Predicting diseases solely from patient-side information, such as demographics and self-reported symptoms, has attracted significant research attention due to its potential to enhance patient awareness, facilitate early healthcare engagement, and improve healthcare system efficiency. However, existing approaches encounter critical challenges, including imbalanced disease distributions and a lack of interpretability, resulting in biased or unreliable predictions. To address these issues, we propose the Knowledge graph-enhanced, Prototype-aware, and Interpretable (KPI) framework. KPI systematically integrates structured and trusted medical knowledge into a unified disease knowledge graph, constructs clinically meaningful disease prototypes, and employs contrastive learning to enhance predictive accuracy, which is particularly important for long-tailed diseases. Additionally, KPI utilizes large language models (LLMs) to generate patient-specific, medically relevant explanations, thereby improving interpretability and reliability. Extensive experiments on real-world datasets demonstrate that KPI outperforms state-of-the-art methods in predictive accuracy and provides clinically valid explanations that closely align with patient narratives, highlighting its practical value for patient-centered healthcare delivery.

Relational databases (RDBs) underpin the majority of global data management systems, where information is structured into multiple interdependent tables. In social media platforms, for instance, massive user-generated data are organized across related tables such as users, posts, comments, and interactions, enabling large-scale analysis and predictive modeling of social behaviors. To effectively use the knowledge within RDBs for predictive tasks, recent advances leverage graph representation learning to capture complex inter-table relations as multi-hop dependencies. Despite achieving state-of-the-art performance, these methods remain hindered by the prohibitive storage overhead and excessive training time, due to the massive scale of database and the computational burden of intensive message passing across interconnected tables. To alleviate these concerns, we propose and study the problem of Relational Database Distillation (RDD). Specifically, we aim to distill large-scale RDBs into compact heterogeneous graphs while retaining the predictive power (i.e., utility) required for training graph-based models. Multi-modal column information is preserved through node features, and primary–foreign key relations are encoded via heterogeneous edges, thereby maintaining both data fidelity and relational structure. To ensure adaptability across diverse downstream tasks without engaging the traditional, inefficient bi-level distillation framework, we further design a kernel ridge regression-guided objective with pseudo-labels, which produces quality features for the distilled graph. Extensive experiments on multiple real-world RDBs demonstrate that our solution substantially reduces the data size while maintaining competitive performances on classification and regression tasks, creating an effective pathway for scalable learning with RDBs.

Temporal Graph Neural Networks (TGNNs) are increasingly applied in dynamic scenarios, however, their limited explainability hinders their adoption in high-stakes domains. Existing methods tend to conflate causality with temporal proximity, leading to ambiguous explanations that mix impactful and irrelevant events. Moreover, they lack counterfactual reasoning to assess whether altering specific temporal events would change TGNN predictions. To overcome these challenges, we propose CTM-Explainer, which identifies critical temporal dependencies through iterative “what-if” perturbation analysis. To the best of our knowledge, this is the first post-hoc counterfactual explanation framework for TGNN. It enables precise attribution of how specific timestamped events influence TGNN predictions. By embedding causal analysis into a reinforcement learning framework, CTM-Explainer constructs Counterfactual Temporal Motifs (CTMs) that are causally grounded in model outcome shifts via interventional probability estimation. This design eliminates temporally correlated but non-essential events, while preserving those with verified causal influence. Extensive experiments on real-world and synthetic datasets confirm that CTM-Explainer generates more faithful and concise explanations than existing methods, at significantly lower computational cost.

Automated electrocardiogram (ECG) classification tasks play a crucial role in clinical but face challenges due to the scarcity of accessible and well-labeled data. ECG data augmentation is an effective way to address these challenges, either by altering the characteristics of real ECG data or using statistical and generative models to generate labeled data. However, the generated data often suffer from noise in both the data and label, which can reduce the performance of classification models. To address this, we propose a novel self-iterative two-stage data augmentation method for automated ECG classification, called SiTs-ECG. In the generation stage, an unconditional diffusion model, guided by a Transformer encoder, is trained to capture the complex characteristics of long-term ECG signals, generating high-quality ECG-like samples. In the selection stage, the generated samples are assigned pseudo-labels by a well-trained base classification model, and those generated samples for which the model can confidently predict the pseudo-labels are selected. We then integrate these stages into a self-iterative training process to continually improve the performance of base classification model. Extensive experiments on three real-world datasets demonstrate the effectiveness of our method. Notably, on the Apnea-ECG dataset, using ECG-Transformer as the downstream classification model, Precision, Recall, F1, and Accuracy are improved by 7.9, 9.1, 9.2, and 7.3 percentage points, respectively. Furthermore, our method is versatile and compatible with various generative and downstream classification models, showing promising applications in automated ECG classification in the clinical field.

Traffic prediction plays a crucial role in smart cities. As concerns over data privacy grow, direct data sharing is increasingly restricted, prompting substantial interest in Federated Graph Learning for traffic prediction. Nonetheless, most existing methods follow batch learning paradigms, which are unsuitable for dynamic, streaming traffic data. In practical applications, traffic data arrives continuously, calling for online learning techniques. Moreover, current methods often rely on split learning to capture spatio-temporal dependencies, which increases communication overhead and latency, limiting their real-time applicability. To this end, we propose aswiftonlinefederated Graph Learning Framework for Traffic Streaming Data Prediction (Sofedfor short). We introduce an early training strategy to equip clients with the up-to-date local temporal models and dynamic spatial features, enabling rapid adaptation to traffic fluctuations while minimizing client response time. Additionally, we pre-train a masked data generation module to synthesize multi-step data, effectively decoupling the server from real-time ground-truth dependency and enhancing model generalization. Lastly, the client model is optimized for lightweight deployment by offloading specific components to the server. Extensive experiments on real-world datasets demonstrate thatSofedachieves state-of-the-art performance with significantly reduced client response time and communication cost.

Model merging has become a popular approach for combining individual models into a single model that inherits their capabilities and achieves improved performance. However, its success has not yet been transferred to semantic segmentation tasks due to two major challenges: 1) current model merging methods predominantly employ static merging strategies with fixed coefficients, limiting their ability to incorporate task-specific prior knowledge and 2) semantic segmentation faces large distribution shifts across multiple domains, causing negative transfer in the merged model. In this article, we propose an effective model merging approach for semantic segmentation, named M2Seg. To dramatically integrate relevant priors based on the input data, we propose a novel SVD-structured MoE module for adaptive merging. To address the severe distribution shifts, we further introduce a test-time dynamic calibration function designed to minimize discrepancies between training and test statistics. Additionally, historical information is leveraged to refine activation statistics during inference. Recognizing that unreliable data can negatively impact update directions, we develop a pixel-efficient entropy minimization mechanism to filter unstable pixels, thus stabilizing the merging process and enhancing segmentation performance. Extensive experiments on both seen and unseen semantic segmentation tasks demonstrate the superior effectiveness and generalization capability of our proposed method. The source code and pretrained checkpoints are available athttps://github.com/cht619/MMSeg

With growing concerns over user privacy, federated recommendation (FedRec) has emerged as a mainstream solution for personalized recommendation services. FedRec trains user-private parameters on local clients while collaboratively updating global parameters on a centralized server. However, despite advances in optimizing these local and global parameters, existing methods overlook two key challenges: tradeoff training and distribution discrepancy . Tradeoff training balances timely local updates with diverse global parameters, limiting the model’s learning ability. Distribution discrepancy arises from the divergence between locally trained global parameters and those aggregated by the server, corrupting inference performance. To fill in the gap, we propose FedSC , a principled federated recommendation framework that boosts FedRec’s training and inference processes with minimal yet nontrivial efforts. During training, FedSC employs a stochastic aggregation strategy where all users participate in every round, while only a random subset is selected for aggregation, preserving the diversity of global parameters and ensuring timely local updates. During inference, FedSC makes recommendations with a consistency inference mechanism that uses the most recent locally trained global parameters of each user to improve the model’s understanding of user preferences. Extensive experiments on multiple benchmark datasets demonstrate the superiority of FedSC, achieving up to a 20% improvement in most evaluation scenarios.

Spatio-temporal video grounding (STVG) aims to precisely locate a spatio-temporal tube in an untrimmed video corresponding to a given language description. Many existing methods decouple spatial and temporal grounding as separate tasks, missing the strong interdependencies between the two, which are crucial for accurately aligning spatial regions (such as objects) with their motion over time. Thus, to enhance spatio-temporal associations, we introduce a new Prior-Driven Transformer Network (PDTNet) with predicted temporal boundaries as priors to guide object bounding boxes for improved spatial grounding over time. Firstly, PDTNet employs a temporal prior, termed reference query, to enhance discriminability between language-related and language-irrelevant visual content, improving temporal boundary localization. Further, the context within predicted temporal boundaries serves as another prior knowledge to modulate spatial features. We also introduce a prediction-aware Gaussian prior to precise object localization. This ensures consistent tube construction and accurate object localization. Extensive experiments on STVG benchmarks validate the effectiveness of PDTNet. Code is available at https://github.com/tongzhang111/PDTNet .

Traditional force-based graph layout models are rooted in virtual physics, while criteria-driven techniques position nodes by directly optimizing graph readability criteria. In this article, we systematically explore the integration of these two approaches, introducing criteria-driven force-based graph layout techniques. We propose a general framework that, based on user-specified readability criteria, such as minimizing edge crossings, automatically constructs a force-based model tailored to generate layouts for a given graph. Models derived from highly similar graphs can be reused to create initial layouts, users can further refine layouts by imposing different criteria on subgraphs. We perform quantitative comparisons between our layout methods and existing techniques across various graphs and present a case study on graph exploration. Our results indicate that our framework generates superior layouts compared to existing techniques and exhibits better generalization capabilities than deep learning-based methods.

