection and Hint-based Network Learning Model (DMSHM), using only a small part of the historical log to achieve accurate predictions. First, we discover the phenomenon of sample overlap when applying replay-based continual learning in prediction tasks. In order to surmount this challenge and effectively integrate new sample distribution, we propose a density-based sample selection strategy that utilizes kernel density estimation to calculate sample density as a reference to compute sample weight, and employs weight sampling to construct a new memory set. Then we implement hint-based network learning based on hint representation to optimize the parameters. Finally, we conduct experiments on public and industrial datasets to demonstrate that our proposed method outperforms state-of-the-art continual learning methods in terms of memory capacity and prediction accuracy. Furthermore, we demonstrate remarkable practicability of DMSHM in real industrial applications.

Face recognition service providers protect face privacy by extracting compact and discriminative facial features (representations) from images, and storing the facial features for real-time recognition. However, such features can still be exploited to recover the appearance of the original face by building a reconstruction network. Although sev-eral privacy-preserving methods have been proposed, the enhancement offace privacy protection is at the expense of accuracy degradation. In this paper, we propose an adver-sarial features-based face privacy protection (AdvFace) approach to generate privacy-preserving adversarial features, which can disrupt the mapping from adversarial features to facial images to defend against reconstruction attacks. To this end, we design a shadow model which simulates the attackers' behavior to capture the mapping function from facial features to images and generate adversarial la-tent noise to disrupt the mapping. The adversarial features rather than the original features are stored in the server's database to prevent leaked features from exposing facial information. Moreover, the AdvFace requires no changes to the face recognition network and can be implemented as a privacy-enhancing plugin in deployed face recognition systems. Extensive experimental results demonstrate that Adv Face outperforms the state-of-the-art face privacy-preserving methods in defending against reconstruction at-tacks while maintaining face recognition accuracy.

In recommendation scenarios, there are two long-standing challenges, i.e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks. To cope with these issues, existing works emphasize on leveraging Multi-Task Learning (MTL) frameworks (Category 1) or causal debiasing frameworks (Category 2) to incorporate more auxiliary data in the entire exposure/inference space $\mathcal{D}$ or debias the selection bias in the click/training space ${\mathcal{O}}$. However, these two kinds of solutions cannot effectively address the not-missing-at-random problem and debias the selection bias in ${\mathcal{O}}$ to fit the inference in $\mathcal{D}$. To fill the research gaps, we propose a Direct entire-space Causal Multi-Task framework, namely DCMT, for post-click conversion prediction in this paper. Specifically, inspired by users’ decision process of conversion, we propose a new counterfactual mechanism to debias the selection bias in $\mathcal{D}$, which can predict the factual CVR and the counterfactual CVR under the soft constraint of a counterfactual prior knowledge. Extensive experiments demonstrate that our DCMT can improve the state-of-the-art methods by an average of 1.07% in term of CVR AUC on the offline datasets and 0.75% in term of PV-CVR on the online A/B test (the Alipay Search). Such improvements can increase millions of conversions per week in real industrial applications, e.g., the Alipay Search.

As an emerging technology, federated learning (FL) plays a critical role for information sharing in industrial Internet of Things (IIoT). FL integrates information from multiple devices to collaboratively train a joint machine learning model locally without sharing the individual training data. Most existing incentive mechanism schemes for FL assume that the task publisher is completely rational and capable of making decisions based on expected utility theory (EUT). However, in reality, the task publisher is characterized as bounded rationality under risks and uncertainties, whose risk-awareness makes EUT inapplicable when making decisions. To tackle the above challenge, a novel incentive mechanism for IIoT-FL based on contract theory and prospect theory is proposed in this paper. We leverage prospect theory to model the task publisher’s risk-awareness behavior. To guarantee high model accuracy while avoiding serious time delay, we take the global model quality and time satisfactory into account when designing the optimal contract. Simulation results demonstrate that our incentive mechanism is effective under asymmetric information and risk.

Federated edge learning (FEEL) is gaining increasing attention due to its characteristics of privacy protection, low latency, and low communication overhead. However, it still faces challenges such as a single point of failure and the imbalance between communication efficiency and training efficiency caused by heterogeneous clients. To address the above issues, we investigate a semi-decentralized FEEL (SD-FEEL) architecture, where edge servers train their local models with the associated clients in a centralized manner and exchange models with their one-hop neighbors distributively. For the upper-layer edge servers, a fully asynchronous aggregation mechanism is proposed to accelerate the model diffusion, while for the lower-layer clients, the proximal policy optimization (PPO) algorithm is employed to dynamically select the aggregation time based on currently available resources. Simulation results show that the proposed algorithm can effectively balance training efficiency and communication efficiency. Besides, the model accuracy of the proposed algorithm is improved by around 4.5% and 11% compared to asynchronous FL and synchronous FL, respectively.

An intelligent optimization algorithm is only valid for solving some problems, which difficultly solves all operation optimization problems of integrated coal mine energy systems with different characteristics. An optimization paradigm usually consists of multiple operators/strategies, each of which is suitable for solving different problems. It is difficult for an operator/strategy to ensure that the population can evolve forward in the evolution process since the state of the population is changing. To this end, a multi-granularity autonomous intelligent optimization method is proposed to optimize the operation of integrated coal mine energy systems with various scenarios. This method automatically determines appropriate optimization paradigms according to problem characteristics and adaptively adjusts optimization operators/strategies based on population states in the evolution process. For the adaptive adjustment of operators/strategies, this paper proposes an adaptive adjustment strategy based on Q-Learning. Taking a coal mine in Shanxi Province, China as the research object, a series of experiments are conducted, and the experimental results show the effectiveness of the proposed algorithm.

Sequential recommender systems (SRSs) are typically trained to predict the next item as the target given its preceding (and succeeding) items as the input. Such a paradigm assumes that every input-target pair is reliable for training. However, users can be induced to click on items that are inconsistent with their true preferences, resulting in unreliable instances, i.e., mismatched input-target pairs. Current studies on mitigating this issue suffer from two limitations: (i) they discriminate instance reliability according to models trained with unreliable data, yet without theoretical guarantees that such a seemingly contradictory solution can be effective; and (ii) most methods can only tackle either unreliable input or targets but fail to handle both simultaneously. To fill the gap, we theoretically unveil the relationship between SRS predictions and instance reliability, whereby two error-bounded strategies are proposed to rectify unreliable targets and input, respectively. On this basis, we devise a model-agnostic Bidirectional Data Rectification (BirDRec) framework, which can be flexibly implemented with most existing SRSs for robust training against unreliable data. Additionally, a rectification sampling strategy is devised and a self-ensemble mechanism is adopted to reduce the (time and space) complexity of BirDRec. Extensive experiments on four real-world datasets verify the generality, effectiveness, and efficiency of our proposed BirDRec.

Neural Temporal Point Processes (TPPs) are the prevalent paradigm for modeling continuous-time event sequences, such as user activities on the web and financial transactions. In real world applications, the event data typically comes in a streaming manner, where the distribution of the patterns may shift over time. Under the privacy and memory constraints commonly seen in real scenarios, how to continuously monitor a TPP to learn the streaming event sequence is an important yet under-investigated problem. In this work, we approach this problem by adopting Continual Learning (CL), which aims to enable a model to continuously learn a sequence of tasks without catastrophic forgetting. While CL for event sequence is less well studied, we present a simple yet effective framework, PromptTPP, by integrating the base TPP with a continuous-time retrieval prompt pool. In our proposed framework, prompts are small learnable parameters, maintained in a memory space and jointly optimized with the base TPP so that the model is properly instructed to learn event streams arriving sequentially without buffering past examples or task-specific attributes. We formalize a novel and realistic experimental setup for modeling event streams, where PromptTPP consistently sets state-of-the-art performance across two real user behavior datasets.

The conventional single-target Cross-Domain Recommendation (CDR) aims to improve the recommendation performance on a sparser target domain by transferring the knowledge from a source domain that contains relatively richer information. By contrast, in recent years, dual-target CDR has been proposed to improve the recommendation performance on both domains simultaneously. However, to this end, there are two challenges in dual-target CDR: (1) how to generate both relevant and diverse augmented user representations, and (2) how to effectively decouple domain-independent information from domain-specific information, in addition to domain-shared information, to capture comprehensive user preferences. To address the above two challenges, we propose a Disentanglement-based framework with Interpolative Data Augmentation for dual-target Cross-Domain Recommendation, called DIDA-CDR. In DIDA-CDR, we first propose an interpolative data augmentation approach to generating both relevant and diverse augmented user representations to augment sparser domain and explore potential user preferences. We then propose a disentanglement module to effectively decouple domain-specific and domain-independent information to capture comprehensive user preferences. Both steps significantly contribute to capturing more comprehensive user preferences, thereby improving the recommendation performance on each domain. Extensive experiments conducted on five real-world datasets show the significant superiority of DIDA-CDR over the state-of-the-art methods.

Most session-based recommender systems (SBRSs) focus on extracting information from the observed items in the current session of a user to predict a next item, ignoring the causes outside the session (called outer-session causes, OSCs) that influence the user’s selection of items. However, these causes widely exist in the real world, and few studies have investigated their role in SBRSs. In this work, we analyze the causalities and correlations of the OSCs in SBRSs from the perspective of causal inference. We find that the OSCs are essentially the confounders in SBRSs, which leads to spurious correlations in the data used to train SBRS models. To address this problem, we propose a novel SBRS framework named COCO-SBRS (COunterfactual COllaborative Session-Based Recommender Systems) to learn the causality between OSCs and user-item interactions in SBRSs. COCO-SBRS first adopts a self-supervised approach to pre-train a recommendation model by designing pseudo-labels of causes for each user’s selection of the item in data to guide the training process. Next, COCO-SBRS adopts counterfactual inference to recommend items based on the outputs of the pre-trained recommendation model considering the causalities to alleviate the data sparsity problem. As a result, COCO-SBRS can learn the causalities in data, preventing the model from learning spurious correlations. The experimental results of our extensive experiments conducted on three real-world datasets demonstrate the superiority of our proposed framework over ten representative SBRSs.

Streaming Recommender Systems (SRSs) have emerged to deliver recommendations based on pervasive data streams, which are a sequence of user-item interactions with multiple behavior types (e.g., purchase, add-to-cart, and view). However, existing SRSs all rely on a single behavior type (e.g., purchase) to make streaming recommendations, and commonly suffer from the data sparsity problem. To address this issue, the relatively more abundant multi-behavior interactions (i.e., interactions with multiple behavior types) could be well leveraged for more accurate streaming recommendations. However, it remains a challenge on how to effectively leverage the commonly-existing and complex multi-behavior interactions for improving the accuracy of streaming recommendations. Targeting at this challenge, we propose the first Multi-behavior Streaming Recommender System in the literature, called MbSRS, to elaborately exploit multi-behavior interactions for delivering accurate recommendations in streaming scenarios. In MbSRS, we first learn instant user preferences and unified item characteristics collaboratively from multi-behavior interactions. Then, we attentively learn long-term user preferences from the historical items interacted by the corresponding users. After that, we wisely fuse the learned instant and long-term user preferences via a gate mechanism. Finally, a novel multi-behavior-specific training process is devised for more effectively learning user preferences towards items from multi-behavior interactions. Extensive experiments on three real-world datasets demonstrate that the proposed MbSRS significantly outperforms the state-of-the-art baselines.

Recent considerable state-of-the-art advancements within the automotive sector, coupled with an evolution of the promising paradigms of vehicle-to-everything communication and the Internet of Vehicles (IoV), have facilitated vehicles to generate and, accordingly, disseminate an enormous amount of safety-critical and non-safety infotainment data in a bid to guarantee a highly safe, convenient, and congestion-aware road transport. These dynamic networks require intelligent security measures to ensure that the malicious messages, along with the vehicles that disseminate them, are identified and subsequently eliminated in a timely manner so that they are not in a position to harm other vehicles. Failing to do so could jeopardize the entire network, leading to fatalities and injuries amongst road users. Several researchers, over the years, have envisaged conventional cryptographic-based solutions employing certificates and the public key infrastructure for enhancing the security of vehicular networks. Nevertheless, cryptographic-based solutions are not optimum for an IoV network primarily, since the cryptographic schemes could be susceptible to compromised trust authorities and insider attacks that are highly deceptive in nature and cannot be noticed immediately and are, therefore, capable of causing catastrophic damage. Accordingly, in this article, a distributed trust management system has been proposed that ascertains the trust of all the reputation segments within an IoV network. The envisaged system takes into consideration the salient characteristics of familiarity, i.e., assessed via a subjective logic approach, similarity, and timeliness to ascertain the weights of all the reputation segments. Furthermore, an intelligent trust threshold mechanism has been developed for the identification and eviction of the misbehaving vehicles. The experimental results suggest the advantages of our proposed IoV-based trust management system in terms of optimizing the misbehavior detection and its resilience to various sorts of attacks.

Automatic tumor or lesion segmentation is a crucial step in medical image analysis for computer-aided diagnosis. Although the existing methods based on convolutional neural networks (CNNs) have achieved the state-of-the-art performance, many challenges still remain in medical tumor segmentation. This is because, although the human visual system can detect symmetries in 2-D images effectively, regular CNNs can only exploit translation invariance, overlooking further inherent symmetries existing in medical images, such as rotations and reflections. To solve this problem, we propose a novel group equivariant segmentation framework by encoding those inherent symmetries for learning more precise representations. First, kernel-based equivariant operations are devised on each orientation, which allows it to effectively address the gaps of learning symmetries in existing approaches. Then, to keep segmentation networks globally equivariant, we design distinctive group layers with layer-wise symmetry constraints. Finally, based on our novel framework, extensive experiments conducted on real-world clinical data demonstrate that a group equivariant Res-UNet (called GER-UNet) outperforms its regular CNN-based counterpart and the state-of-the-art segmentation methods in the tasks of hepatic tumor segmentation, COVID-19 lung infection segmentation, and retinal vessel detection. More importantly, the newly built GER-UNet also shows potential in reducing the sample complexity and the redundancy of filters, upgrading current segmentation CNNs, and delineating organs on other medical imaging modalities.

An Attributed Dynamic Graph (ADG) contains multiple dynamic attributes associated with each edge in the graph, where people usually can specify multiple constraints in the attributes to illustrate their requirements, such as the total cost, the total travel time and the stopover interval of a flight between two cities. This inspires the Multi-Constrained Temporal Path (MCTP) discovery in ADGs, which is a challenging NP-Complete problem. The existing methods adopt Reinforcement Learning (RL) and Monte Carlo Tree Search (MCTS) in MCTP discovery. However, they require a certain degree of discovery experience to obtain better results, which can lead to the expensive cost of query time and storage space, and thus are not applicable in real-time applications. This motivates us to develop a new Adaptive Monte Carlo Tree Search algorithm (A-MCTS). A-MCTS dynamically adjusts the priority of historical records that are used in MCTS to improve the performance and reduce the size of required discovery experience. The experimental results on ten real-world dynamic graphs demonstrate that our proposed A-MCTS outperforms the state-of-the-art methods in terms of both efficiency and effectiveness.

Semantic relation prediction aims to mine the implicit relationships between objects in heterogeneous graphs, which consist of different types of objects and different types of links. In real-world scenarios, new semantic relations constantly emerge and they typically appear with only a few labeled data. Since a variety of semantic relations exist in multiple heterogeneous graphs, the transferable knowledge can be mined from some existing semantic relations to help predict the new semantic relations with few labeled data. This inspires a novel problem of few-shot semantic relation prediction across heterogeneous graphs. However, the existing methods cannot solve this problem because they not only require a large number of labeled samples as input, but also focus on a single graph with a fixed heterogeneity. Targeting this novel and challenging problem, in this paper, we propose a Meta-learning based Graph neural network for Semantic relation prediction, named MetaGS. First, MetaGS decomposes the graph structure between objects into multiple normalized subgraphs, then adopts a two-view graph neural network to capture local heterogeneous information and global structure information of these subgraphs. Second, MetaGS aggregates the information of these subgraphs with a hyper-prototypical network, which can learn from existing semantic relations and adapt to new semantic relations. Third, using the well-initialized two-view graph neural network and hyper-prototypical network, MetaGS can effectively learn new semantic relations from different graphs while overcoming the limitation of few labeled data. Extensive experiments on three real-world datasets have demonstrated the superior performance of MetaGS over the state-of-the-art methods.

In this paper, we study the problem of multi-source cross-network node classification, which aims to classify unlabeled nodes in a target network by leveraging the knowledge learned from the rich labeled nodes in multiple source networks. The existing multi-source transfer learning approaches generally fail to model the structural information of networks, and the current cross-network node classification models mainly neglect that not all source networks can boost the task performance in the target network. Thus, none can be directly applied to the multi-source cross-network node classification task. To this end, in this paper, we propose a novel multi-source data selection (MSDS) based framework for cross-network node classification, which integrates multi-source transfer learning with network embedding to learn label-discriminative and network-invariant node representations. In MSDS, we first propose the multi-source network data selection, which applies three distances to jointly select the transferable source networks to well alleviate the problem of suboptimal solution or even negative transfer. In addition, we devise a new feature information alignment technique to make node vector representations network-invariant. Moreover, we incorporate aggregated structural information and feature information to make node representations label-discriminative. Extensive experiments on real-world datasets demonstrate that the proposed approaches outperform the state-of-the-art non-transfer and single-source transfer approaches in terms of classification accuracy.

Graph Pattern based Node Matching(GPNM) is to find all the matches of the nodes in a data graph$G_D$based on a given pattern graph$G_P$. GPNM has become increasingly important in many applications, e.g., group finding and expert recommendation. In real scenarios, both$G_P$and$G_D$are updated frequently. However, the existing GPNM methods either need to perform a new GPNM procedure from scratch to deliver the node matching results based on the updated$G_P$and$G_D$or incrementally perform the GPNM procedure for each of the updates, leading to low efficiency. Although the elimination relations between updates and partitions of data graphs are considered in the state-of-the-art method, it still suffers from low efficiency as only the labels of nodes are considered in the partitions. Therefore, there is a pressing need for a new method to efficiently deliver the node matching results on the updated graphs. In this paper, we propose a new Partition-aware GPNM algorithm, called P-GPNM, where we propose two new partition methods, i.e.,connection-based partitionanddensity-based partition. In these two methods, P-GPNM considers the dense connections between partitions and the inner connections inside a single partition, respectively. The experimental results on five real-world social graphs demonstrate that our proposed P-GPNM is much more efficient than the state-of-the-art GPNM methods.

Users’ purchase behaviors are complex and dynamic, which are usually driven by various personal demands evolving with time. According to psychology and economic theories, user demands can be satisfied with a sequence of purchase behaviors, resulting in a basket of items. However, most of the existing works simply predict the next basket from a shallow perspective of (purchase) sequence data modeling without deep insight into the underlying factors which drive user purchase behaviors. In fact, filling a basket with multiple items is a process to incrementally satisfy a user's demand. Therefore, the key challenges to predict a user's next basket lie in (1) how to track the changes of the user's demand, and (2) how to satisfy her demand at a given moment. To this end, we propose an Evolving DEmand SAtisfaction (EvoDESA) model to model a user's demand evolution for next-basket prediction. In EvoDESA, a demand evolution module learns the dynamics of user demand over a sequence of basket-purchase behaviors. Then, a next-basket planning module effectively packs an optimal combination of items to best satisfy the user's current demand. Extensive experiments on three real-world transaction datasets demonstrate the considerable superiority of EvoDESA over the state-of-the-art approaches.

The sparse interactions between users and items on the web have aggravated the difficulty of their representations in recommender systems. Existing approaches leverage item attributes (e.g., item categories and tags) to alleviate the data sparsity problem, so as to enhance the performance and interpretability of recommendation. However, directly using all attributes of items cannot avoid the negative impacts of low-quality attributes, where manually labeling the quality of attributes is time-consuming. To this end, we propose HQRec to jointly measure the quality of attributes automatically and perform recommendation accurately. Specifically, we first analyze the different qualities among item attributes, and propose to leverage item categories to select high-quality tags via category-guided quality measurement and direction-aware optimization in an unsupervised fashion. Then, we propose to capture the complex relations among users and items based on the high-quality attributes, where a novel quality-aware embedding fusion and quality-aware embedding propagation mechanism for users and items is devised. Extensive experiments on four real-world benchmark datasets show drastic performance gains brought by our proposed HQRec framework, which constantly achieves an average of 14.73% improvement over the state-of-the-art baselines in terms of Recall and NDCG metrics. Insightful case studies also show that our automatic quality measurements are highly accurate and interpretable.

Cross-Domain Recommendation (CDR) and Cross-System Recommendation (CSR) have been proposed to improve the recommendation accuracy in a target dataset (domain/system) with the help of a source one with relatively richer information. However, most existing CDR and CSR approaches are single-target, namely, there is a single target dataset, which can only help the target dataset and thus cannot benefit the source dataset. In this paper, we focus on three new scenarios, i.e., Dual-Target CDR (DTCDR), Multi-Target CDR (MTCDR), and CDR+CSR, and aim to improve the recommendation accuracy in all datasets simultaneously for all scenarios. To do this, we propose a unified framework, called GA (based onGraph embedding andAttention techniques), for all three scenarios. In GA, we first construct separate heterogeneous graphs to generate more representative user and item embeddings. Then, we propose an element-wise attention mechanism to effectively combine the embeddings of common entities (users/items) learned from different datasets. Moreover, to avoid negative transfer, we further propose aPersonalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i.e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively. Extensive experiments conducted on four real-world datasets demonstrate that our proposed GA models significantly outperform the state-of-the-art approaches.

Federated Learning (FL), allowing data owners to conduct model training without sending their raw data to third-party servers, can enhance data privacy in Mobile Edge Computing (MEC) which brings data processing closer to the data sources. However, the heterogeneity of local data and constrained local resources in MEC bring new challenges hindering the development of FL. To this end, we propose an Auction-based Cluster Federated Learning scheme, called ACFL, comprising a clustered FL framework and an auction-based client selection strategy. Our clustered FL framework first introduces a mean-shift clustering algorithm to FL, which can intelligently cluster clients according to their local data distribution. Then, we select clients from each cluster using an auction mechanism to participate in FL training, which can mitigate the impact of data heterogeneity on model convergence and balance energy consumption. Moreover, we prove the proposed clustered FL framework converges at a sublinear rate. Extensive experiments conducted on real-world datasets demonstrate that the proposed FL scheme outperforms the conventional FL schemes in terms of convergence rate and energy balance.

The prediction of keypoints by generating high-resolution heatmaps has become a popular solution in human pose estimation. While this kind of method requires up-sampling or deconvolution operations, which would bring a great challenge to the acceleration of model inference. If performing keypoint prediction on low-resolution heatmaps, the performance is unsatisfied due to serious quantization errors. To solve this contradiction, we propose to perform joint training of the heatmap and center offset on low-resolution heatmaps to reduce quantization errors, which could achieve the comparable performance to the high-resolution heatmap and reduce the computational complexity. In addition, we utilize transformer to enhance the representation ability of low-resolution features, instead of increasing the network layers or the convolution kernel size. The transformer could bring the significant improvement of the performance with little computation cost. Combining the above two modules, we design a new lightweight pose estimation model, named LightPose. Experimental results have shown that, compared with HRNet, our method could achieve the state-of-the-art performance on COCO and MPII datasets with a massive reduction of the parameters by 86% and GFLOPs by 67%.

With the advancement of data science and AI, more and more powerful and accurate recommender systems (RSs) have been developed. They provide recommendation services in various areas, including shopping, eating, travelling and entertainment. RSs have achieved a great success and benefted the society. However, most of the research on RS has focused on the improvement of the recommendation accuracy, while ignoring other important qualities, such as trustworthiness (robustness, fairness, explainability, privacy and security) and social impact (influence on users' recognition and behaviours) of the recommendations. These are important aspects and cannot be overlooked since they measure properties that determine whether the recommendation service is reliable, trustworthy and benefcial to individual users and society. In this work, responsible recommendations refer to trustworthy recommendation techniques and positive-social-impact recommendation results.