Single-angle plane wave (SAPW) ultrasound imaging has gained significant attention in ultrafast and wearable ultrasound systems due to its high frame rate and hardware efficiency. However, the lack of transmit diversity leads to severe degradation in image quality, limiting its clinical utility. In contrast, Coherent Plane Wave Compounding (CPWC) improves spatial resolution and contrast by aggregating data from multiple transmission angles, but at the expense of a substantially reduced frame rate. To overcome this trade-off, we propose TF-Fusion, a novel Time-Frequency Domain Feature Fusion framework that enhances SAPW imaging by jointly exploiting both time- and frequency-domain features extracted from raw in-phase/quadrature (IQ) data. Specifically, our model utilizes a dual-branch encoder to learn compact and complementary representations from each domain, followed by a learnable fusion module that adaptively integrates the multi-domain information. This design facilitates effective noise and artifact suppression while preserving fine anatomical structures. We evaluate TF-Fusion on two public benchmarks—PICMUS and CUBDL—and demonstrate that our method significantly improves image resolution and contrast, achieving performance comparable to multi-angle CPWC methods. Notably, TF-Fusion maintains the high temporal resolution of SAPW, making it well-suited for real-time and resource-constrained ultrasound imaging scenarios.

Vision-Language Models (VLMs) have great potential for advancing echocardiography (Echo) probe navigation, which is crucial for assisting sonographers in standardized view acquisition. However, the high clinical deployment costs and spurious correlations pose major challenges for VLM-based probe navigation. To address these challenges, we propose Contrastive Language-Image Navigator for Latent Hyperbolic Geometric Knowledge Distillation (CLINav-GKD), a novel VLM-based 6-DOF Echo probe navigation framework. Specifically, Contrastive Language-Image Navigator (CLN) proposes a lightweight VLM-based 6-DOF navigator, reducing deployment costs while improving sensitivity to quality variations. Latent Hy perbolic Geometric Distiller (LGD) models the global geometric-topology between samples, mitigating spurious correlations and enhancing robustness. We train CLINav-GKD on real-world data with probe motion trajectories. Experimental results show that CLINav-GKD outperforms other VLM-based distillation methods by 2.8%, 3.8%, and 3.6% in probe navigation, achieving a superior balance of accuracy, robustness, and deployability for real-world clinical use. Code and data are available at https://github.com/DaisyLi0516/CLINav-GKD.

Homomorphic permutation is fundamental to privacy-preserving computations based on batch-encoding homomorphic encryption. It underpins nearly all homomorphic matrix operations and predominantly influences their complexity. Permutation decomposition as a potential approach to optimize this critical component remains underexplored. In this paper, we propose novel decomposition techniques to optimize homomorphic permutations, advancing homomorphic encryption-based privacy-preserving computations. We start by defining an ideal decomposition form for permutations and propose an algorithm searching for depth-1 ideal decompositions. Based on this, we prove the full-depth ideal decomposability of permutations used in specific homomorphic matrix transposition (HMT) and multiplication (HMM) algorithms, allowing them to achieve asymptotic improvement in speed and rotation key reduction. As a demonstration of applicability, substituting the HMM components in the best-known inference framework of encrypted neural networks with our enhanced version shows up to a 3.9× reduction in latency. We further devise a new method for computing arbitrary homomorphic permutations, specifically those with weak structures that cannot be ideally decomposed. We design a network structure that deviates from the conventional scope of decomposition and outperforms the state-of-the-art technique under a limited rotation key budget, achieving a speed-up of up to 1.69 ×.

Contrastive Language-Image Pre-training (CLIP) has emerged as an effective framework for multi-modal representation learning, achieving notable success in diverse tasks such as medical image analysis. CLIP's growing prominence in medical image applications is restricted by its significant computational demands, creating implementation challenges in resource-constrained clinical environments. While knowledge distillation offers an effective approach for model compression with preserved accuracy, existing methods suffer from two fundamental limitations. Firstly, existing methods focus on learning better information from single models while ignoring the fact that student models can generalize well under the guidance of multiple teachers. Secondly, they overlook the complementary information in the CLIP model where the text encoder and image encoder can be leveraged as heterogeneous information to teach one single modality. To tackle these challenges, we propose an Adaptive Heterogeneous Multi-teacher Knowledge Distillation (AdaHet-MKD) framework for effective knowledge transfer across heterogeneous text-image models and among multiple teacher models. The key innovations include: (i) adaptively determining the contribution of each teacher model to specific instances, thereby generating integrated soft logits, and (ii) enabling the student model to operate independently of the teacher model's architecture, which enhances flexibility in teacher-student pairings. Experimental evaluations on publicly available medical datasets demonstrate that our approach has achieved the state-of-the-art performance compared to baselines.

Querying desired data from the key-value store on a cloud server is a prevalent scenario. Client queries might include sensitive information that the client prefers to keep confidential from the server. This occasion resembles the Keyword Private Information Retrieval (KPIR). Prior works on keyword PIR consider that there are no duplicated key-value pairs in the store, i.e., each key only occurs once with only a single value attached. This is one of the cases in practical applications. However, there is also a typical case where a key may occur multiple times with different values. Straightly applying the existing keyword PIR to this case doesn't work and may finally obtain a false query result. We are the first to extend the setting that keys in the store may appear with different values multiple times. To solve this problem, we propose FEDPIR, a fast single-server keyword PIR protocol that supports querying a large-scale key-value store with multiple values per key. FEDPIR uses a novel encoding and decoding strategy combined with a high-throughput linear homomorphic encryption to improve performance significantly. Our extensive experiments on different store configurations show that our FEDPIR achieves 1.2-65.6x lower query latency and 1.5-37.9x lower cost monetarily compared with the baseline methods.

Due to the distributed nature of federated learning (FL), the vulnerability of the global model and the need for coordination among many client devices pose significant challenges. As a promising decentralized, scalable and secure solution, blockchain-based FL methods have attracted widespread attention in recent years. However, traditional consensus mechanisms designed for Proof of Work (PoW) similar to blockchain incur substantial resource consumption and compromise the efficiency of FL, particularly when participating devices are wireless and resource-limited. To address asynchronous client participation and data heterogeneity in FL, while limiting the additional resource overhead introduced by blockchain, we propose the Directed Acyclic Graph-based Asynchronous Federated Learning (DAG-AFL) framework. We develop a tip selection algorithm that considers temporal freshness, node reachability and model accuracy, with a DAG-based trusted verification strategy. Extensive experiments on 3 benchmarking datasets against eight state- of-the-art approaches demonstrate thatDAG-AFL significantly improves training efficiency and model accuracy by 22.7% and 6.5% on average, respectively.

Federated Semi-Supervised Learning (FSSL) integrates Semi-Supervised Learning (SSL) with the federated framework, enabling clients to collaboratively train a global model using their local labeled and unlabeled data while preserving data privacy. Existing methods (e.g., FedMatch, FedSSL) rely on a central server to aggregate model parameters and utilize a centralized proxy dataset to guide the training process. However, these approaches face privacy risks, cause negative transfer due to data heterogeneity, and violate the lightweight design principle of federated learning. This paper proposes a decentralized framework, FedDSSL, which employs a dynamic topology structure to adaptively adjust the connection weights among clients, thereby enhancing collaborative efficiency. FedDSSL adopts a topology graph, where connection weights between clients are adaptively adjusted based on data similarity, enabling more efficient collaborative training. To replace the centralized proxy dataset, FedDSSL utilizes local self-supervised pre-training and crossclient knowledge distillation for regularization alignment. Additionally, FedDSSL introduces a distributed optimization strategy, employing multi-client collaborative validation and dynamic consistency regularization to improve the quality of pseudo-labels and model robustness. Experimental results demonstrate that FedDSSL outperforms mainstream methods in both IID and non-IID scenarios. It provides an efficient and lightweight solution for privacy-sensitive fields such as healthcare, significantly enhancing model robustness and generalization ability.

As the social environment is growing more complex and collaboration is deepening, factors affecting the healthy development of service ecosystem are constantly changing and diverse, making its governance a crucial research issue. Applying the scenario analysis method and conducting scenario rehearsals by constructing an experimental system before managers make decisions, losses caused by wrong decisions can be largely avoided. However, it relies on predefined rules to construct scenarios and faces challenges such as limited information, a large number of influencing factors, and the difficulty of measuring social elements. These challenges limit the quality and efficiency of generating social and uncertain scenarios for the service ecosystem. Therefore, we propose a scenario generator design method, which adaptively coordinates three Large Language Model (LLM) empowered agents that autonomously optimize experimental schemes to construct an experimental system and generate high quality scenarios. Specifically, the Environment Agent (EA) generates social environment including extremes, the Social Agent (SA) generates social collaboration structure, and the Planner Agent (PA) couples task-role relationships and plans task solutions. These agents work in coordination, with the PA adjusting the experimental scheme in real time by perceiving the states of each agent and these generating scenarios. Experiments on the ProgrammableWeb dataset illustrate our method generates more accurate scenarios more efficiently, and innovatively provides an effective way for service ecosystem governance related experimental system construction.

Recent research in cooperative Multi-Agent Reinforcement Learning (MARL) has shown significant interest in utilizing Graph Neural Networks (GNNs) for communication learning due to their strong ability to process feature and topological information of agents into message representations for downstream action selection and coordination. However, GNNs generally assume network homogeneity that nodes of the same class tend to be interconnected. In real-world multi-agent systems, such assumptions are often unrealistic, as agents within the same class can be distant from each other. Furthermore, GNN-based MARL methods overlook the crucial role of feature similarity of agents in action coordination, which also restricts their performance. To overcome these limitations, we propose a Multi-Agent communication mechanism with Information preserving graph contrastive Learning (MAIL), which enhances message representation by preserving the comprehensive features of adjacent agents while integrating topological information. Specifically, MAIL considers three distinct graph views: original view, agent feature view, and global topological view. MAIL performs contrastive learning across three views to extract comprehensive information. MAIL effectively learns robust and expressive message representations for downstream tasks. Extensive experiments across various environments demonstrate that MAIL outperforms existing GNN-based MARL methods.