In recent years, sequential recommender systems (SRSs) and session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs to capture users' short-term but dynamic preferences for enabling more timely and accurate recommendations. Although SRSs and SBRSs have been extensively studied, there are many inconsistencies in this area caused by the diverse descriptions, settings, assumptions and application domains. There is no work to provide a unified framework and problem statement to remove the commonly existing and various inconsistencies in the area of SR/SBR. There is a lack of work to provide a comprehensive and systematic demonstration of the data characteristics, key challenges, most representative and state-of-the-art approaches, typical real- world applications and important future research directions in the area. This work aims to fill in these gaps so as to facilitate further research in this exciting and vibrant area.

Despite the tremendous efforts by social media platforms and fact-check services for fake news detection, fake news and misinformation still spread wildly on social media platforms (e.g., Twitter). Consequently, fake news mitigation strategies are urgently needed. Most of the existing work on fake news mitigation focuses on the overall mitigation on a whole social network while ignoring developing concrete mitigation strategies to deter individual users from sharing fake news. In this paper, we propose a novel veracity-aware and event-driven recommendation model to recommend personalised corrective true news to individual users for effectively debunking fake news. Our proposed model Rec4Mit (Recommendation for Mitigation) not only effectively captures a user’s current reading preference with a focus on which event, e.g., US election, from her/his recent reading history containing true and/or fake news, but also accurately predicts the veracity (true or fake) of candidate news. As a result, Rec4Mit can recommend the most suitable true news to best match the user’s preference as well as to mitigate fake news. In particular, for those users who have read fake news of a certain event, Rec4Mit is able to recommend the corresponding true news of the same event. Extensive experiments on real-world datasets show Rec4Mit significantly outperforms the state-of-the-art news recommendation methods in terms of the capability to recommend personalized true news for fake news mitigation.

Synthetic aperture radar (SAR) can monitor the sea surface imprints of tropical cyclones (TCs) with high spatial resolution, day and night. Automatically locating TC center positions in SAR images is a challenging task. This article developed a two-stage, fully automatic TC-center estimation algorithm. First, the sea surface wind directions (SSWDs) at SSWD points are retrieved by the improved local gradient (ILG) method. We incrementally deflected the SSWD outward at a 0.5° angle from −50° to 10° (the negative angles represent clockwise deflection). The heat maps are generated for each of the 121 angles, and the values at each heat map are the cumulative numbers of the lines perpendicular to the compensated SSWDs. The site corresponding to the maximum cumulative number in all 121 heat maps is the coarsely estimated center position. This center search is the culmination if it falls outside the SAR image. Otherwise, the second stage is triggered, and the sub-SAR image (150 km$\times150$km) centered at the coarsely estimated center position is extracted. Then, the first-stage procedure is repeated with the sub-SAR image to precisely estimate the center position. Optionally, the precisely estimated center position can be further adjusted by considering that normalized radar cross section (NRCS) is normally minimal at the TC center. We applied the algorithm to 87 SAR images. Five of these images do not contain TC centers. The results are in good agreement with the visually located TC center positions and those in the best track (BT) datasets.

Wind-induced oriented textures (WIOTs) are commonly used to retrieve sea surface wind directions from synthetic aperture radar (SAR) images. In this study, we found that WIOTs are also related to sea surface wind speeds (SSWSs). The entropy values in the gray-level cooccurrence matrices (GLCMs) for SAR images containing WIOTs will become steady with increasing distance between pairs of pixels. Furthermore, these steady values of entropy (SVEs) show a clear linear relationship with SSWSs. As a result, an SSWS retrieval model was developed based on this relationship. We used 2222/2223 Sentinel-1 SAR images (wind speed ranges from 5 to 20 m/s) to fit/validate the algorithm. The retrieved SSWSs were compared with the European Centre for Medium-Range Weather Forecast (ECMWF) SSWSs, Cross-Calibrated Multi-Platform (CCMP) SSWSs, and Tropical Atmosphere/Ocean (TAO) buoy measurements, and the root-mean-square differences (RMSDs) were 1.78, 1.70, and 1.78 m/s, respectively. The new model was also tested for SAR images acquired under hurricane conditions. The wind comparisons against stepped-frequency microwave radiometer (SFMR) measurements show an RMSD of 1.28 m/s. Our model’s performance was also tested with the images at different spatial scales in the validation data set. Since the model is based on inherent image patterns, it still works well for SAR images without precise calibration.

Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build privacy-preserving DNN models from either algorithmic perspective or cryptographic perspective. The former mainly splits the DNN computation graph between data holders or between data holders and server, which demonstrates good scalability but suffers from accuracy loss and potential privacy risks. In contrast, the latter leverages time-consuming cryptographic techniques, which has strong privacy guarantee but poor scalability. In this article, we propose SPNN—a Scalable and Privacy-preserving deep Neural Network learning framework, from an algorithmic-cryptographic co-perspective. From algorithmic perspective, we split the computation graph of DNN models into two parts, i.e., the private-data-related computations that are performed by data holders and the rest heavy computations that are delegated to a semi-honest server with high computation ability. From cryptographic perspective, we propose using two types of cryptographic techniques, i.e., secret sharing and homomorphic encryption, for the isolated data holders to conduct private-data-related computations privately and cooperatively. Furthermore, we implement SPNN in a decentralized setting and introduce user-friendly APIs. Experimental results conducted on real-world datasets demonstrate the superiority of our proposed SPNN.

Implicit feedback is widely used in collaborative filtering methods for sequential recommendation. It is well known that implicit feedback contains a large number of values that aremissing not at random(MNAR); and the missing data is a mixture of negative and unknown feedback, making it difficult to learn users’ negative preferences. Recent studies modeledexposure, a latent missingness variable which indicates whether an item is exposed to a user, to give each missing entry a confidence of being negative feedback. However, these studies use static models and ignore the information in temporal dependencies among items, which seems to be an essential underlying factor to subsequent missingness. To model and exploit the dynamics of missingness, we propose a latent variable named “user intent” to govern the temporal changes of item missingness, and a hidden Markov model to represent such a process. The resulting framework captures the dynamic item missingness and incorporates it into matrix factorization (MF) for recommendation. We further extend the proposed framework to capture the dynamic preference of users, which results in a unified framework that is able to model different evolution patterns of user intent and user preference. We also explore two types of constraints to achieve a more compact and interpretable representation ofuser intents. Experiments on real-world datasets demonstrate the superiority of our method against state-of-the-art recommender systems.

Virtual network embedding (VNE) can effectively deploy virtual networks (VNs) onto shared substrate network (SN) resources. However, with the consistent changing scalability and diversity demands of VNs, traditional VNE methods prove to be a challenging task for current cloud service platforms. Thus, we model a repeatable multi-dimensional virtual network embedding (RMD-VNE) problem for implementing multi-dimensional virtual networks (MD-VNs) that involves real servers, virtual machines, containers, and network simulators. The MD-VN is preprocessed and embedded via a heuristic method denoted asReMiDvne. Following its transformation for the containers and simulation networks, the MD-VN topology undergoes a process of coarsening, partitioning, and uncoarsening.ReMiDvnethen applies a topology-aware repeatable embedding solution to complete the embedding stage. Experimental results demonstrate thatReMiDvneoutperforms seven baseline approaches through small-, 1,000- and 10,000-scale VNE simulation experiments. Remarkably,ReMiDvneimproves the average rates of acceptance ratio, revenue, and revenue-cost ratio by up to 40.45, 40.45, and 299.03 percent, respectively, and reduces the average rate of cost by up to 64.16 percent. Furthermore, real-world VNE experiments are conducted based on the OpenStack platform. The results reveal the ability ofReMiDvneto efficiently reduce communication costs by up to 45.93 and 63.43 percent for download and upload, respectively.

CVaR-sensitive online portfolio selection (CS-OLPS) becomes increasingly important for investors because of its effectiveness to minimize conditional value at risk (CVaR) and control extreme losses. However, the non-stationary nature of financial markets makes it very difficult to address the CS-OLPS problem effectively. To address the CS-OLPS problem in non-stationary markets, we propose an effective news-driven method, named CAND, which adaptively exploits news to determine the adjustment tendency and adjustment scale for tracking the dynamic optimal portfolio with minimal CVaR in each trading round. In addition, we devise a filtering mechanism to reduce the errors caused by the noisy news for further improving CAND's effectiveness. We rigorously prove a sub-linear regret of CAND. Extensive experiments on three real-world datasets demonstrate CAND’s superiority over the state-of-the-art portfolio methods in terms of returns and risks.

Recent years have witnessed the fast development of the emerging topic of Graph Learning based Recommender Systems (GLRS). GLRS mainly employ advanced graph learning approaches to model users’ preferences and intentions as well as items’ characteristics and popularity for Recommender Systems (RS). Differently from other approaches, including content based filtering and collaborative filtering, GLRS are built on graphs where the important objects, e.g., users, items, and attributes, are either explicitly or implicitly connected. With the rapid development of graph learning techniques, exploring and exploiting homogeneous or heterogeneous relations in graphs is a promising direction for building more effective RS. In this paper, we provide a systematic review of GLRS, by discussing how they extract knowledge from graphs to improve the accuracy, reliability and explainability of the recommendations. First, we characterize and formalize GLRS, and then summarize and categorize the key challenges and main progress in this novel research area.

To address the long-standing data sparsity problem in recommender systems (RSs), cross-domain recommendation (CDR) has been proposed to leverage the relatively richer information from a richer domain to improve the recommendation performance in a sparser domain. Although CDR has been extensively studied in recent years, there is a lack of a systematic review of the existing CDR approaches. To fill this gap, in this paper, we provide a comprehensive review of existing CDR approaches, including challenges, research progress, and prospects. Specifically, we first summarize existing CDR approaches into four types, including single-target CDR, single-target multi-domain recommendation (MDR), dual-target CDR, and multi-target CDR. We then present the definitions and challenges of these CDR approaches. Next, we propose a full-view categorization and new taxonomies on these approaches and report their research progress in detail. In the end, we share several promising prospects in CDR.

The changing preferences of users towards items trigger the emergence of session-based recommender systems (SBRSs), which aim to model the dynamic preferences of users for next-item recommendations. However, most of the existing studies on SBRSs are based on long sessions only for recommendations, ignoring short sessions, though short sessions, in fact, account for a large proportion in most of the real-world datasets. As a result, the applicability of existing SBRSs solutions is greatly reduced. In a short session, quite limited contextual information is available, making the next-item recommendation very challenging. To this end, in this paper, inspired by the success of few-shot learning (FSL) in effectively learning a model with limited instances, we formulate the next-item recommendation as an FSL problem. Accordingly, following the basic idea of a representative approach for FSL, i.e., meta-learning, we devise an effective SBRS called INter-SEssion collaborativeRecommender neTwork (INSERT) for next-item recommendations in short sessions. With the carefully devised local module and global module, INSERT is able to learn an optimal preference representation of the current user in a given short session. In particular, in the global module, a similar session retrieval network (SSRN) is designed to find out the sessions similar to the current short session from the historical sessions of both the current user and other users, respectively. The obtained similar sessions are then utilized to complement and optimize the preference representation learned from the current short session by the local module for more accurate next-item recommendations in this short session. Extensive experiments conducted on two real-world datasets demonstrate the superiority of our proposed INSERT over the state-of-the-art SBRSs when making next-item recommendations in short sessions.

With the prevalence of online review websites, large-scale data promote the necessity of focused analysis. This task aims to capture the information that is highly relevant to a specific aspect. However, the broad scope of the aspects of the various products makes this task overarching but challenging. A commonly used solution is to modify the topic models with additional information to capture the features for a specific aspect (referred to as a targeted aspect). However, the existing topic models, either perform the full analysis to capture features as many as possible or estimate the similarity to capture features as coherent as possible, overlook the fine-grained semantic relations between the features, resulting in the captured features coarse and confusing. In this paper, we propose a novel Hierarchical Features-based Topic Model (HFTM) to extract targeted aspects from online reviews, then to capture the aspect-specific features. Specifically, our model can not only capture the direct features posing target-to-feature semantics but also capture the latent features posing feature-to-feature semantics. The experiments conducted on real-world datasets demonstrate that HFTMl outperforms the state-of-the-art baselines in terms of both aspect extraction and document classification.

Graph Pattern based Node Matching (GPNM) has been proposed to find all the matches of the nodes in a data graph GD based on a given pattern graph GP. GPNM has been increasingly adopted in many applications such as group finding and expert recommendation, in which data graphs are frequently updated overtime. Moreover, many typical pattern graphs frequently and repeatedly appear in users' queries in a short period of time, e.g., social graph searches on Facebook. To deliver a GPNM result in such applications, the existing GPNM methods have to perform an incremental GPNM procedure for each of the updates in the data graph, which is computationally expensive. To address this problem, in this paper, we first analyze the elimination relationships between multiple updates in GD and the hierarchical structure between these elimination relationships. Then, we generate an Elimination Hierarchy Tree (EH-Tree) to index the elimination relationships and propose an EH-Tree based GPNM method, called EHGPNM, considering the elimination relationships between multiple updates in GD. EH-GPNM first delivers the GPNM result of an initial query, and then delivers the GPNM result of a subsequent query, based on the initial GPNM result and the multiple updates of GD that occur between those two queries. The experimental results on five real-world social graphs demonstrate that our proposed EH-GPNM is much more efficient than the state-of-the-art GPNM methods.

As enterprises around the globe embrace globalization, strategic alliances among enterprises have become an important means to gain competitive advantages. Enterprises cooperate to improve the quality or lower the prices of their services, which introduce quality correlations, i.e., the quality of a service is associated with other services. Existing approaches for service composition have not fully and systematically considered the quality correlations between services. In this paper, we propose a novel approach named Q2C (Query of Quality Correlation) to systematically model quality correlations and enable efficient queries of quality correlations for service compositions. Given a service composition and a set of candidate services, Q2C first preprocesses the quality correlations among the candidate services and then constructs a quality correlation index graph to enable efficient queries for quality correlations. Extensive experiments are conducted on a real-world web service dataset to demonstrate the effectiveness and efficiency of Q2C.

Human behaviors are complex, which are often observed as a sequence of heterogeneous actions. In this paper, we take user choices for shopping baskets as a typical case to study the complexity of user behaviors. Most of existing approaches often model user behaviors in a mechanical way, namely treating a user action sequence as homogeneous sequential data, such as hourly temperatures, which fails to consider the complexity in user behaviors. In fact, users' choices are driven by certain underlying intentions (e.g., feeding the baby or relieving pain) according to Psychological theories. Moreover, the durations of intentions to drive user actions are quite different; some of them may be persistent while others may be transient. According to Psychological theories, we develop a hierarchical framework to describe the goal, intentions and action sequences, based on which, we design Intention Nets (IntNet). In IntNet, multiple Action Chain Nets are constructed to model the user actions driven by different intentions, and a specially designed Persistent-Transient Intention Unit models the different intention durations. We apply the IntNet to next-basket prediction, a recent challenging task in recommender systems. Extensive experiments on real-world datasets show the superiority of our Psychology-inspired model IntNet over the state-of-the-art approaches.

Graph Pattern based Node Matching (GPNM) is to find all the matches of the nodes in a data graph GDbased on a given pattern graph GP. GPNM has become increasingly important in many applications, e.g., group finding and expert recommendation. In real scenarios, both GPand GDare updated frequently. However, the existing GPNM methods either need to perform a new GPNM procedure from scratch to deliver the node matching results based on the updated GPand GDor incrementally perform the GPNM procedure for each of the updates, leading to low efficiency. Therefore, there is a pressing need for a new method to efficiently deliver the node matching results on the updated graphs. In this paper, we first analyze and detect the elimination relationships between the updates. Then, we construct an Elimination Hierarchy Tree (EH-Tree) to index these elimination relationships. In order to speed up the GPNM process, we propose a graph partition method and then propose a new updates-aware GPNM method, called UA-GPNM, considering the single-graph elimination relationships among the updates in a single graph of GPor GD, and also the cross-graph elimination relationships between the updates in GPand the updates in GD. UA-GPNM first delivers the GPNM result of an initial query, and then delivers the GPNM result of a subsequent query, based on the initial GPNM result and the multiple updates that occur between two queries. The experimental results on five real-world social graphs demonstrate that our proposed UA-GPNM is much more efficient than the state-of-the-art GPNM methods.

Edge computing is a promising paradigm that can boost the performance of novel mobile applications and energize the real-time governance of Internet-of-Things (IoT) big data. In edge computing, mobile application vendors are allowed to employ edge resources to speed up end-users' applications in an elastic and on-demand manner. However, due to the complex geographical distribution of edge servers and users, how to decide the most appropriate destination edge server to hire and how to decide the corresponding user-server allocation plan with as-low-as-possible monetary cost are the key problems for application vendors. Instead of assuming a simultaneous-batch-arrival pattern of incoming users and considering static optimization of the Edge User Allocation (EUA) problem by most existing studies, in this paper, we consider an online EUA problem where users' arrival and departure follow a general pattern. We take the long-term edge user allocation rate and edge server leasing cost as scheduling targets and propose a decentralized collaborative and fuzzy-control-based approach to yielding real-time user-edge-server allocation schedules. In this approach, edge users are allowed to independently make their own allocation decision only based on local information (i.e., the status of nearby edge servers). Experiments on real-world edge datasets demonstrate our approach outperforms state-of-the-art approaches in terms of long-term allocation rate and system cost.

User purchase behaviours are complex and dynamic, which are usually observed as multiple choice actions across a sequence of shopping baskets. Most of the existing next-basket prediction approaches model user actions as homogeneous sequence data without considering complex and heterogeneous user intentions, impeding deep under-standing of user behaviours from the perspective of human inside drivers and thus reducing the prediction performance. Psychological theories have indicated that user actions are essentially driven by certain underlying intentions (e.g., diet and entertainment). Moreover, different intentions may influence each other while different choices usually have different utilities to accomplish an intention. Inspired by such psychological insights, we formalize the next-basket prediction as an Intention Recognition, Modelling and Accomplishing problem and further design the Intention2Basket (Int2Ba in short) model. In Int2Ba, an Intention Recognizer, a Coupled Intention Chain Net, and a Dynamic Basket Planner are specifically designed to respectively recognize, model and accomplish the heterogeneous intentions behind a sequence of baskets to better plan the next-basket. Extensive experiments on real-world datasets show the superiority of Int2Ba over the state-of-the-art approaches.

The conventional single-target Cross-Domain Recommendation (CDR) only improves the recommendation accuracy on a target domain with the help of a source domain (with relatively richer information). In contrast, the novel dual-target CDR has been proposed to improve the recommendation accuracies on both domains simultaneously. However, dual-target CDR faces two new challenges: (1) how to generate more representative user and item embeddings, and (2) how to effectively optimize the user/item embeddings on each domain. To address these challenges, in this paper, we propose a graphical and attentional framework, called GA-DTCDR. In GA-DTCDR, we first construct two separate heterogeneous graphs based on the rating and content information from two domains to generate more representative user and item embeddings. Then, we propose an element-wise attention mechanism to effectively combine the embeddings of common users learned from both domains. Both steps significantly enhance the quality of user and item embeddings and thus improve the recommendation accuracy on each domain. Extensive experiments conducted on four real-world datasets demonstrate that GA-DTCDR significantly outperforms the state-of-the-art approaches.

Online portfolio selection (OLPS) is a fundamental and challenging problem in financial engineering, which faces two practical constraints during the real trading, i.e., cardinality constraint and non-zero transaction costs. In order to achieve greater feasibility in financial markets, in this paper, we propose a novel online portfolio selection method named LExp4.TCGP with theoretical guarantee of sublinear regret to address the OLPS problem with the two constraints. In addition, we incorporate side information into our method based on contextual bandit, which further improves the effectiveness of our method. Extensive experiments conducted on four representative real-world datasets demonstrate that our method significantly outperforms the state-of-the-art methods when cardinality constraint and non-zero transaction costs co-exist.

Federated collaborative filtering (Fed-CF) is a variant of federated learning (FL) models, which can protect user privacy in recommender systems. In Fed-CF, the recommendation model is collectively trained across multiple decentralized clients by exchanging gradients only. However, the decentralized nature of Fed-CF makes it vulnerable to shilling attacks, which can be realized by inserting fake ratings of target items to distort recommendation results. Unfortunately, previous detection algorithms cannot work well in the FL framework, as all original data samples are not disclosed at all. In this paper, we are the first to systematically study the problem of shilling attacks in the context of federated learning, and propose an effective detection method called Federated Shilling Attack Detector (FSAD) to detect shilling attackers in Fed-CF. We first show the feasibility of shilling attacks in Fed-CF. Next, we dedicatedly design four novel features based on exchanged gradients among clients. By incorporating these gradient-based features, we train a semi-supervised Bayes classifier to identify shilling attackers effectively. Finally, we conduct extensive experiments based on real-world datasets to evaluate the performance of our proposed FSAD method. The experimental results show that FSAD can detect shilling attackers in Fed-CF with high accuracy, with the F1value as high as 0.90 on the Netflix dataset, which approaches the performance of the optimal detector that utilizes complete private user information for detection.

In order to address the data sparsity problem in recommender systems, in recent years, Cross-Domain Recommendation (CDR) leverages the relatively richer information from a source domain to improve the recommendation performance on a target domain with sparser information. However, each of the two domains may be relatively richer in certain types of information (e.g., ratings, reviews, user profiles, item details, and tags), and thus, if we can leverage such information well, it is possible to improve the recommendation performance on both domains simultaneously (i.e., dual-target CDR), rather than a single target domain only. To this end, in this paper, we propose a new framework, DTCDR, for Dual-Target Cross-Domain Recommendation. In DTCDR, we first extensively utilize rating and multi-source content information to generate rating and document embeddings of users and items. Then, based on Multi-Task Learning (MTL), we design an adaptable embedding-sharing strategy to combine and share the embeddings of common users across domains, with which DTCDR can improve the recommendation performance on both richer and sparser (i.e., dual-target) domains simultaneously. Extensive experiments conducted on real-world datasets demonstrate that DTCDR can significantly improve the recommendation accuracies on both richer and sparser domains and outperform the state-of-the-art single-domain and cross-domain approaches.

Clustering Web services can promote the quality of services discovery and management within a service repository. Traditional clustering methods primarily focus on using the semantic distance between service features, i.e., latent topics learned from WSDL documents, to measure the service content similarity between Web services. Few works exploited the structural information generated during the usage of Web services, i.e., the service compositing and tagging behaviors. Nowadays, Web services frequently interact (e.g., composition relation and tag sharing relation) with each other to form a complex service relationship network. The rich network relations inherently reflect either positive or negative categorical relevance between services, which can be strong supplement of service semantics in characterizing the functional affinities between services. In this paper, we propose to utilize the services relationship network for augmented services clustering algorithm design. We first learn semantic information from service descriptions based on the widely used Doc2Vec model. Then, we propose a revised K-means algorithm for service clustering that benefits simultaneously from service semantics and network relations, where the service relations are previously preserved in a set of low-dimensional vectors achieved based on a recently proposed network embedding technique. Experiments on a real-world dataset demonstrated that the proposed clustering approach yields an improvement of 6.89% than the state-of-the-art.

A session-based recommender system (SBRS) suggests the next item by modeling the dependencies between items in a session. Most of existing SBRSs assume the items inside a session are associated with one (implicit) purpose. However, this may not always be true in reality, and a session may often consist of multiple subsets of items for different purposes (e.g., breakfast and decoration). Specifically, items (e.g., bread and milk) in a subsethave strong purpose-specific dependencies whereas items (e.g., bread and vase) from different subsets have much weaker or even no dependencies due to the difference of purposes. Therefore, we propose a mixture-channel model to accommodate the multi-purpose item subsets for more precisely representing a session. Filling gaps in existing SBRSs, this model recommends more diverse items to satisfy different purposes. Accordingly, we design effective mixture-channel purpose routing networks (MCPRN) with a purpose routing network to detect the purposes of each item and assign it into the corresponding channels. Moreover, a purpose specific recurrent network is devised to model the dependencies between items within each channel for a specific purpose. The experimental results show the superiority of MCPRN over the state-of-the-art methods in terms of both recommendation accuracy and diversity.