Telecommunication fraud refers to deceptive activities in the field of communication services. This research focuses on a category of fraud identified as ''mutation telecommunication fraud". There is currently a lack of research on mutation telecommunication fraud detection, allowing this type of fraud to persist uncaught. We identify that detecting mutation fraud requires capturing multi-source patterns, including user communication graphs and temporal-spatial Voice of Call (VOC) features. Specifically, we introduce MutationGuard, which leverages Graph Neural Networks (GNN) to capture changes in user communication graphs. For VOC records, we map call start times onto a 3D cylindrical surface, thereby representing each VOC record in spatial coordinates and utilizing proposed LFFE and TCFE modules to capture local fraud behaviors and temporal behavior changes. The proposed neural modeling approach that facilitates multi-source information fusion constitutes a significant advancement in detecting mutation fraud. Experiment results reveal a significant improvement in the AUC score by 1.52% and the F1 score by 1.36% on the proposed telecommunication fraud dataset. Particularly, our method shows a significant improvement of 13.93% in accuracy on mutation fraud data. We also validate the effectiveness of our method on the publicly available Sichuan Telecommunication Fraud dataset.

Cross-modal alignment is an important multi-modal task, aiming to bridge the semantic gap between different modalities. The most reliable fundamention for achieving this objective lies in the semantic consistency between matched pairs. Conventional methods implicitly assume embeddings contain solely semantic information, ignoring the impact of non-semantic information during alignment, which inevitably leads to information bias or even loss. These non-semantic information primarily manifest as stylistic variations in the data, which we formally define as style information. An intuitive approach is to separate style from semantics, aligning only the semantic information. However, most existing methods distinguish them based on feature columns, which cannot represent the complex coupling relationship between semantic and style information. In this paper, we propose PICO, a novel framework for suppressing style interference during embedding interaction. Specifically, we quantify the probability of each feature column representing semantic information, and regard it as the weight during the embedding interaction. To ensure the reliability of the semantic probability, we propose a prototype iterative construction method. The key operation of this method is a performance feedback-based weighting function, and we have theoretically proven that the function can assign higher weight to prototypes that bring higher performance improvements. Extensive experiments on various benchmarks and model backbones demonstrate the superiority of PICO, outperforming state-of-the-art methods by 5.2%-14.1%.

Unified Anomaly Detection (UAD) aims to identify anomalies across diverse domains without access to target domain data during training. Unlike traditional anomaly detection methods that rely on training separate models for each domain, UAD employs a single model to generalize across multiple categories. A key challenge lies in the domain shift between seen and unseen data, which requires capturing invariant discriminative patterns between reference and query images across different domains during in-context learning for unified anomaly detection. To tackle this, we propose a novel UAD framework to learn the invariant discriminative patterns through pre-, in- and post-processing modules. First, a pre-processing VLM-guided data augmentation module generates diverse and semantically consist images, followed by a latent-space filtering mechanism. Second, an in-processing Adaptive VQ memory module stores representative discriminative patterns to enable robust residual comparison. Third, a post-processing GUR (Geometric distributions Upgrade Representation) feature augmentation module models geometric feature distributions to synthesize informative prompts, improving the quality of feature delta estimation for anomaly scoring. Extensive experiments on benchmark datasets demonstrate that our method achieves superior generalization in detecting anomalies across unseen domains, outperforming existing state-of-the-art approaches.

Sequential recommender systems (SRSs) excel in capturing users' dynamic interests, thus playing a key role in various industrial applications. The popularity of SRSs has also driven emerging research on their security aspects, where data poisoning attack for targeted item promotion is a typical example. Existing attack mechanisms primarily focus on increasing the ranks of target items in the recommendation list by injecting carefully crafted interactions (i.e., poisoning sequences), which comes at the cost of demoting users' real preferences. Consequently, noticeable recommendation accuracy drops are observed, restricting the stealthiness of the attack. Additionally, the generated poisoning sequences are prone to substantial repetition of target items, which is a result of the unitary objective of boosting their overall exposure and lack of effective diversity regularizations. Such homogeneity not only compromises the authenticity of these sequences, but also limits the attack effectiveness, as it ignores the opportunity to establish sequential dependencies between the target and many more items in the SRS. To address the issues outlined, we propose a Diversity-aware Dual-promotion Sequential Poisoning attack method named DDSP for SRSs. Specifically, by theoretically revealing the conflict between recommendation and existing attack objectives, we design a revamped attack objective that promotes the target item while maintaining the relevance of preferred items in a user's ranking list. We further develop a diversity-aware, auto-regressive poisoning sequence generator, where a re-ranking method is in place to sequentially pick the optimal items by integrating diversity constraints. By attacking two representative SRSs on three real-world datasets, comprehensive experimental results demonstrate that DDSP outperforms state-of-the-art attack methods in attack effectiveness. Moreover, DDSP achieves the strongest stealthiness with its lowest impact on recommendation accuracy.

The automated analysis of chest X-rays using deep learning technologies has emerged as a critical trend in healthcare, offering the potential to enhance diagnostic efficiency and reduce clinician workload. However, the prohibitive cost of annotation and privacy concerns restrict the expansion of chest X-ray datasets, hindering the development of chest X-ray analysis models. One solution is to introduce generative models that synthesize new samples to expand datasets. Recent advances in diffusion models have demonstrated impressive capabilities, yet prevalent diffusion-based data augmentation techniques typically depend on alterations in color and shape, which are not always appropriate for medical imaging tasks. Consequently, we propose a diffusion-based data augmentation method that generates noise incorporating only the essential information, derived from the region of interest and guided by textual prompts. This noise is then combined with noise that encapsulates global information through concatenation, resulting in a synthesized version of chest X-rays that satisfy the fine-grained characteristics of medical images. We fine-tune the diffusion model using a publicly available dataset and evaluate our method on typical chest X-ray classification tasks. The results show that our method outperforms common data augmentation methods on multiple tasks.

The rapid spread of rumors on social media has posed significant challenges to maintaining public trust and information integrity.Since an information cascade process is essentially a propagation tree, recent rumor detection models leverage graph neural networks to additionally capture information propagation patterns, thus outperforming text-only solutions.Given the variations in topics and social impact of the root node, different source information naturally has distinct outreach capabilities, resulting in different heights of propagation trees.This variation, however, impedes the data-driven design of existing graph-based rumor detectors.Given a shallow propagation tree with limited interactions, it is unlikely for graph-based approaches to capture sufficient cascading patterns, questioning their ability to handle less popular news or early detection needs.In contrast, a deep propagation tree is prone to noisy user responses, and this can in turn obfuscate the predictions.In this paper, we propose a novel Epidemiology-informed Network (EIN) that integrates epidemiological knowledge to enhance performance by overcoming data-driven methods' sensitivity to data quality.Meanwhile, to adapt epidemiology theory to rumor detection, it is expected that each user's stance toward the source information will be annotated.To bypass the costly and time-consuming human labeling process, we take advantage of large language models to generate stance labels, facilitating optimization objectives for learning epidemiology-informed representations.Our experimental results demonstrate that the proposed EIN not only outperforms state-of-the-art methods on real-world datasets but also exhibits enhanced robustness across varying tree depths.We release the code at https://github.com/WeiJiang01/EIN.

User prediction aims to identify the user who show potential value in e-commerce platforms. Existing user prediction algorithms primarily focus on distinguishing between potential user, those likely to purchase a specific product in the future, and non-potential user, those unlikely to do so. However, these algorithms often overlook a valuable group named conditional potential user in non-potential group. Conditional potential user, initially categorized as non-potential, can convert into potential user under specific converted condition (e.g., product trial, coupon receipt, or certification attainment). Additionally, conventional user prediction models do not offer insights into the associated converted condition and provide classification results only. Furthermore, the lack of explainability in user prediction methods limits their practical utility. To tackle these challenges, this paper proposes a definitive concept for conditional potential users and introduces an innovative user prediction framework, the Conditional Potential User Mining (CPUM). Addressing the challenge of predicting conditional potential users, CPUM employs a Gold Standard Classifier to ascertain users’ intentions, thereby identifying their interest in target products under converted conditions and enabling the prediction of conditional potential users. Moreover, CPUM adopts an explainable surrogate model with an attention mechanism to boost explainability. This model is designed to mirror the decision-making capacity of the Gold Standard Classifier and provides importance explanations for different user interactions. This enables precise identification of converted conditions in conditional potential users, thus enhancing explainability. The effectiveness of this method is substantiated by experimental results derived from extensive e-commerce datasets from Alibaba and Amazon, demonstrating its cutting-edge performance and applicability. • Introduces the concept of conditional potential users in e-commerce. • Launches CPUM framework for accurate prediction of conditional potential users. • Enhances model explainability with a surrogate model and attention mechanism. • Validates CPUM’s effectiveness with Amazon and Alibaba datasets. • Offers a scalable user prediction model adaptable to various e-commerce platforms.

Incorporating unmanned aerial vehicles (UAVs) and distributed sensors into aerial-terrestrial networks (ATNs) improves the ability to monitor remote and challenging environments. However, in such harsh environments, the UAV must return to the base station multiple times to be recharged to ensure that all sensors can be accessed. Neglecting the energy consumption associated with the backhaul recharging path would lead to a decrease in task efficiency and an increase in overall energy consumption. To address the challenge, this article formulates a UAV back-haul trajectory planning (UBTP) problem, aiming to optimize both the data collection and charging paths for UAVs. At the same time, a two-stage deep reinforcement learning (DRL)-based method is developed to address the UBTP problem. The first stage of the proposed method determines the navigation sequence taking into account the energy consumption of the data collection and charging path. The subsequent stage refines the trajectory by considering the sensing ranges of the sensors. The numerical results demonstrate that the proposed approach provides solutions that are more energy-efficient compared to benchmark methods, thereby enhancing the UAV’s ability to harvest data sustainably and effectively from distributed sensors in challenging environments.

Federated learning (FL) is a rapidly evolving paradigm that facilitates distributed training of large-scale deep neural networks (DNNs). However, the distributed nature exposes the system to threats from potentially malicious or low-quality participants, which can significantly degrade the overall performance of FL. Existing contribution evaluation approaches in previous FL studies are vulnerable when there exist complicated types of malicious or low-quality clients. In this article, we propose to assess the clients’ contributions by treating their model parameters as data. By extracting information from the statistical properties of model parameters using principal component analysis-based data mining techniques, we quantitatively estimate the similarity and diversity between different clients. Furthermore, we analyze the convergence of our proposed method and establish a convergence rate of$\mathcal {O}({1}/{T})$with commonly accepted assumptions. Extensive experiments are conducted on public datasets to evaluate the effectiveness of our proposed method against typical malicious or low-quality clients: sybil-based backdoor attackers and clients with redundant data. Experimental results demonstrate the superiority of our approach in excluding malicious or low-quality clients and thereby enhancing the model performance in FL.

Federated Learning (FL) is a new learning framework in which$s$clients collaboratively train a model under the guidance of a central server. Meanwhile, with the advent of the era of large models, the parameters of models are facing explosive growth. Therefore, it is important to design federated learning algorithms for edge environment. However, the edge environment is severely limited in computing, storage, and network bandwidth resources. Concurrently, adaptive gradient methods show better performance than constant learning rate in non-distributed settings. In this paper, we propose a pruning-based distributed Adam (PD-Adam) algorithm, which combines model pruning and adaptive learning steps to achieve asymptotically optimal convergence rate of$O(1/\sqrt[4]{K})$. At the same time, the algorithm can achieve convergence consistent with the centralized model. Finally, extensive experiments have confirmed the convergence of our algorithm, demonstrating its reliability and effectiveness across various scenarios. Specially, our proposed algorithm is$2$% and$18$% more accurate than the current state-of-the-art FedAvg algorithm on the ResNet and CIFAR datasets.

Federated domain adaptation (FDA) aims to transfer knowledge collaboratively from multiple source domains to related but different unlabelled target domains. The data of each domain are locally maintained, and various domain gaps exist among them, resulting in extreme challenges in simultaneously mitigating diverse distribution shifts and preserving discriminative knowledge without accessing the source data. Many existing works have failed to fully explore different source models to measure domain shifts and leverage semantic knowledge, resulting in skewed alignment and partial preservation of discriminative information. In this paper, we propose a novel approach named FDAC to addressFederatedDomainAdaptation by thoroughly investigating source models via dualContrastive mechanisms. FDAC contrastively increases the data diversity to align features across domains in a fine-grained manner by manipulating the latent deep architecture and compensating for knowledge from each source domain; simultaneously, it contrastively utilizes the comprehensive semantic knowledge of different source domains to guide the adaptation process. Extensive experiments on several real datasets demonstrate that FDAC outperforms all comparative methods under most conditions. Furthermore, FDAC only needs approximately half of the communication rounds compared with the state-of-the-art methods, indicating that FDAC can significantly improve communication efficiency, which is another key factor in the federated setting. The source code is publicly available athttps://github.com/ycarobot/FDAC.

Federated Learning is a data privacy-protected distributed machine learning framework, but malicious clients can damage it. Byzantine-robust federated learning aims to learn an accurate global model despite the presence of malicious clients. Most current defenses assume that clients have identically and independently distributed (i.i.d.) data and thus cannot perform well in canonical non-i.i.d. scenarios. Several non-i.i.d. statistic-based defenses have been recently proposed to identify malicious clients through gradient statistics without any auxiliary techniques. They thus can only ensure robustness under certain attacks with specific characteristics. We propose Sophon, a comprehensive defense using auxiliary data to combat an arbitrary number of malicious clients in both i.i.d. and non-i.i.d. cases. Specifically, Sophon first normalizes received client gradients to reduce the dominance of malicious gradients. Then it introduces a dual trust mechanism to assign the aggregation weight for each gradient. The dual trust mechanism estimates the consistency-based and diversity-based trust scores of client gradients and integrates the two scores as the aggregation weight to effectively suppress the impact of malicious gradients. Extensive experimental results on three datasets from different domains, with diverse models and FL scenarios, show that Sophon is robust in maintaining the overall accuracy of the training model.

The proliferation of healthcare data sources, including diverse imaging modalities and biochemical measurements, has created unprecedented opportunities for comprehensive disease prediction. Multi-modal clinical data, encompassing medical imaging reports, biochemical assays, and longitudinal clinical records, provides a rich foundation for developing sophisticated diagnostic models. Graph Neural Networks (GNNs) have emerged as a leading methodological framework, distinguished by their capacity to model complex inter-patient relationships and capture community structures within patient data. Despite their promise, current GNN-based approaches exhibit limitations in handling noisy, low-quality data and often impose overly restrictive graph smoothness constraints. These limitations can obscure patient-specific variations and compromise model robustness. To overcome these challenges, we propose HierSSL (Hierarchical Self-Supervised Learning), a novel multi-modal disease prediction framework that enhances representational learning through dual-scale self-supervision mechanisms operating at both local and global levels. HierSSL's architecture specifically addresses two critical aspects: 1) the capture of local inter-modality dependencies and global community patterns, and 2) the optimization of multi-modal feature integration through an innovative combination of feature consistency constraints and graph contrastive learning. Empirical evaluation across two distinct disease prediction datasets demonstrates that HierSSL achieves statistically significant performance improvements compared to state-of-the-art methods, highlighting its efficacy in robust multi-modal data integration for disease prediction tasks.

Network motifs provide a deep insight into the network functional abilities, and have proven useful in various practical applications. Existing studies reveal that different definitions of motifs may be needed for different temporal networks. In this study, we focus on a class of temporal networks such that the nodes and edges keep fixed, but the edge labels vary regularly with timestamps. First, we propose a proper definition of temporal motifs, which appear continuously within sufficiently large time intervals, to properly reinterpret the recurrent and statistically significant nature of motifs in temporal networks. Second, we develop a low polynomial time solution to find temporal motifs for all possible time intervals with the top to bottom and right to left scheme, based on the analyses of the properties for temporal motifs. Third, we develop a theoretically faster incremental solution to efficiently find temporal motifs to support continuously updates of temporal networks, by identifying unaffected time intervals and unnecessary edges. Finally, we have conducted extensive experiments to verify the efficiency and usefulness of our static and incremental solutions.

Graph Neural Networks (GNNs) hold promise in various application domains, but their limited explainability hinders widespread adoption, impacting customer satisfaction and loyalty. This issue intensifies when addressing diverse explanation needs of different user groups. Current GNN explanation models focus on a single objective, neglecting varied and potential conflicting user requirements, resulting in suboptimal outcomes. Moreover, existing models prioritize explanation objectives during multi-objective explanations, disrupting the intrinsic hierarchical structures and distant relationships within the graphs, further diminishing their effectiveness. To tackle these challenges, this paper introduces a novel multi-objective explanatory framework with hierarchical structure attribution for GNNs, termed HM-Explainer. This framework constructs a multi-objective explanation generation module based on Pareto theory to balance different and potentially conflicting explanatory objectives. Additionally, to embed hierarchical information into explanations, HM-Explainer designs node-level and cluster-level attribution modules to analyze the impact of input data on GNN decisions hierarchically. Furthermore, a self-attention mechanism is integrated into the node-level attribution module to account for the influence of distant neighbors. Ultimately, the efficacy of HM-Explainer is validated across multiple datasets for different GNN models through experimentation.

With the convenient design and prolific functionalities, wireless earbuds are fast penetrating in our daily life and taking over the place of traditional wired earphones. The sensing capabilities of wireless earbuds have attracted great interests of researchers on exploring them as a new interface for human-computer interactions. However, due to its extremely compact size, the interaction on the body of the earbuds is limited and not convenient. In this paper, we proposeUi-Ear, a new on-face gesture recognition system to enrich interaction maneuvers for wireless earbuds.Ui-Earexploits the sensing capability of Inertial Measurement Units (IMUs) to extend the interaction to the skin of the face near ears. The accelerometer and gyroscope in IMUs perceive dynamic vibration signals induced by on-face touching and moving, which brings rich maneuverability. Since IMUs are provided on most of the budget and high-end wireless earbuds, we believe thatUi-Earhas great potential to be adopted pervasively. To demonstrate the feasibility of the system, we define seven different on-face gestures and design an end-to-end learning approach based on Convolutional Neural Networks (CNNs) for classifying different gestures. To further improve the generalization capability of the system, adversarial learning mechanism is incorporated in the offline training process to suppress the user-specific features while enhancing gesture-related features. We recruit 20 participants and collect a realworld datasets in a common office environment to evaluate the recognition accuracy. The extensive evaluations show that the average recognition accuracy ofUi-Earis over 95% and 82.3% in the user-dependent and user-independent tasks, respectively. Moreover, we also show that the pre-trained model (learned from user-independent task) can be fine-tuned with only few training samples of the target user to achieve relatively high recognition accuracy (up to 95%). At last, we implement the personalization and recognition components ofUi-Earon an off-the-shelf Android smartphone to evaluate its system overhead. The results demonstrateUi-Earcan achieve real-time response while only brings trivial energy consumption on smartphones.

Federated learning aims to facilitate collaborative training among multiple clients with data heterogeneity in a privacy-preserving manner, which either generates the generalized model or develops personalized models. However, existing methods typically struggle to balance both directions, as optimizing one often leads to failure in another. To address the problem, this article presents a method named personalized federated learning via cross silo prototypical calibration (pFedCSPC) to enhance the consistency of knowledge of clients by calibrating features from heterogeneous spaces, which contributes to enhancing the collaboration effectiveness between clients. Specifically, pFedCSPC employs an adaptive aggregation method to offer personalized initial models to each client, enabling rapid adaptation to personalized tasks. Subsequently, pFedCSPC learns class representation patterns on clients by clustering, averages the representations within each cluster to form local prototypes, and aggregates them on the server to generate global prototypes. Meanwhile, pFedCSPC leverages global prototypes as knowledge to guide the learning of local representation, which is beneficial for mitigating the data imbalanced problem and preventing overfitting. Moreover, pFedCSPC has designed a cross-silo prototypical calibration (CSPC) module, which utilizes contrastive learning techniques to map heterogeneous features from different sources into a unified space. This can enhance the generalization ability of the global model. Experiments were conducted on four datasets in terms of performance comparison, ablation study, in-depth analysis, and case study, and the results verified that pFedCSPC achieves improvements in both global generalization and local personalization performance via calibrating cross-source features and strengthening collaboration effectiveness, respectively.