The emerging topic of sequential recommender systems (SRSs) has attracted increasing attention in recent years. Different from the conventional recommender systems (RSs) including collaborative filtering and content-based filtering, SRSs try to understand and model the sequential user behaviors, the interactions between users and items, and the evolution of users’ preferences and item popularity over time. SRSs involve the above aspects for more precise characterization of user contexts, intent and goals, and item consumption trend, leading to more accurate, customized and dynamic recommendations. In this paper, we provide a systematic review on SRSs. We first present the characteristics of SRSs, and then summarize and categorize the key challenges in this research area, followed by the corresponding research progress consisting of the most recent and representative developments on this topic. Finally, we discuss the important research directions in this vibrant area.

Incorporating accountability mechanisms in online services requires effective trust management and immutable, traceable source of truth for transaction evidence. The emergence of the blockchain technology brings in high hopes for fulfilling most of those requirements. However, a major challenge is to find a proper consensus protocol that is applicable to the crowdsourcing services in particular and online services in general. Building upon the idea of using blockchain as the underlying technology to enable tracing transactions for service contracts and dispute arbitration, this paper proposes a novel consensus protocol that is suitable for the crowdsourcing as well as the general online service industry. The new consensus protocol is called “Proof-of-Trust” (PoT) consensus; it selects transaction validators based on the service participants' trust values while leveraging RAFT leader election and Shamir's secret sharing algorithms. The PoT protocol avoids the low throughput and resource intensive pitfalls associated with Bitcoin' s “Proof-of-Work” (PoW) mining, while addressing the scalability issue associated with the traditional Paxos-based and Byzantine Fault Tolerance (BFT)-based algorithms. In addition, it addresses the unfaithful behaviors that cannot be dealt with in the traditional BFT algorithms. The paper demonstrates that our approach can provide a viable accountability solution for the online service industry.

Graph Pattern based Node Matching (GPNM) is to find all the matches of the nodes in a data graph GD based on a given pattern graph GP. GPNM has become increasingly important in many applications, e.g., group finding and expert recommendation. In real scenarios, both GP and GD are updated frequently. However, the existing GPNM methods need to perform a new GPNM procedure from scratch to deliver the node matching results based on the updated GP and updated GD, which consumes much time. Therefore, there is a pressing need for a novel method to efficiently deliver the node matching results. In this paper, we propose a novel INCremental GPNM method called INC-GPNM, where we first build up indices to incrementally maintain the shortest path length range between different label types in GD, and then identify the affected parts of GD in GPNM including nodes and edges w.r.t. the updates of GP and GD. Moreover, based on the index structure and our novel search strategies, INC-GPNM can efficiently deliver node matching results taking the updates of GP and GD as input, and can greatly save the query processing time with improved time complexity. The extensive experiments on five real-world social graphs demonstrate that our method greatly outperforms the state-of-the-art GPNM method in efficiency.

In the field of service computing, user preferences and service quality may change with time, environment and other factors. A recommendation algorithm that considers both the dynamic characteristics of users and the dynamic quality of services (QoS) is proposed in this paper. On the one hand, this algorithm uses the temporal LDA (Latent Dirichlet Allocation) model to mine dynamic user preferences. On the other hand, it considers the dynamic changes of QoS and focuses on the latest QoS. The service recommendation list is then generated for the user based on dynamic user preferences and dynamic QoS. Experimental results on a real-world dataset show that the proposed algorithm outperforms some classic algorithms and the state-of-the-art algorithms in terms of accuracy, recall and diversity.

General recommender and sequential recommender are two commonly applied modeling paradigms for recommendation tasks. General recommender focuses on modeling the general user preferences, ignoring the sequential patterns in user behaviors; whereas sequential recommender focuses on exploring the item-to-item sequential relations, failing to model the global user preferences. In addition, better recommendation performance has recently been achieved by adopting an approach to combine them. However, previous approaches are unable to solve both tasks in a unified way and cannot capture the whole historical sequential information. In this paper, we propose a recommendation model named Recurrent Collaborative Filtering (RCF), which unifies both paradigms within a single model.Specifically, we combine recurrent neural network (the sequential recommender part) and matrix factorization model (the general recommender part) in a multi-task learning framework, where we perform joint optimization with shared model parameters enforcing the two parts to regularize each other. Furthermore, we empirically demonstrate on MovieLens and Netflix datasets that our model outperforms the state-of-the-art methods across the tasks of both sequential and general recommender.

Cross-Domain Recommendation (CDR) and Cross-System Recommendations (CSR) are two of the promising solutions to address the long-standing data sparsity problem in recommender systems. They leverage the relatively richer information, e.g., ratings, from the source domain or system to improve the recommendation accuracy in the target domain or system. Therefore, finding an accurate mapping of the latent factors across domains or systems is crucial to enhancing recommendation accuracy. However, this is a very challenging task because of the complex relationships between the latent factors of the source and target domains or systems. To this end, in this paper, we propose a Deep framework for both Cross-Domain and Cross-System Recommendations, called DCDCSR, based on Matrix Factorization (MF) models and a fully connected Deep Neural Network (DNN). Specifically, DCDCSR first employs the MF models to generate user and item latent factors and then employs the DNN to map the latent factors across domains or systems. More importantly, we take into account the rating sparsity degrees of individual users and items in different domains or systems and use them to guide the DNN training process for utilizing the rating data more effectively. Extensive experiments conducted on three real-world datasets demonstrate that DCDCSR framework outperforms the state-of-the-art CDR and CSR approaches in terms of recommendation accuracy.

Graph Pattern Matching (GPM) has been used in lots of areas, like biology, medical science, and physics. With the advent of Online Social Networks (OSNs), recently, GPM has been playing a significant role in social network analysis, which has been widely used in, for example, finding experts, social community mining, and social position detection. Given a query which contains a pattern graph GQand a data graph GD, a GPM algorithm finds those subgraphs, GM, that match GQin GD. However, the existing GPM methods do not consider the multiple end-to-end constraints of the social contexts, like social relationships, social trust, and social positions on edges in GQ, which are commonly found in various applications, such as crowdsourcing travel, social network based ecommerce, and study group selection, etc. In this paper, we first conceptually extend Bounded Simulation to Multi-Constrained Simulation (MCS), and propose a novel NP-Complete Multi-Constrained Graph Pattern Matching (MC-GPM) problem. Then, to address the efficiency issue in large-scale MC-GPM, we propose a new concept called Strong Social Component (SSC), consisting of participants with strong social connections. We also propose an approach to identifying SSCs, and propose a novel index method and a graph compression method for SSC. Moreover, we devise a multithreading heuristic algorithm, called M-HAMC, to bidirectionally search the MC-GPM results in parallel without decompressing graphs. An extensive empirical study over five real-world large-scale social graphs has demonstrated the effectiveness and efficiency of our approach.

On a crowdsourcing platform, in order to cheat for rewards or sabotage the crowdsourcing processes, spam workers submit numerous random and erroneous answers to the tasks published by honest requesters. This type of behaviours extremely reduces the enthusiasm of honest users, which may lead a crowdsourcing platform to a failure. To defend the threats from spam workers, reputation-based defense mechanisms and verification-based defense mechanisms have been proposed in crowdsourcing environments. However, reputation-based defense fails to indicate the trust level of a worker who boosts its reputation by transacting with his/her accomplices. In addition, verification-based defense is costly and ineffective when facing a large number of spam workers with "good" reputations. Thus, it is a challenging problem to effectively defend the threats from spam workers. In this paper, we propose a new trust vector-based threat defense model CrowdDefense. Firstly, we build a Crowdsourcing Trust Network (CTN) consisting of requesters, workers and their transaction relations. Then, we analyze three threat patterns of spam workers. Based on the analysis, we infer the trust relation between a worker and a requester who are indirectly linked with each other. Moreover, we compute a worker's trust relations with different requesters, and present them in a new Worker Trust Vector (WTV) that indicates the worker's global trust. As spam workers always succeed in the transactions with their accomplices, they cannot obtain comprehensively good trust scores in their WTVs and thus are prevented from participating in tasks. The experiments demonstrate that CrowdsDefense significantly outperforms the state-of-the-art approaches in terms of preventing spam workers from participating in the tasks published by honest requesters.

To address the issue of data sparsity and cold-start in recommender system, social information (e.g., user-user trust links) has been introduced to complement rating data for improving the performances of traditional model-based recommendation techniques such as matrix factorization (MF) and Bayesian personalized ranking (BPR). Although effective, the utilization of the explicit user-user relationships extracted directly from such social information has three main limitations. First, it is difficult to obtain explicit and reliable social links. Only a small portion of users indicate explicitly their trusted friends in recommender systems. Second, the “cold-start” users are “cold” not only on rating but also on socializing. There is no significant amount of explicit social information that can be useful for “cold-start” users. Third, an active user can be socially connected with others who have different taste/preference. Direct usage of explicit social links may mislead recommendation. To address these issues, we propose to extract implicit and reliable social information from user feedbacks and identify top-k semantic friends for each user. We incorporate the top-k semantic friends information into MF and BPR frameworks to solve the problems of ratings prediction and items ranking, respectively. The experimental results on three real-world datasets show that our proposed approaches achieve better results than the state-of-the-art MF with explicit social links (with 3.0% improvement on RMSE), and social BPR (with 9.1% improvement on AUC).

The popularity of tagging systems provides a great opportunity to improve the performance of item recommendation. Although existing approaches use topic modeling to mine the semantic information of items by grouping the tags labelled for items, they overlook an important property that tags link users and items as a bridge. Thus these methods cannot deal with the data sparsity without commonly rated items (DS-WO-CRI) problem, limiting their recommendation performance. Towards solving this challenging problem, we propose a novel tag and rating based collaborative filtering (CF) model for item recommendation, which first uses topic modeling to mine the semantic information of tags for each user and for each item respectively, and then incorporates the semantic information into matrix factorization to factorize rating information and to capture the bridging feature of tags and ratings between users and items.As a result, our model captures the semantic correlation between users and items, and is able to greatly improve recommendation performance, especially in DS-WO-CRI situations.Experiments conducted on two popular real-world datasets demonstrate that our proposed model significantly outperforms the conventional CF approach, the state-of-the-art social relation based CF approach, and the state-of-the-art topic modeling based CF approaches in terms of both precision and recall, and it is an effective approach to the DS-WO-CRI problem.

In Online Social Networks (OSNs), the important participants, the trust relations between participants, and the interaction contexts between participants greatly impact a participant's decision-making in many applications, such as service provider selection and crowdsourcing service invocation. However, predicting the trust between two unknown participants based on the whole large-scale social network can lead to very high computation costs. Thus, prior to trust prediction, extracting a small-scale sub-network containing the important participants and the corresponding contextual information with a high density could make the trust prediction more efficient and effective. However, extracting such a sub-network has been proved to be an NP-Complete problem. To address this challenging problem, we propose a strong social component-aware trust sub-network extraction model, So-BiNet, to search for near-optimal solutions effectively and efficiently. Our method can extract a trust sub-network without any decompression, which can in turn greatly save the search time of trust sub-network extraction. The experiments, conducted on four social network datasets, demonstrate that our approach can efficiently extract sub-networks covering important participants and contextual information while keeping a high density. Our approach is superior to the state-of-the-art approaches in terms of the quality of the sub-networks extracted within the same execution time.