Federated learning has recently been applied to recommendation systems to protect user privacy. In federated learning settings, recommendation systems can train recommendation models by collecting the intermediate parameters instead of the real user data, which greatly enhances user privacy. In addition, federated recommendation systems (FedRSs) can cooperate with other data platforms to improve recommendation performance while meeting the regulation and privacy constraints. However, FedRSs face many new challenges such as privacy, security, heterogeneity, and communication costs. While significant research has been conducted in these areas, gaps in the surveying literature still exist. In this article, we: 1) summarize some common privacy mechanisms used in FedRSs and discuss the advantages and limitations of each mechanism; 2) review several novel attacks and defenses against security; 3) summarize some approaches to address heterogeneity and communication costs problems; 4) introduce some realistic applications and public benchmark datasets for FedRSs; and 5) present some prospective research directions in the future. This article can guide researchers and practitioners understand the research progress in these areas.

Context-aware emotion recognition (CAER) leverages comprehensive scene information, including facial expressions, body postures, and contextual background. However, current studies predominantly rely on facial expressions, body postures, and global contextual features; the interaction between the agents (target individuals) and other objects in the scene is usually absent or incomplete. In this article, a three-dimensional view relationship-based CAER (TDRCer) method is proposed, which comprises two branches: the personal emotional branch (PEB) and the contextual emotional branch (CEB). First, PEB is designed for the extraction of facial expression features and body posture features from the agent. A vision transformer (ViT), pretrained by contrastive learning with a novel loss function combining Euclidean distance and cosine similarity, is applied to enhance the robustness of facial expression features. Meanwhile, the human body contour images extracted by semantic segmentation are fed into another ViT to extract body posture features. Second, CEB is constructed for the extraction of global contextual features and interactive relationships among objects in the scene. The images masked by the agents' bodies are fed into a ViT to extract global contextual features. By leveraging both the gaze angle and depth map, a three-dimensional view graph (3DVG) is constructed to represent the interactive relationships between agents and objects in the scene. Then, a graph convolutional network is employed to extract interactive relationship features from the 3DVG. Finally, the multiplicative fusion strategy is applied to fuse the features of two branches, and the fused features are utilized to classify the emotions. TDRCer achieves an accuracy of 89.90% on the CAER-S dataset and a mean average precision (mAP) of 36.02% on the EMOTIons in context (EMOTIC) dataset. The code can be accessed at https://github.com/mengTender/TDRCer.

Since the creation of the Web, recommender systems (RSs) have been an indispensable personalization mechanism in information filtering. Most state-of-the-art RSs primarily depend on categorical features such as user and item IDs, and use embedding vectors to encode their information for accurate recommendations, resulting in an excessively large embedding table owing to the immense feature corpus. To prevent the heavily parameterized embedding table from harming RSs’ scalability, both academia and industry have seen increasing efforts compressing RS embeddings, and this trend is further amplified by the recent uptake in edge computing for online services. However, despite the prosperity of existing lightweight embedding-based RSs (LERSs), a strong diversity is seen in the evaluation protocols adopted across publications, resulting in obstacles when relating the reported performance of those LERSs to their real-world usability. On the other hand, among the two fundamental recommendation tasks, namely traditional collaborative filtering and content-based recommendation, despite their common goal of achieving lightweight embeddings, the outgoing LERSs are designed and evaluated with a straightforward “either-or” choice between the two tasks. Consequently, the lack of discussions on a method’s cross-task transferability will likely hinder the development of unified, more scalable solutions for production environments. Motivated by these unresolved issues, this study aims to systematically investigate existing LERSs’ performance, efficiency, and cross-task transferability via a thorough benchmarking process. To create a generic, task-independent baseline, we propose an efficient embedding compression approach based on magnitude pruning, which is proven to be an easy-to-deploy yet highly competitive baseline that outperforms various complex LERSs. Our study reveals the distinct performance of different LERSs across the two recommendation tasks, shedding light on their effectiveness and generalizability under different settings. Furthermore, to account for edge-based recommendation—an increasingly popular use case of LERSs, we have also deployed and tested all LERSs on a Raspberry Pi 4, where their efficiency bottleneck is exposed compared with GPU-based deployment. Finally, we conclude this article with critical summaries on the performance comparison, suggestions on model selection based on task objectives, and underexplored challenges around the applicability of existing LERSs for future research. To encourage and support future LERS research, we publish all source codes and data, checkpoints, and documentation at https://github.com/chenxing1999/recsys-benchmark .

Intravascular ultrasound (IVUS) not only reveals changes within the vascular lumen but also illustrates the cross-sectional structure, encompassing aspects such as plaques, vessel wall thickness, morphology, and composition. However, during the image acquisition process, ultrasound imaging of vessels can lead to intraluminal misalignment due to motion, resulting in inaccurate measurement outcomes. Current methods for motion artifact removal in IVUS face the following challenges: (a) Gating, which extracts key gating frames to form a new artifact-free sequence, but often results in the loss of substantial useful information; and (b) Direct artifact removal, which requires lumen segmentation followed by registration, where the accuracy of registration is highly dependent on segmentation accuracy. To address these challenges, this paper proposes a robust direct artifact removal method based on spatiotemporal representations. Specifically, to address the issue of information loss in gating methods, a spatiotemporal representation network is introduced, which primarily relies on temporal granularity normalization and spatial position compensation. To tackle the problem of direct artifact removal methods heavily relying on segmentation accuracy, this paper integrates the segmentation network with the artifact removal network, allowing for mutual supervision. This approach ensures effective motion artifact removal even when segmentation accuracy is not optimal. Experimental results show that our method not only achieves state-of-the-art (SOTA) performance in both quantitative and qualitative evaluations but also maintains robust motion artifact removal even when the segmentation network is replaced with one of lower performance.

Test-time medical image segmentation is a critical component in clinical practice, enabling pre-trained medical segmentation models to effectively adapt unseen medical samples with potential distribution shifts. However, existing methods are typically task-specific and restricted to certain diseases, with limited research focusing on test-time adaptation for universal segmentation, i.e. Segment Anything Model (SAM). Moreover, it is difficult to generate suitable prompts that can be effectively utilized by SAM for unseen test data without any label information. To address these challenges, we propose TTCS, a novel Test-Time medical image segmentation method using CLIP-guided SAM adaption, which achieves effective universal segmentation across diverse medical segmentation tasks. Specifically, we introduce a test-time prompt tuning strategy that leverages the semantic information from CLIP to generate precise prompts for each test data, effectively addressing the issue of poor prompt quality for SAM due to label scarcity. After generating the prompt for SAM, we implement an adaptive self-training strategy to further increase SAM’s robustness under distribution shifts. Our proposed method is inherently task-agnostic, and extensive experiments demonstrate the superior performance of our TTCS approach.

In the early development of many fundus diseases, changes in retinal layer thickness occur, and optical coherence tomography (OCT) serves as the gold standard for detecting variations in retinal layer thickness. Consequently, extensive research has been conducted on retinal layer segmentation (RLS) based on OCT images. However, current breakthroughs in RLS primarily focus on innovations in deep learning (DL) models and improvements in training strategies, which constrains the means to enhance the accuracy of RLS. We have discovered a new dimension of spectral information that can be utilized to improve the precision of RLS. Experimental results demonstrate that the accuracy of RLS, measured by the mIoU metric, can be maximized with an improvement of up to 1.57 percentage points, and that different combinations of spectral images vary in their effectiveness at enhancing segmentation outcomes. Our study will introduce novel research avenues in the domain of RLS based on DL.

Urban flow prediction is a spatio-temporal modelling task that estimates the throughput of transportation services like buses, taxis, and ride-sharing, where data-driven models have become the most popular solution in the past decade. Meanwhile, the implicitly learned mapping between historical observations to the prediction targets tend to over-simplify the dynamics of real-world urban flows, leading to suboptimal predictions. Some recent spatio-temporal prediction solutions bring remedies with the notion of physics-guided machine learning (PGML), which describes spatio-temporal data with nuanced and principled physics laws, thus enhancing both the prediction accuracy and interpretability. However, these spatio-temporal PGML methods are built upon a strong assumption that the observed data fully conforms to the differential equations that define the physical system, which can quickly become ill-posed in urban flow prediction tasks. The observed urban flow data, especially when sliced into time-dependent snapshots to facilitate predictions, is typically incomplete and sparse, and prone to inherent noise incurred in the collection process (e.g., uncalibrated traffic sensors). As a result, such physical inconsistency between the data and PGML model significantly limits the predictive power and robustness of the solution. Moreover, due to the interval-based predictions and intermittent nature of data filing (e.g., one record per 30 minutes) in many transportation services, the instantaneous dynamics of urban flows can hardly be captured, rendering differential equation-based continuous modelling a loose fit for this setting. To overcome the challenges, we develop a discretized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR) to enhance PN. Technically, P-GASR incorporates an active sample reweighting pipeline, which not only minimizes the model uncertainty of PN to enhance robustness, but also prioritizes data samples that exhibit higher physical compliance to reinforce their contribution to PN training. Experimental results in four real-world datasets demonstrate that our method achieves state-of-the-art performance with a demonstrable improvement in robustness. The code is released at https://github.com/WeiJiang01/P-GASR.

The drug recommendation task aims to predict safe and effective drug prescriptions based on the patients' historical electronic health records (EHRs). However, existing drug recommendation models generally have two limitations. First, they neglect the inherent characteristics of multiple views existing in patients' clinical data (e.g., diagnoses and procedures), leading to fragmented and inconsistent patient representations. Second, they do not fully exploit drug label information. Most models do not explicitly establish a mapping relationship between drug labels and patients' historical visits. To address these two problems, we proposed a label-aware multi-view drug recommendation model named LAMRec. In particular, LAMRec uses a cross-attention module to fuse information from the diagnosis and procedure views, and increases the mutual information of patient multi-view representations through multi-view contrastive loss; the label-wise attention mechanism fully explores drug label information by constructing an adaptive mapping of drug-visit to generate personalized representations that are aware of the drug-related visit information. Experiments on three real world medical datasets demonstrated the superiority of LAMRec, with a relative reduction of 5.25% in DDI compared to the optimal baseline, a relative improvement of 4.20% in Jaccard similarity scores, and a relative improvement of 3.10% in F1 scores. We released the code online at: https://github.com/Tyunsen/LAMRec.

Food recommendation systems play a pivotal role in shaping dietary salubrity and fostering sustainable lifestyles by recommending recipes and foodstuffs that align with user preferences. Metadata information of a recipe, encompassing multi-modal descriptions, constituent ingredients, and health-related attributes, can furnish a more holistic perspective on the recipe's profile, thereby augmenting recommendation performance. However, existing state-of-the-art methods often overlook the inherent interdependencies between modalities, ingredients, and health factors, leaving the health information pertaining to recipe characteristics underexploited. Notably, our preliminary investigation on two datasets unveiled that the semantic divergence between health-related knowledge and collaborative filtering signals is more pronounced in comparison to other metadata information, thereby potentially impeding the efficacy of food recommendation systems. To address these limitations, we propose HealthRec, a novel multi-modal food recommendation framework with health-aware knowledge distillation. HealthRec employs a global graph representation learning module to capture high-order dependencies across diverse food-related relations, enriching the representations. Subsequently, a co-attention network is leveraged to capture local, recipe-level knowledge transfer between modality-related and ingredient-related embeddings. Additionally, we exploit external supervision signals derived from WHO recommendations, utilizing knowledge distillation during the training phase to transfer local health-aware knowledge into global collaborative embeddings. Extensive experimentation on real-world datasets demonstrates HealthRec's superiority compared to current state-of-the-art recommendation baselines, highlighting its effectiveness in modeling health-aware food recommendations.

Academic qualifications and degrees are important manifestations of students' acceptance of higher education and important proof of social recognition. However, the existing certification system for academic qualifications and degrees has problems such as complex processes, centralization, and difficulty in tracing, leading to serious fraud and difficulty in meeting the comprehensive talent evaluation and data verification needs of employers. The article proposes privacy protection and data verification methods based on asymmetric encryption technology to protect the entire process of education authentication; At the same time, a smart contract upgrade method was proposed to support iterative development; And adopt an on chain and off chain collaborative storage solution to improve the operational efficiency of the blockchain system. Based on the existing problems in academic degree certification and combined with the above methods, a complete system for academic degree certification has been constructed. After testing, all functions of the system are good and meet the expected results.

This research proposed a model called rational intelligence and studied its reasoning capability as compared to ChatGPT-4o in counterfactual reasoning tasks. Unlike traditional AI models that rely heavily on data-driven approaches, rational intelligence allows for reasoning over abstract principles and hypothetical scenarios, similar to human cognitive processes. The proposed Rational Intelligence Model (RIM) applies Large Language Models (LLMs) to enable human-like comprehension, knowledge application, and problem-solving capabilities. In complex counterfactual reasoning tasks with scenarios proven to be challenging to human adults, we demonstrate that RIM achieves a clearly higher accuracy rate (76%) compared to ChatGPT-4o (68%), showing its enhanced reasoning capabilities. Additionally, RIM incorporates a self-reflection mechanism to manage knowledge conflicts and gaps, which can further improve its performance and adaptability.

Owing to the nature of privacy protection, feder-ated recommender systems (FedRecs) have garnered increasing interest in the realm of on-device recommender systems. However, most existing FedRecs only allow participating clients to collaboratively train a recommendation model of the same public parameter size. Training a model of the same size for all clients can lead to suboptimal performance since clients possess varying resources. For example, clients with limited training data may prefer to train a smaller recommendation model to avoid excessive data consumption, while clients with sufficient data would benefit from a larger model to achieve higher recommendation accuracy. To address the above challenge, this paper introduces HeteFedRec, a novel FedRec framework that enables the assignment of personalized model sizes to partici-pants. Specifically, we present a heterogeneous recommendation model aggregation strategy, including a unified dual-task learning mechanism and a dimensional decorrelation regularization, to allow knowledge aggregation among recommender models of different sizes. Additionally, a relation-based ensemble knowledge distillation method is proposed to effectively distil knowledge from heterogeneous item embeddings. Extensive experiments conducted on three real-world recommendation datasets demonstrate the effectiveness and efficiency of HeteFedRec in training federated recommender systems under heterogeneous settings.

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM’s adversarial robustness. This paper proposes an efficient tool to audit the LLM’s adversarial robustness via a prompt-based adversarial attack (PromptAttack). PromptAttack converts adversarial textual attacks into an attack prompt that can cause the victim LLM to output the adversarial sample to fool itself. The attack prompt is composed of three important components: (1) original input (OI) including the original sample and its ground-truth label, (2) attack objective (AO) illustrating a task description of generating a new sample that can fool itself without changing the semantic meaning, and (3) attack guidance (AG) containing the perturbation instructions to guide the LLM on how to complete the task by perturbing the original sample at character, word, and sentence levels, respectively. Besides, we use a fidelity filter to ensure that PromptAttack maintains the original semantic meanings of the adversarial examples. Further, we enhance the attack power of PromptAttack by ensembling adversarial examples at different perturbation levels. Comprehensive empirical results using Llama2 and GPT-3.5 validate that PromptAttack consistently yields a much higher attack success rate compared to AdvGLUE and AdvGLUE++. Interesting findings include that a simple emoji can easily mislead GPT-3.5 to make wrong predictions. Our source code is available at https://github.com/GodXuxilie/PromptAttack.

Recent years have witnessed a growing interest in Federated Knowledge Graph Embedding, driven by its potential to leverage knowledge from various data owners to improve link prediction performance without the need for data sharing. Existing works typically assume that the central Federated Learning (FL) server owns a table containing unique entities/relations for all FL clients. In addition, all clients are assumed to use the same knowledge graph embedding method. However, these methods are vulnerable to privacy leakage and do not fully explore the different contributions of local entity embeddings. To bridge this gap, we propose a randomized embedding method selection approach for privacy-preserving federated knowledge graph embedding (FedRMS). It selects a knowledge graph embedding method for each client during the local training process with randomness and employs an attention-based aggregator to derive the global entity embedding on the FL server. Extensive experiments on three real-world public datasets demonstrate that FedRMS achieves significant improvements in terms of both privacy preservation and link prediction against 5 state-of-the-art methods.

Graph Neural Networks (GNNs) have significantly advanced recommendation systems by capturing complex interplays between user-item relationships and dependencies. However, inherent noise in user behaviors, manifesting as random clicks and diverse browsing patterns, disrupts the structural integrity of graphs, thereby degrading the accuracy and reliability of GNN-based recommendation systems. Traditional graph pruning methods, which remove or reweight connections, often fail to adequately address this noise because they neglect the deeper causal factors influencing user choices, resulting in biased outcomes. To confront these challenges, this paper presents the GNN-based Causal Denoising Framework (GCDF). GCDF employs causal relationships to filter out noisy connections, thus enhancing the performance of GNNs. By utilizing a denoised graph that more accurately reflects the causal interactions among items, GCDF significantly improves the accuracy and reliability of recommendations, as evidenced by comprehensive empirical evaluations.

The rapid advancement and extensive implementation of Large Language Models (LLMs) are milestones in the realm of artificial intelligence. Although Parameter-Efficient Transfer Learning (PETL), a.k.a. Adapter, methods have reduced the barrier for fine-tuning and inference on LLMs, it becomes a challenge to efficiently deploy and fine-tuning different adapter models needed for massive AI applications. With the popularity of SoC chips, the computing power of edge devices has improved significantly. To meet the computational resources required by LLM applications and improve quality of service (QoS), we propose Edge-LLM, a server-node collaboration framework for large-scale language model serving, to efficiently utilize edge resources to accelerate LLM fine-tuning and inference in resource-constrained scenarios. In the framework, we implement an adaptive quantization strategy, FM cache mechanism, and value density first (VDF) scheduling algorithm to reduce GPU overhead and accelerate LLM computation. The experimental results demonstrate that Edge-LLM can significantly improve overall computational speed by a factor of 17, decrease the number of tasks experiencing timeouts by 63%, and reduce GPU overhead by up to 43%.

Crowdsourcing has been widely adopted in various domains for problem-solving, idea generation and data collection, leveraging distributed networks for efficient outcomes. Crowdsourcing platforms harness workers’ collective productivity by assigning tasks to a diverse pool of workers. However, all these tasks are assigned to registered high-quality workers on the platform, which is prone to task congestion. Moreover, the mechanical scheduling of workers ignores workers’ productivity fluctuations, and fails to make full use of the productivity of high-quality workers who are not currently online. In order to solve these problems, we design a Self-organizing Collaborative Crowdsourcing Framework (SoCCF) to support worker collaboration. Specifically, we propose a two-stage strategy, including a Reputation-driven Collaborative Partner Selection (RCPS) algorithm to expand the pool of collaborative workers and a Lyapunov optimization-based Task Acceptance and Sub-Delegation (LTASD) algorithm to guide worker to make workload decisions that meet emotional needs. Extensive experiments based on simulated crowdsourcing scenarios demonstrate that SoCCF consistently achieves higher overall service utility, while ensuring that workers can achieve 90.2% of the benefits of traditional algorithms with only 82.5% effort on average.

More and more business applications are crossing organization boundaries and typically involves a set of interactive organizations, known as cross-organization business process management. By taking as input the distributed event logs of each organization, cross-organization process mining techniques can reconstruct the underlying business process model to help process comprehension and improvements. Unfortunately, existing process mining techniques completely ignore the privacy issue, i.e., the privacy of the event log and business process model is not guaranteed. To cope with this challenge, this paper proposes a privacy-preserving cross-organizational business process mining framework based on blockchain and cryptography. Specifically, it mainly includes three steps: (1) each organization builds its private business process model, interaction messages, and collaborative tasks from its event log; (2) collaborative public process model for each organization is generated based on blockchain using privacy security intersection (PSI) cryptography algorithms to ensure the privacy of each organization; and (3) each organization combines its private business process model with relevant public process models, to obtain an organization-specific collaborative business process model. Using four public cross-organization datasets, the privacy-preserving ability and application of the proposed technique is demonstrated.