On a crowdsourcing platform consisting of requestersand workers, it is a challenge to recommend suitableworkers for a human intelligence task (HIT) published by a requester. A suitable worker is the one who has a high probability of submitting a correct answer for the published HIT. However, there are four problems that make the existing methods be less effective in recommending suitable workers. First, on most of crowdsourcing platforms, the great majority of workers have good reputations and thus are regarded as homogenous workers who have equal opportunities to be recommended. Secondly, dishonest workers may gain recommendations by counterfeiting good reputations and overstating personal skills. Moreover, the classical data sparsity and cold start problems co-exist in crowdsourcing environments. To effectively differentiate homogenous workers, we firstlycalculate a worker's performance in different types of HITspublished by different requesters. Aiming to improve the accuracy of predicting a worker's performance, we propose a metric which separately considers two requesters' similarities in transacting with the common workers they trust and in transacting with the common workers they distrust. Afterwards, targeting dishonest behaviours, we propose a transaction-based trust model. Targeting the data sparsity problem, we propose a new trust sub-network extraction algorithm (TSE) to discover more requesters who can provide trustworthy opinions for generating recommendations. Furthermore, we propose two strategiesfor solving the cold start problem. Finally, by incorporatingthe similarity metric, the new trust model, the new trustsub-network extraction algorithm and the new strategies, wepropose a novel trust-aware worker recommendation methodCrowdRec. The experimental results illustrate that CrowdRecsignificantly outperforms CF and three state-of-the-art trustbased recommendation methods both in terms of accuracy and coverage.

Cloud computing has provided an attractive model for business service delivery. However, accountability aspects, mainly the monitoring of the execution of a service contract, liability assignment and dispute arbitration are still lacking. On the one hand, the traditional centralized monitoring and the trusted-third party (TTP) based arbitration solutions are not suitable for the distributed cloud environment. On the other hand, a decentralized solution also faces challenges in guaranteeing fairness, accuracy and sustainability. To address this issue, this paper firstly proposes an innovative service contract management scheme that facilitates the monitoring of the execution of a service contract in a peer-to-peer environment, inspired by the concept of blockchain in Bitcoin. Secondly, on top of the scheme it presents a novel dispute resolution protocol based on the Byzantine agreement and the commitment scheme. Thirdly, it identifies the optimal settings of the key parameters of the protocol through a set of experiments and scenario analysis, aiming to strike the balance of fairness, accuracy, incentive maximization for the honest arbiters and cost minimization for the overall arbitration process. With this approach, service participants can be held accountable in a truly distributed environment without the presence of a central authority, which increases businesses confidence on adopting cloud services.

Graph Pattern Matching (GPM) plays a significant role in social network analysis, which has been widely used in, for example, experts finding, social community mining and social position detection. Given a pattern graph GQand a data graph GD, a GPM algorithm finds those subgraphs, GM, that match GQin GD. However, the existing GPM methods do not consider the multiple constraints on edges in GQ, which are commonly exist in various applications such as, crowdsourcing travel, social network based e-commerce and study group selection, etc. In this paper, we first conceptually extend Bounded Simulation to Multi-Constrained Simulation (MCS), and propose a novel NP-Complete Multi-Constrained Graph Pattern Matching (MC-GPM) problem. Then, to address the efficiency issue in large-scale MC-GPM, we propose a new concept called Strong Social Component (SSC), consisting of participants with strong social connections. We also propose an approach to identify SSCs, and propose a novel index method and a graph compression method for SSC. Moreover, we devise a heuristic algorithm to identify MC-GPM results effectively and efficiently without decompressing graphs. An extensive empirical study on five real-world large-scale social graphs has demonstrated the effectiveness, efficiency and scalability of our approach.

On a crowd sourcing platform consisting of task publishers and workers, it is critical for a task publisher to select trustworthy workers to solve human intelligence tasks (HITs). Currently, the prevalent trust evaluation mechanism employs the overall approval rate of HITs, with which dishonest workers can easily succeed in pursuing the maximal profit by quickly giving plausible answers or counterfeiting HITs approval rates. In crowd sourcing environments, a worker's trustworthiness varies in contexts, i.e. It varies in different types of tasks and different reward amounts of tasks. Thus, we propose two classifications based on task types and task reward amount respectively. On the basis of the classifications, we propose a trust evaluation model, which consists of two types of context-aware trust: task type based trust (TaTrust) and reward amount based trust (RaTrust). Then, we model trustworthy worker selection as a multi-objective combinatorial optimization problem, which is NP-hard. For solving this challenging problem, we propose an evolutionary algorithm MOWS_GA based on NSGA-II. The results of experiments illustrate that our proposed trust evaluation model can effectively differentiate honest workers and dishonest workers when both of them have high overall HITs approval rates.

Online Social Networks (OSNs) have become an integral part of daily life in recent years. OSNs contain important participants, the trust relations between participants, and the contexts in which participants interact with each other. All of these have a great influence on the prediction of the trust between a source participant and a target participant, which is important for a participant's decision-making process in many applications, such as seeking service providers. However, predicting the trust from a source participant to a target one based on the whole social network is not really feasible. Thus, prior to trust prediction, the extraction of a small-scale sub-network containing most of the important nodes and contextual information with a high density rate could make trust prediction more efficient and effective. However, extracting such a sub-network has been proved to be an NP-Complete problem. To address this challenging problem, we propose BiNet: a social context-aware trust sub-network extraction model to search for near-optimal solutions effectively and efficiently. In this model, we first capture important factors that affect the trust between participants in OSNs. Next, we define a utility function to measure the trust factors of each node in a social network. At last, we design a novel binary ant colony algorithm with newly designed initialization and mutation processes for sub-network extraction incorporating the utility function. The experiments, conducted on two popular datasets of Epinion and Slash dot, demonstrate that our approach can extract sub-networks covering important participants and contextual information while keeping a high density rate. Our approach is superior to the state-of-the-art approaches in terms of the quality of extracted sub-networks within the same execution time.

Online Social Networks (OSNs) have been used as the means for a variety of applications, like employment system, e-Commerce and CRM system. In these applications, social influence acts as a significant role, affecting people's decision-making. However, the existing social influence evaluation methods do not fully consider the social contexts, like the social relationships and the social trust between participants, and the preferences of participants, which have significant impact on social influence evaluation in OSNs. Thus, these existing methods cannot deliver accurate social influence evaluation results. In our paper, we propose a Context-Aware Trust-Oriented Influencers Finding method, called CT-Influence, with social contexts taken into account. We conduct experiments onto two real social network datasets, i.e., Epinions and DBLP. The experimental results illustrate that our CT-Influence method greatly outperforms the state-of-the-art method So Cap in terms of effectiveness and efficiency.

Due to the diversity and dynamic nature of cloud services, it is usually hard for potential cloud consumers to select the most suitable cloud service. This paper proposes CCCloud: a context-aware and credible cloud service selection model based on the comparison and aggregation of subjective assessments extracted from ordinary cloud consumers and objective assessments from quantitative performance testing parties. We propose a novel approach to evaluate cloud users' credibility, which not only can accurately evaluate how truthfully they assess cloud services, but also resist user collusion. In addition, in our model, objective assessments are used as benchmarks to filter out potentially biased subjective assessments, and then objective assessments and subjective assessments are aggregated to evaluate the overall performance of a cloud service. Furthermore, our model takes the contexts of objective assessments and subjective assessments into account. By calculating the similarity between different contexts, the benchmark level of objective assessments is dynamically adjusted according to context similarity, and the aggregated final scores of alternative cloud services are weighted by the similarity between the contexts of a potential cloud consumer and every testing party. This makes our cloud service selection model reflect potential cloud consumers' customized requirements more effectively. Finally, our proposed model is evaluated through the experiments conducted under different conditions. The experimental results demonstrate that our model significantly outperforms the existing work, especially in the resistance of user collusion.

In e-commerce environments, the trustworthiness of a seller is utterly important to potential buyers, especially when a seller is not known to them. Most existing trust evaluation models compute a single value to reflect the general trustworthiness of a seller without taking any transaction context information into account. With such a result as the indication of reputation, a buyer may be easily deceived by a malicious seller in a transaction where the notorious value imbalance problem is involved—in other words, a malicious seller accumulates a high-level reputation by selling cheap products and then deceives buyers by inducing them to purchase more expensive products. In this article, we first present a trust vector consisting of three values for contextual transaction trust (CTT). In the computation of CTT values, three identified important context dimensions , including Product Category, Transaction Amount, and Transaction Time, are taken into account. In the meantime, the computation of each CTT value is based on both past transactions and the forthcoming transaction. In particular, with different parameters specified by a buyer regarding context dimensions, different sets of CTT values can be calculated. As a result, all of these trust values can outline the reputation profile of a seller that indicates the dynamic trustworthiness of a seller in different products, product categories, price ranges, time periods, and any necessary combination of them. We name this new model ReputationPro . Nevertheless, in ReputationPro , the computation of reputation profile requires new data structures for appropriately indexing the precomputation of aggregates over large-scale ratings and transaction data in three context dimensions, as well as novel algorithms for promptly answering buyers’ CTT queries. In addition, storing precomputed aggregation results consumes a large volume of space, particularly for a system with millions of sellers. Therefore, reducing storage space for aggregation results is also a great demand. To solve these challenging problems, we first propose a new index scheme CMK-tree by extending the two-dimensional K-D-B-tree that indexes spatial data to support efficient computation of CTT values. Then, we further extend the CMK-tree and propose a CMK-tree RS approach to reducing the storage space allocated to each seller. The two approaches are not only applicable to three context dimensions that are either linear or hierarchical but also take into account the characteristics of the transaction-time model—that is, transaction data is inserted in chronological order. Moreover, the proposed data structures can index each specific product traded in a time period to compute the trustworthiness of a seller in selling a product. Finally, the experimental results illustrate that the CMK-tree is superior in efficiency of computing CTT values to all three existing approaches in the literature. In particular, while answering a buyer’s CTT queries for each brand-based product category, the CMK-tree has almost linear query performance. In addition, with significantly reduced storage space, the CMK-tree RS approach can further improve the efficiency in computing CTT values. Therefore, our proposed ReputationPro model is scalable to large-scale e-commerce Web sites in terms of efficiency and storage space consumption.

Online social networking sites have become popular platforms on which users can link with each other and share information, not only basic rating information but also information such as contexts, social relationships, and item contents. However, as far as we know, no existing works systematically combine diverse types of information to build more accurate recommender systems. In this paper, we propose a novel context-aware hierarchical Bayesian method. First, we propose the use of spectral clustering for user-item subgrouping, so that users and items in similar contexts are grouped. We then propose a novel hierarchical Bayesian model that can make predictions for each user-item subgroup, our model incorporate not only topic modeling to mine item content but also social matrix factorization to handle ratings and social relationships. Experiments on an Epinions dataset show that our method significantly improves recommendation performance compared with six categories of state-of-the-art recommendation methods in terms of both prediction accuracy and recall. We have also conducted experiments to study the extent to which ratings, contexts, social relationships, and item contents contribute to recommendation performance in terms of prediction accuracy and recall.

Online social networks have been used for a variety of rich activities in recent years, such as investigating potential employees and seeking recommendations of high quality services and service providers. In such activities, trust is one of the most critical factors for the decision-making of users. In the literature, the state-of-the-art trust prediction approaches focus on either dispositional trust tendency and propagated trust of the pair-wise trust relationships along a path or the similarity of trust rating values. However, there are other influential factors that should be taken into account, such as the similarity of the trust rating distributions. In addition, tendency, propagated trust and similarity are of different types, as either personal properties or interpersonal properties. But the difference has been neglected in existing models. Therefore, in trust prediction, it is necessary to take all the above factors into consideration in modeling, and process them separately and differently. In this paper we propose a new trust prediction model based on trust decomposition and matrix factorization, considering all the above influential factors and differentiating both personal and interpersonal properties. In this model, we first decompose trust into trust tendency and tendency-reduced trust. Then, based on tendency-reduced trust ratings, matrix factorization with a regularization term is leveraged to predict the tendency-reduced values of missing trust ratings, incorporating both propagated trust and the similarity of users' rating habits. In the end, the missing trust ratings are composed with predicted tendency-reduced values and trust tendency values. Experiments conducted on a real-world dataset illustrate significant improvement delivered by our approach in trust prediction accuracy over the state-of-the-art approaches.

Online Social Networks (OSNs) have been used to enhance service provision and service selection, where trust is one of the most important factors for the decision making of service consumers. Thus, it is significant to evaluate the trustworthiness of the service providers along the social trust paths from a service consumer to a service provider. However, there are usually many social trust paths between an unknown service consumer and service provider. Thus, a challenging problem is how to effectively and effciently find those social trust paths that can yield trustworthy trust evaluation results based on the requirements of a service consumer particularly in the real-time OSN environments. In this paper, we first present a contextual trust-oriented social network structure and a concept of Quality of Trust (QoT). We then model the multiple social trust paths finding with end-to-end QoT constraints as the Multiple Constrained K Optimal Paths (MCOP-K) selection problem, which is NP-Complete. To deal with this challenging problem, based on the Monte Carlo method and our optimization search strategies, we propose a new efficient and effective approximation algorithm D-MCBA. The results of our experiments conducted on a real-world dataset of OSNs illustrate that D-MCBA can efficiently identify the social trust paths with better quality than our previously proposed MONTE K algorithm that is the most promising algorithm for the social trust path finding in OSNs.

This paper proposes a novel context-aware cloud service selection model based on the comparison and aggregation of subjective assessment extracted from cloud user feedback and objective assessment from quantitative performance testing. In this model, objective assessment provided by some professional testing parties is used as a benchmark to filter out potentially biased subjective assessment from cloud users, then objective assessment and subjective assessment are aggregated to evaluate the overall performance of cloud services according to potential cloud users' personalized requests. Moreover, our model takes the contexts of objective assessment and subjective assessment into account. By calculating the similarity between different contexts, the benchmark level of objective assessment is dynamically adjusted according to context similarity, which makes the following comparison and aggregation process more accurate and effective. After aggregation, the final results can quantitatively reflect the overall quality of cloud services. Finally, our proposed model is evaluated through the experiments executed in different conditions.

Cloud computing services have been increasingly considered by business as a viable option for reducing IT expenditure. The highly automated and agile nature of cloud services offer businesses low cost, high efficiency and flexibility benefits. However, there are often associated problems with unmanaged accountability such as lack of disclosure of service obligations, mechanisms for detection for obligation fulfilment or determination of liable party if an obligation is violated. This paper analyses the accountability properties of a cloud service and proposes an accountable cloud service (ACS) model to address those problems. The ACS model is underpinned by a hybrid logic system called Dynamic Logic for Accountability (DLA) extended from Dynamic Logic. ACS provides an intuitive notation for modeling service collaboration diagrams based on a reduced version of BPMN2.0 to capture the fulfillment of service obligations. We also propose an Obligation Flow Diagram (OFD) as a simple method for conflict resolution and verification for the ACS model. The ACS model enables obligation specification, decomposition, validation, machine-interpretation, monitoring and reasoning, and ultimately facilitates accountability in cloud service consumption. Using Amazon S3 service as a case study, we show how to address those known accountability problems using our ACS model. Finally we discuss the applicability of our model to cloud services in general.

ABSTRACT In e‐commerce environments, the reputation of sellers is a crucial issue to potential buyers in making decisions. Most existing trust evaluation models compute a single value to reflect the general trust level of a seller without taking any transaction context into account. With such a simple trust evaluation model, a buyer may be easily deceived by a malicious seller in a transaction where the notoriousvalue imbalance problemis involved, namely, the malicious seller can accumulate a high level of trust by selling cheap products and then start to deceive buyers by inducing them to purchase expensive products. In this article, we first present a trust vector consisting of four trust values (termed asCTTvalues), the computation of each of which is based on both past transactions and the forthcoming transaction. In addition, in the computation of CTT values, the parameters, such as product category, price range, and time range, can be specified and adjusted by the buyer, yielding different sets of trust values that can outline the seller's reputation profile. As a result, the value imbalance problem potentially existing in a forthcoming transaction can be identified. The computation of CTT values requires the pre‐computation of aggregates over large‐scale ratings and transaction data with necessary combinations of three dimensions (i.e., product category, price, and time), so as to deliver prompt responses to a buyer's query on different CTT values. In solving this challenging problem, we propose three new data structures and algorithms that mainly focus on efficient computation of CTT values. Our experiments conducted on both eBay data sets and large‐scale synthetic data sets illustrate the advantages and disadvantages of our proposed approaches when responding to a buyer's CTT queries. Copyright © 2014 John Wiley & Sons, Ltd.

Reputation-based trust models are widely used in e-commerce applications, and feedback ratings are aggregated to compute sellers' reputation trust scores. The “all good reputation” problem, however, is prevalent in current reputation systems-reputation scores are universally high for sellers and it is difficult for potential buyers to select trustworthy sellers. In this paper, based on the observation that buyers often express opinions openly in free text feedback comments, we propose CommTrust for trust evaluation by mining feedback comments. Our main contributions include: 1) we propose a multidimensional trust model for computing reputation scores from user feedback comments; and 2) we propose an algorithm for mining feedback comments for dimension ratings and weights, combining techniques of natural language processing, opinion mining, and topic modeling. Extensive experiments on eBay and Amazon data demonstrate that CommTrust can effectively address the “all good reputation” issue and rank sellers effectively. To the best of our knowledge, our research is the first piece of work on trust evaluation by mining feedback comments.

Online trading takes place in a very complex environment full of uncertainty in which deceitful service providers or sellers may strategically change their behaviors to maximize their profits. The proliferation of deception cases makes it essential and challenging to model the dynamics of a service provider and predict the trustworthiness of the service provider in transactions. Recently, probabilistic trust models have been used to assist decision making in computing environments. Although the typical Hidden Markov Model (HMM) has been used to model a provider's behavior dynamics, existing approaches focus only on the outcomes or ignore the hidden characteristics of the HMM model. In this paper, we model the dynamic trust of service providers concerning a forthcoming transaction in light of as much information as we can consider, including the static features, such as the provider's reputation and item price, and the dynamic features, such as the latest profile changes of a service provider and price changes. Based on a service provider's historical transactions, we predict the trustworthiness of the service provider in a forthcoming transaction. In addition, the Mutual Information theories and the Principle Component Analysis method are leveraged to eliminate redundant information and combine essential features to form lower dimensional feature vectors. Furthermore, by adopting Vector Quantization techniques, we apply the discrete HMM in a more powerful way, in which all the features extracted from both contextual information and the rating of each transaction are treated as observations of HMM. We evaluate our approach empirically in order to study its performance. The experiment results illustrate that our approach significantly outperforms the state-of-the-art probabilistic trust methods in accuracy in the cases with complex changes.

Online Social networks have provided the infrastructure for a number of emerging applications in recent years, e.g., for the recommendation of service providers or the recommendation of files as services. In these applications, trust is one of the most important factors in decision making by a service consumer, requiring the evaluation of the trustworthiness of a service provider along the social trust paths from a service consumer to the service provider. However, there are usually many social trust paths between two participants who are unknown to one another. In addition, some social information, such as social relationships between participants and the recommendation roles of participants, has significant influence on trust evaluation but has been neglected in existing studies of online social networks. Furthermore, it is a challenging problem to search the optimal social trust path that can yield the most trustworthy evaluation result and satisfy a service consumer's trust evaluation criteria based on social information. In this paper, we first present a novel complex social network structure incorporating trust, social relationships and recommendation roles, and introduce a new concept, Quality of Trust (QoT), containing the above social information as attributes. We then model the optimal social trust path selection problem with multiple end-to-end QoT constraints as a Multiconstrained Optimal Path (MCOP) selection problem, which is shown to be NP-Complete. To deal with this challenging problem, we propose a novel Multiple Foreseen Path-Based Heuristic algorithm MFPB-HOSTP for the Optimal Social Trust Path selection, where multiple backward local social trust paths (BLPs) are identified and concatenated with one Forward Local Path (FLP), forming multiple foreseen paths. Our strategy could not only help avoid failed feasibility estimation in path selection in certain cases, but also increase the chances of delivering a near-optimal solution with high quality. The results of our experiments conducted on a real data set of online social networks illustrate that MFPB-HOSTP algorithm can efficiently identify the social trust paths with better quality than our previously proposed H_OSTP algorithm that outperforms prior algorithms for the MCOP selection problem.

Trust is one of the most important factors for participants' decision-making in Online Social Networks (OSNs). The trust network from a source to a target without any prior interaction contains some important intermediate participants, the trust relations between the participants, and the social context, each of which has an important influence on trust evaluation. Thus, before performing any trust evaluation, the contextual trust network from a given source to a target needs to be extracted first, where constraints on the social context should also be considered to guarantee the quality of extracted networks. However, this problem has been proved to be NP-Complete. Towards solving this challenging problem, we first propose a complex contextual social network structure which considers social contextual impact factors. These factors have significant influences on both social interaction between participants and trust evaluation. Then, we propose a new concept called QoTN (Quality of Trust Network) and a social context-aware trust network discovery model. Finally, we propose a Social Context-Aware trust Network discovery algorithm (SCAN) by adopting the Monte Carlo method and our proposed optimization strategies. The experimental results illustrate that our proposed model and algorithm outperform the existing methods in both algorithm efficiency and the quality of the extracted trust network.

Online Social Networks (OSNs) have provided an infrastructure for a number of emerging applications in recent years, e.g., for the recommendation of service providers, where trust is one of the most important factors for the decision-making of service consumers. In order to evaluate the trustworthiness of a service provider (i.e., the target) without any prior interaction with a service consumer (i.e., the source), the trust network from the source to the target need to be extracted firstly before performing any trust evaluation, as it contains some important intermediate participants, the trust relations between the participants, and the social context, each of which has an important influence on trust evaluation. However, the network extraction has been proved to be NP-Complete. Towards solving this challenging problem, we first propose a complex contextual social network structure which considers some social contexts, having significant influences on both social interactions and trust evaluation between participants. Then, we propose a new concept called QoTN (Quality of Trust Network) and a social context-aware trust network discovery model. Finally, we propose a Heuristic Social Context-Aware trust Network discovery algorithm (H-SCAN) by adopting the K-Best-First Search (KBFS) method and our optimization strategies. The experimental results illustrate that our proposed model and algorithm outperform the existing methods in both algorithm efficiency and the quality of the extracted trust networks.

In recent years, online social networks with numerous participants have been used as the means for rich activities, where trust is one of the most important indications for participants' decision making, demanding the evaluation of the trustworthiness of a target participant along a certain social trust path from a source participant. However, there are usually many social trust paths between participants. Thus, a challenging problem is how to select the optimal one from massive social trust paths yielding the most trustworthy trust evaluation result based on participants trust evaluation criteria. To address this issue, in this paper, we first propose a new Multiple QoT Constrained Social Trust Path (MQCSTP) selection model which considers both adjacent constraints and end-to-end constraints, based on a novel concept Quality of Trust (QoT) and a novel complex social network structure. We then model the MQCSTP selection as the classical NP-Complete Multi-Constrained Optimal Path (MCOP) selection problem. For solving this problem, we propose an effective and efficient heuristic algorithm, called H_MQCSTP. The results of our experiments conducted on a real dataset of online social networks illustrate that the proposed method outperforms existing models in both efficiency and the quality of delivered solutions.

In e-commerce environments, trust is a dominating factor in seller selection. Most existing trust evaluation studies compute a single value to reflect the "general' or "global" trust level of a seller provider without any contextual transaction information taken into account. As a result, a buyer may be easily deceived by a malicious seller in a forthcoming transaction. For example, with the notorious "value imbalance problem", a malicious seller can build up a high trust level by selling cheap products and then starts to deceive buyers in selling expensive products. To detect this problem and avoid massive monetary losses of buyers, trust evaluation should be associated with both past transactions and the new one, and take transaction context into account. In particular, the computed trust result should outline the seller's reputation profile indicating the trust level in a specific product or a product category, a price range, a time period or any necessary combination of them. However, this need requires complex computation and thus new data structures and efficient algorithms. In this paper, we design a new data structure to support the CTT computation in e-commerce environments. In addition, based on the new data structures, we further propose an approach for promptly responding to a buyer's CTT query. The conducted experiments illustrate that our proposed structure and approach can yield much shorter computation time than the existing approaches.