As AI applications are widely deployed in various fields, the computing cost of AI is skyrocketing. The high cost not only puts pressure on the environment but also poses challenges for researchers entering the field of deep learning. Green AI is gradually gaining attention, aiming to reduce computing costs and make AI application deployment more efficient and environmentally friendly. However, due to the wide variety of deep learning models, there are many challenges in efficiently deploying multiple models on GPUs. An unreasonable model deployment strategy will lead to insufficient utilization of GPU computing resources. We address some of these challenges through AutoMP, a tool that automates performance testing for model placement on GPUs. Through AutoMP, researchers can flexibly initiate a large number of experiments to study which models are suitable for inference tasks on the same GPU, thereby making GPU utilization more efficient. AutoMP provides a user-friendly visual interface and an API to meet users’ needs in different scenarios. AutoMP also provides a complete experimental analysis tool that generates visual charts of experimental data from multiple dimensions and gives experimental conclusions to assist researchers in making decisions. To date, AutoMP has been used by a large number of users for empirical research on deep learning model placement. The cumulative number of experiments has exceeded 10,000. The flexibility and extensibility of AutoMP and our own experience using it show that this tool plays a vital role in promoting Green AI.

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test data with potential distribution shifts. Most existing TTA methods focus on classification problems. The pronounced success of classification might lead numerous newcomers and engineers to assume that classic TTA techniques can be directly applied to the more challenging task of semantic segmentation. However, this belief is still an open question. In this paper, we investigate the applicability of existing classic TTA strategies in semantic segmentation. Our comprehensive results have led to three key observations. First, the classic normalization updating strategy only brings slight performance improvement, and in some cases, it might even adversely affect the results. Even with the application of advanced distribution estimation techniques like batch renormalization, the problem remains unresolved. Second, although the teacher-student scheme does enhance the training stability for segmentation TTA in the presence of noisy pseudo-labels and temporal correlation, it cannot directly result in performance improvement compared to the original model without TTA under complex data distribution. Third, segmentation TTA suffers a severe long-tailed class-imbalance problem, which is substantially more complex than that in TTA for classification. This long-tailed challenge negatively affects segmentation TTA performance, even when the accuracy of pseudo-labels is high. Besides those observations, we find that visual prompt tuning (VisPT) is promising in segmentation TTA and propose a novel method named TTAP. The outstanding performance of TTAP has also been verified. We hope the community can give more attention to this challenging, yet important, segmentation TTA task in the future. The source code is available at: https://github.com/ycarobot/TTAP.

Graph neural networks (GNNs) are currently one of the most performant and versatile collaborative filtering methods. Meanwhile, like in traditional collaborative filtering, owing to the use of an embedding table to represent each user/item entity as a distinct vector, GNN-based recommenders have inherited its long-standing defect of parameter inefficiency. As a common practice for scalable embeddings, parameter sharing enables the use of fewer embedding vectors (which we term meta-embeddings), where each entity is represented by a unique combination of meta-embeddings instead. When assigning meta-embeddings, most existing methods are a heuristically designed, predefined mapping from each user/item entity's ID to the corresponding meta-embedding indexes (e.g., double hashing), thus simplifying the optimization problem into learning only the meta-embeddings. However, in the context of GNN-based collaborative filtering, such a fixed mapping omits the semantic correlations between entities that are evident in the user-item interaction graph, leading to suboptimal recommendation performance. To this end, we propose Lightweight Embeddings for Graph Collaborative Filtering (LEGCF), a parameter-efficient embedding framework dedicated to GNN-based recommenders. LEGCF innovatively introduces an assignment matrix as an additional learnable component on top of meta-embeddings. To jointly optimize these two heavily entangled components, aside from learning the meta-embeddings by minimizing the recommendation loss, LEGCF further performs efficient assignment update by enforcing a novel semantic similarity constraint and finding its closed-form solution based on matrix pseudo-inverse. The meta-embeddings and assignment matrix are alternately updated, where the latter is sparsified on the fly to ensure negligible storage overhead. Extensive experiments on three benchmark datasets have verified LEGCF's smallest trade-off between size and performance, with consistent accuracy gain over state-of-the-art baselines. The codebase of LEGCF is available in https://github.com/xurong-liang/LEGCF.

Federated recommender systems (FedRecs) have gained significant attention for their potential to protect user's privacy by keeping user privacy data locally and only communicating model parameters/gradients to the server. Nevertheless, the currently existing architecture of FedRecs assumes that all users have the same 0-privacy budget, i.e., they do not upload any data to the server, thus overlooking those users who are less concerned about privacy and are willing to upload data to get a better recommendation service. To bridge this gap, this paper explores a user-governed data contribution federated recommendation architecture where users are free to take control of whether they share data and the proportion of data they share to the server. To this end, this paper presents a cloud-device collaborative graph neural network federated recommendation model, named CDCGNNFed. It trains user-centric ego graphs locally, and high-order graphs based on user-shared data in the server in a collaborative manner via contrastive learning. Furthermore, a graph mending strategy is utilized to predict missing links in the graph on the server, thus leveraging the capabilities of graph neural networks over high-order graphs. Extensive experiments were conducted on two public datasets, and the results demonstrate the effectiveness of the proposed method.

The Point-of-Interest (POI) recommendation system, designed to recommend potential future visits of users based on their check-in sequences, faces the challenge of data scarcity. This challenge primarily stems from the data sparsity issue, namely users interact with only a small number of POIs. Most existing studies attempt to solve this problem by focusing on POI check-in sequences, without considering the substantial multi-modal content information (e.g. textual and image data) commonly associated with POIs. In this paper, we propose a novel multi-modal content-aware framework for POI recommendation (MMPOI). Our approach addresses the issue of data sparsity by incorporating multi-modal content information about POIs from a new perspective. Specifically, MMPOI leverages pre-trained models for inter-modal conversion and employs a unified pre-trained model to extract modal-specific features from each modality, effectively bridging the semantic gap between different modalities. We propose to build a Multi-Modal Trajectory Flow Graph (MTFG) which combines the multi-modal semantic structure with check-in sequences. Moreover, we design an adaptive multi-task Transformer that models users' multi-modal movement patterns and integrates them for the next POI recommendation tasks. Extensive experiments on four real-world datasets demonstrate that MMPOI outperforms state-of-the-art POI recommendation methods. To facilitate reproducibility, we have released both the code and the multi-modal POI recommendation datasets we collect https://github.com/zzmylq/MMPOI

In Location-based Social Networks (LBSNs), Point-of-Interest (POI) recommendation helps users discover interesting places. There is a trend to move from the conventional cloud-based model to on-device recommendations for privacy protection and reduced server reliance. Due to the scarcity of local user-item interactions on individual devices, solely relying on local instances is not adequate. Collaborative Learning (CL) emerges to promote model sharing among users. Central to this CL paradigm is reference data, which is an intermediary that allows users to exchange their soft decisions without directly sharing their private data or parameters, ensuring privacy and benefiting from collaboration. While recent efforts have developed CL-based POI frameworks for robust and privacy-centric recommendations, they typically use a single and unified reference for all users. Reference data that proves valuable for one user might be harmful to another, given the wide range of user preferences. Some users may not offer meaningful soft decisions on items outside their interest scope. Consequently, using the same reference data for all collaborations can impede knowledge exchange and lead to sub-optimal performance. To address this gap, we introduce the Decentralized Collaborative Learning with Adaptive Reference Data (DARD) framework, which crafts adaptive reference data for effective user collaboration. It first generates a desensitized public reference data pool with transformation and probability data generation methods. For each user, the selection of adaptive reference data is executed in parallel by training loss tracking and influence function. Local models are trained with individual private data and collaboratively with the geographical and semantic neighbors. During the collaboration between two users, they exchange soft decisions based on a combined set of their adaptive reference data. Our evaluations across two real-world datasets highlight DARD's superiority in recommendation performance and addressing the scarcity of available reference data.

Abstract Video frame interpolation (VFI) is a technique that synthesises intermediate frames between adjacent original video frames to enhance the temporal super‐resolution of the video. However, existing methods usually rely on heavy model architectures with a large number of parameters. The authors introduce an efficient VFI network based on multiple lightweight convolutional units and a Local three‐scale encoding (LTSE) structure. In particular, the authors introduce a LTSE structure with two‐level attention cascades. This design is tailored to enhance the efficient capture of details and contextual information across diverse scales in images. Secondly, the authors introduce recurrent convolutional layers (RCL) and residual operations, designing the recurrent residual convolutional unit to optimise the LTSE structure. Additionally, a lightweight convolutional unit named separable recurrent residual convolutional unit is introduced to reduce the model parameters. Finally, the authors obtain the three‐scale decoding features from the decoder and warp them for a set of three‐scale pre‐warped maps. The authors fuse them into the synthesis network to generate high‐quality interpolated frames. The experimental results indicate that the proposed approach achieves superior performance with fewer model parameters.

Non-pharmacological treatments have gained significant attention in the field of cognitive impairment. Among them, human–computer interaction-based (HCI) methods have emerged as a promising approach due to their broad applicability and convenience in assessing symptoms associated with this progressively debilitating condition. However, existing rehabilitation training systems for cognitive impairment lack effective assessment methods to meet the diverse rehabilitation needs of users. In this article, we surveyed existing HCI-based cognitive rehabilitation training systems and analyzed their advantages and shortcomings. Drawing from the insights gained from these systems, we propose a novel Leap Motion-based building block training system that incorporates system software capable of generating highly realistic virtual scenes, with the added capability of user behavior detection using Kinect. We conducted user testing of this new system, comparing the performance of a representative cohort with mild cognitive impairment (MCI) (n = 9) to that of disease-free participants (n = 10). Additionally, we conducted ergonomic experiments to assess the system’s performance in elderly people. The experimental results revealed significant differences between the MCI cohort and the control cohort. Specifically, the MCI cohort exhibited a reduced range of motion and longer task completion times compared to the control cohort. These findings have the potential to contribute to the differentiation of cognitive levels. In conclusion, our analysis of existing cognitive rehabilitation training systems provides valuable insights for researchers working on the development of future innovative cognitive rehabilitation training systems and enriches the non-pharmacological treatment models for cognitive impairment. Furthermore, the observed relationship between behavioral data, task completion times, and cognitive levels in older adults offers useful insights for the design of HCI-based approaches for diagnosing and assessing the treatment of MCI.