In Online Social Networks (OSNs), participants can conduct rich activities, where trust is one of the most important factors for their decision making. This necessitates the evaluation of the trustworthiness between two unknown participants along the social trust paths between them based on the trust transitivity properties (i.e., if A trusts B and B trusts C, then A can trust C to some extent). In order to compute more reasonable trust value between two unknown participants, a critical and challenging problem is to make clear how and to what extent trust is transitive along a social trust path. To address this problem, we first propose a new complex social network structure that takes, besides trust, social relationships, recommendation roles and preference similarity between participants into account. These factors have significant influence on trust transitivity. We then propose a general concept, called Quality of Trust Transitivity (QoTT), that takes any factor with impact on trust transitivity as an attribute to illustrate the ability of a trust path to guarantee a certain level of quality in trust transitivity. Finally, we propose a novel Multiple QoTT Constrained Trust Transitivity (MQCTT) model. The results of our experiments demonstrate that our proposed MQCTT model follows the properties of trust and the principles illustrated in social psychology, and thus can compute more resonable trust values than existing methods that consider neither the impact of social aspects nor the properties of trust.

With the advent of service-oriented computing, the issue of trust and Quality of Service (QoS) have become increasingly important. In service-oriented environments, when there are a few service providers providing the same service, a service client would be keen to know the trustworthiness of each service provider in the forthcoming transaction. The trust rating of a delivered service from a service provider can be predicted according to a set of advertised QoS data collected by the trust management authority. Although trust and QoS are qualitative by nature, most data sets represent trust and QoS in the ordinal form for the sake of simplicity. This paper introduces a new approach based on Fuzzy Linear Regression Analysis (FLRA) to extract qualitative information from quantitative data and so use the obtained qualitative information for better modeling of the data. For verification purposes, the proposed approach can be applied for the trust prediction in the forthcoming transaction based on a set of advertised QoS in service-oriented environments.

In Service-Oriented Computing (SOC) environments, the trustworthiness of each service provider is critical for a service client when selecting one from a large pool of service providers. The trust value of a service provider is usually in the range of [0, 1] and is evaluated from the ratings given by service clients, which represent the subjective belief of service clients on the satisfaction of delivered services. So a trust value can be taken as a subjective probability, by which one party believes that another party can perform an action in a certain situation. Hence, subjective probability theory should be adopted in trust evaluation. In addition, in SOC environments, a service provider usually can invoke the services from other service providers forming a composite service. Thus, the global trust of a composite service should be evaluated based on both the subjective probability property of trust and complex invocation structures. In this paper, we first interpret the trust dependency caused by direct service invocations as conditional probability. Then, on the basis of trust dependency, we propose a Subjective probability based deductive (SELECTIVE) approach to evaluate the subjective global trustworthiness of a composite service. All these processes follow subjective probability theory and keep the subjective probability property of trust in evaluations. Our experimental results demonstrate that when compared with existing approaches our proposed SELECTIVE approach can yield more reasonable results.

In a service-oriented online social network consisting of service providers and consumers as participants, a service consumer can search trustworthy service providers via the social network between them. This requires the evaluation of the trustworthiness of a service provider along a potentially very large number of social trust paths from the service consumer to the service provider. Thus, a challenging problem is how to identify K optimal social trust paths that can yield the K most trustworthy evaluation results based on service consumers' evaluation criteria. In this paper, we first present a complex social network structure and a concept, Quality of Trust (QoT). We then model the K optimal social trust paths selection with multiple end-to-end QoT constraints as the Multiple Constrained K Optimal Paths (MCOP-K) selection problem, which is NP-Complete. For solving this challenging problem, based on Dijkstra's shortest path algorithm and our optimization strategies, we propose a heuristic algorithm H-OSTP-K with the time complexity of O(m+Knlogn). The results of our experiments conducted on a real dataset of online social networks illustrate that H-OSTP-K outperforms existing methods in the quality of identified social trust paths.

The trust of sellers and transactions is a very important issue in e-commerce and e-service environments. At some e-commerce websites (such as eBay1), the trust management mechanism can compute a trust value of a seller, which is based on the ratings of past transactions given by buyers. This trust value, however, is static and can only reflect the general or global trust status of a seller, and it is not directly bound to a new transaction. As a result, a buyer maybe easily cheated by a malicious seller in a new transaction with the notorious value imbalance problem [5], i.e., the malicious seller can build up a good reputation by selling cheap products/services and then start to cheat buyers by selling expensive products/services. Instead of providing such a static trust value, in order to provide more objective trust result for anew potential transaction, a trust evaluation mechanism should based on the ratings of past transactions, the nature of both past transactions and the new transaction. In this paper, we propose a new contextual trust evaluation method. Our method compares the transaction context similarity between the new transaction and past transactions, from which the trust value of the new transaction can be determined. Our method can identify and prevent potentially malicious transactions with the value imbalance problem.

In most existing trust evaluation studies, a single value is computed based on the ratings given to a service provider to indicate the current trust level. This is useful but may not represent the trust features well under certain circumstances. Alternatively, a complete set of trust ratings can be transferred to a service client for local trust calculation. But this obviously creates a big overhead in communication as the data set usually has a large size covering a long service history. In this paper, we present a novel two-dimensional aggregation approach consisting of both vertical and horizontal aggregations of trust ratings. The vertical aggregation calculates the aggregated rating representing the trust level for the services delivered in a small time period. The horizontal aggregation applies our proposed optimal algorithm to determine the minimal number of time intervals, within each of which a trust vector with three values can be calculated to represent all the ratings in that time interval and retain the trust features well. Hence, a small set of trust vectors can represent a large set of trust ratings. This is significant for large-scale trust rating transmission and trust evaluation. Experiments have been conducted to illustrate the properties of our proposed approach.

In Service-Oriented Computing (SOC) environments, the trustworthiness of each service is critical for a service client when selecting one from a large pool of services. The trust value of a service is usually in the range of [0,1] and is evaluated from the ratings given by service clients, which represent the subjective belief of these service clients on the satisfaction of delivered services. So a trust value can be taken as the subjective probability, with which one party believes that another party can perform an action in a certain situation. Hence, subjective probability theory should be adopted in trust evaluation. In addition, in SOC environments, a service usually invokes other services offered by different service providers forming a composite service. Thus, the global trust of a composite service should be evaluated based on complex invocation structures. In this paper, firstly, based on Bayesian inference, we propose a novel method to evaluate the subjective trustworthiness of a service component from a series of ratings given by service clients. Secondly, we interpret the trust dependency caused by service invocations as conditional probability, which is evaluated based on the subjective trust values of service components. Furthermore, we propose a joint subjective probability method to evaluate the subjective global trust of a composite service on the basis of trust dependency. Finally, we introduce the results of our conducted experiments to illustrate the properties of our proposed subjective global trust inference method.

Online social networks are becoming increasingly popular and are being used as the means for a variety of rich activities. This demands the evaluation of the trustworthiness between two unknown participants along a certain social trust path between them in the social network. However, there are usually many social trust paths between participants. Thus, a challenging problem is finding which social trust path is the optimal one that can yield the most trustworthy evaluation result.In this paper, we first present a new complex social network structure and a new concept of Quality of Trust (QoT) to illustrate the ability to guarantee a certain level of trustworthiness in trust evaluation. We then model the optimal social trust path selection as a Multi-Constrained Optimal Path (MCOP) selection problem which is NP-Complete. For solving this problem, we propose an efficient approximation algorithm MONTE K based on the Monte Carlo method. The results of our experiments conducted on a real dataset of social networks illustrate that our proposed algorithm significantly outperforms existing approaches in both efficiency and the quality of selected social trust paths.

In the business context, accountability has become a major concern for businesses around the world in aftermath of corporate scandals and fallouts. However, accountability has not been rigorously considered in IT system technologies and solutions. The goal of this study is to provide a clear understanding of accountability concept in service-oriented computing and, more generally, e-society. We first outline the general concept of accountability and presents a review on accountability from both management and IT perspective. We also clarify the ambiguity between the accountability concern and other architectural concerns such as security, QoS, trust and reputation.We present an SOA research project, the Llama accountability framework, which is an accountable service delivery infrastructure to support the monitoring, analysis, and reconfiguration of service processes. We believe such a framework will be useful for ensuring better e-services in an e-society.

Since Representational State Transfer (REST) architecture was proposed by Fielding in early 1990s for distributed hypermedia systems, it has become a popular architectural style of choice in various computing environments. However, REST was not originally designed to support enterprise requirements, in particular the accountability requirements that are crucial for the business services offered through the Software as a Service (SaaS) and Cloud Computing environments. In this paper, we propose an Accountable State Transfer (AST) architecture to bridge the accountability gap in REST. With AST, service participants can be held accountable for each representational state transfer during service consumption. A formal service contract model with a hybrid reasoning mechanism and a novel accountable state transfer protocol are designed as the mechanisms underpinning the AST architecture. Moreover, we implement a Credit Check service prototype based on AST, demonstrating the practicality of such architecture. Inheriting REST's scalability, AST architecture provides the much needed accountability capabilities for the virtual service delivery environment.

Trust is a critical issue in e-commerce and e-service environments. In some applications (such as eBay), the trust management mechanisms have been introduced to provide valuable information to buyers prior to placing orders and making payments. Meanwhile, the trust issue is also actively studied in the research community. However, most studies and applications focus on approaches that result in a single trust value to represent the trust level of sellers or service providers. Such a simple trust evaluation method may not be able to depict the trust history exactly and may leave misleading information to service customers. In this paper, we present a novel approach of trust vector consisting of three values to reflect the trust level with more indications.

Web services specification provides an open standard for the distributed service oriented architecture. It is widely used in Internet and pervasive networks supporting wireless mobile devices. A mobile agent is a composition of computer software and data which is able to migrate from one host to another autonomously and continue its execution on the destination host. Mobile agent technology can reduce the bandwidth requirement and tolerate the network faults - able to operate without an active connection between clients and server. Hence, the applications of the combination of mobile agents and web service have been widely investigated in recent years. However, the security issue is still of a major concern. In this paper, we propose a novel agent-based web service security scheme. This scheme provides a new authentication protocol without using the user- name/password pair, which is infeasible for mobile agent, and gives an alternative method to current security mechanism without using Certification Authorities (CA) based public key infrastructure. With this scheme, we can simplify the key management and reduce the computation particularly for group-oriented web services.

The mobile agent approach is suitable for deploying large-scale parallel processing over distributed hosts. However, if the number of mobile agents is very large and the dispatch is processed in a serial way, it can become a bottleneck that impacts the efficiency as a whole. In this paper, we first briefly present a mobile agent based framework for Internet marketplaces enabling parallel processing. Then we present and discuss several hierarchical dispatch models where the dispatch of multiple mobile agents can be processed in parallel over different hosts. In the best case, the time complexity for dispatching n mobile agents is O(log/sub 2//sup n/). Discussions of these models are taken on the basis of theoretical analysis and experiments.

In this paper, we propose a framework of Internet marketplaces on the basis of mobile agent. It not only simulates real commercial activities by consumers, agents and merchants, but also provides an environment for parallel processing. The latter is particularly important as more shops (sites) can be searched in real time to provide consumers with better choices. The conducted experiments show that, in comparison with several serial mobile agent models, parallel mobile agent model can improve the performance significantly.

We propose a 2-phase evaluation model that can be applied to agent-mediated Internet marketplaces. The model not only facilitates parallel processing, it also allows mobile agents to select online shops (e-shops) and evaluate offers autonomously and automatically. To provide the "best" answer, the approach considers multiple attributes of an e-shop and an offer, such as the commercial credit and security rank of the e-shop, price, delivery/shipment service and warranty service of an offer. Moreover, with the fuzzy-set rules, the evaluation results are more reasonable and accord with human behavior. With the 2-phase evaluation of this model, it can not only help to control the scale of the dispatched mobile agent to a rational level to reduce the burden of network traffic, but also help to evaluate offers to assist users to make good decisions.

Presents a mobile agent-based three-tier protocol to improve the data transmission while accessing distributed databases. When a mobile agent is employed to fulfil a distributed query, it has many choices for travelling in the network. The master/slave pattern can be applied to mobile agents on the basis of a centralized two-phase commit (2PC) protocol to allow the parallel execution of mobile agents. In this paper, a three-tier protocol is proposed, which clusters all the slave agents to strengthen the parallelism. This three-tier protocol can significantly weaken the data transmission bottleneck and reduce the response time. This paper describes the protocol and a performance evaluation of it.