Vertical Federated Learning (VFL) is a private-preserving distributed machine learning paradigm that collaboratively trains machine learning models with participants whose local data overlap largely in the sample space, but not so in the feature space. Existing VFL methods are mainly based on synchronous computation and homomorphic encryption (HE). Due to the differences in the communication and computation resources of the participants, straggling participants can cause delays during synchronous VFL model training, resulting in low computational efficiency. In addition, HE incurs high computation and communication costs. Moreover, it is difficult to establish a VFL coordinator (a.k.a. server) that all participants can trust. To address these problems, we propose an efficient Asynchronous Multi-participant Vertical Federated Learning method (AMVFL). AMVFL leverages asynchronous training which reduces waiting time. At the same time, secret sharing is used instead of HE for privacy protection, which further reduces the computational cost. In addition, AMVFL does not require a trusted entity to serve as the VFL coordinator. Experimental results based on real-world and synthetic datasets demonstrate that AMVFL can significantly reduce computational cost and improve the accuracy of the model compared to five state-of-the-art VFL methods.

Big data and strong computing power have promoted artificial intelligence to the era of big models. In particular, ChatGPT’s debut heralded the vigorous development of large models. It is an urgent problem to train large models with trillion-level parameters efficiently. Traditional single-machine training stores all data and model parameters in memory. However, due to the limitation of memory and communication resources, when the amount of data or model parameters increases, the problem of memory shortage and communication blocking often occurs. Therefore, distributed training is the most effective ways to solve the above problems and improve training efficiency. In this paper, we propose the algorithmDL-DP, which can achieve an asymptotically optimal convergence rate$O(1/{\sqrt{TK\Gamma^*}})$while satisfyingε-differential privacy, whereTis the local epoch number,Kis the global maximum iteration number and$\Gamma^*$is the minimum covering index. In particular, when${\Gamma ^*} = N$, DL-DP achieves a convergence rate of$O(1/{\sqrt{TKN}})$, which is equivalent to the best-known FedAvg approach implemented by training the full model at each client. When${\Gamma ^*} = 1$, DL-DP achieves a convergence rate of$O(1/{\sqrt{TK}})$, which is comparable to OAP that assumes all parameters need to be trained at least once in each iteration. Finally, our algorithm has been demonstrated to converge through extensive experiments.

Nowadays, many dynamic recommendations still suffer from the insufficiency of finding user online interest evolving patterns because of those complicated interactions. In general, each interaction is usually impacted by multiple underlying reasons, which needs us to open the “box” of each interaction instance instead of simply treating them as a pair-wise link. Besides, different users usually perform differently for their long-term and short-term tastes, leaving traditional sequential models far from personalized. In this article, we propose a novel recommendation model based on Graph Diffusion and Ebbinghaus Curve. Specifically, to explore the underline reasons for different interactions, we explore an underlying sub-graph for each interaction and find important reasoning paths within the sub-graph via a well-designed graph diffusion method. To capture users’ personalized strategies on long-term and short-term tastes, we are inspired by the Ebbinghaus Curve, which can naturally describe users’ memory patterns, and design an effective neural network to process users’ evolving behaviors. We conduct extensive experiments on four real-world datasets and the results further confirm the superiority of our model compared with existing state-of-the-art baselines.

Traditional recommender systems estimate user preference on items purely based on historical interaction records, thus failing to capture fine-grained yet dynamic user interests and letting users receive recommendation only passively. Recent conversational recommender systems (CRSs) tackle those limitations by enabling recommender systems to interact with the user to obtain her/his current preference through a sequence of clarifying questions. Recently, there has been a rise of using knowledge graphs (KGs) for CRSs, where the core motivation is to incorporate the abundant side information carried by a KG into both the recommendation and conversation processes. However, existing KG-based CRSs are subject to two defects: (1) there is a semantic gap between the learned representations of utterances and KG entities, hindering the retrieval of relevant KG information; (2) the reasoning over KG is mostly performed with the implicitly learned user interests, overlooking the explicit signals from the entities actually mentioned in the conversation. To address these drawbacks, we propose a new CRS framework, namely, the Knowledge Enhanced Conversational Reasoning (KECR) model. As a user can reflect her/his preferences via both attribute- and item-level expressions, KECR jointly embeds the structured knowledge from two levels in the KG. A mutual information maximization constraint is further proposed for semantic alignment between the embedding spaces of utterances and KG entities. Meanwhile, KECR utilizes the connectivity within the KG to conduct explicit reasoning of the user demand, making the model less dependent on the user’s feedback to clarifying questions. As such, the semantic alignment and explicit KG reasoning can jointly facilitate accurate recommendation and quality dialogue generation. By comparing with strong baselines on two real-world datasets, we demonstrate that KECR obtains state-of-the-art recommendation effectiveness, as well as competitive dialogue generation performance.

Medicine package recommendation aims to assist doctors in clinical decision-making by recommending appropriate packages of medicines for patients. Current methods model this task as a multi-label classification or sequence generation problem, focusing on learning relationships between individual medicines and other medical entities. However, these approaches uniformly overlook the interactions between medicine packages and other medical entities, potentially resulting in a lack of completeness in recommended medicine packages. Furthermore, medicine commonsense knowledge considered by current methods is notably limited, making it challenging to delve into the decision-making processes of doctors. To solve these problems, we propose DIAGNN, a Dual-level Interaction Aware heterogeneous Graph Neural Network for medicine package recommendation. Specifically, DIAGNN explicitly models interactions of medical entities within electronic health records(EHRs) at two levels, individual medicine and medicine package, leveraging a heterogeneous graph. A dual-level interaction aware graph convolutional network is utilized to capture semantic information in the medical heterogeneous graph. Additionally, we incorporate medication indications into the medical heterogeneous graph as medicine commonsense knowledge. Extensive experimental results on real-world datasets validate the effectiveness of the proposed method.

Accurately estimating packages’ arrival time in e-commerce can enhance users’ shopping experience and improve the placement rate of products. This problem is often formalized as an Origin-Destination (OD)-based ETA (i.e., estimated time of arrival) prediction task, where the delivery time is estimated mainly based on sender and receiver addresses and other context information. One inherent challenge of the OD-based ETA problem is that the delivery time highly depends on the actual delivery trajectory which is unknown at the time of prediction. In this article, we tackle this challenge by effectively exploiting historical delivery trajectories. We propose a novel Knowledge Distillation Graph neural network-based package ETA prediction (KDG-ETA) model, which uses knowledge distillation in the training phase to distill the knowledge of historical trajectories into OD pair embeddings. In KDG-ETA, a multi-level trajectory graph representation model is proposed to fully exploit trajectory information at the node-level, edge-level, and path-level. Then, the OD representations embedded with trajectory knowledge are combined with context embeddings from feature extraction module for delivery time prediction using an adaptive attention module. KDG-ETA consistently outperforms existing state-of-the-art OD-based ETA prediction methods on three real-world Alibaba datasets, reducing the Mean Absolute Error (MAE) by 3.0%–39.1% as demonstrated in our extensive empirical evaluation.

Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance. The underlying principle of CL-based recommendation models is to ensure the consistency between representations derived from different graph augmentations of the user-item bipartite graph. This self-supervised approach allows for the extraction of general features from raw data, thereby mitigating the issue of data sparsity. Despite the effectiveness of this paradigm, the factors contributing to its performance gains have yet to be fully understood. This paper provides novel insights into the impact of CL on recommendation. Our findings indicate that CL enables the model to learn more evenly distributed user and item representations, which alleviates the prevalent popularity bias and promoting long-tail items. Our analysis also suggests that the graph augmentations, previously considered essential, are relatively unreliable and of limited significance in CL-based recommendation. Based on these findings, we put forward an eXtremelySimpleGraphContrastiveLearning method (XSimGCL) for recommendation, which discards the ineffective graph augmentations and instead employs a simple yet effective noise-based embedding augmentation to generate views for CL. A comprehensive experimental study on four large and highly sparse benchmark datasets demonstrates that, though the proposed method is extremely simple, it can smoothly adjust the uniformity of learned representations and outperforms its graph augmentation-based counterparts by a large margin in both recommendation accuracy and training efficiency. The code and used datasets are released athttps://github.com/Coder-Yu/SELFRec.

Personalized federated learning (PFL) learns a personalized model for each client in a decentralized manner, where each client owns private data that are not shared and data among clients are non-independent and identically distributed (i.i.d.) However, existing PFL solutions assume that clients have sufficient training samples to jointly induce personalized models. Thus, existing PFL solutions cannot perform well in a few-shot scenario, where most or all clients only have a handful of samples for training. Furthermore, existing few-shot learning (FSL) approaches typically need centralized training data; as such, these FSL methods are not applicable in decentralized scenarios. How to enable PFL with limited training samples per client is a practical but understudied problem. In this article, we propose a solution called personalized federated few-shot learning (pFedFSL) to tackle this problem. Specifically, pFedFSL learns a personalized and discriminative feature space for each client by identifying which models perform well on which clients, without exposing local data of clients to the server and other clients, and which clients should be selected for collaboration with the target client. In the learned feature spaces, each sample is made closer to samples of the same category and farther away from samples of different categories. Experimental results on four benchmark datasets demonstrate that pFedFSL outperforms competitive baselines across different settings.

In this paper, a mixed-bouncing based channel model with cooperative space-array-time (S-A-T) consistency and space-array-time-frequency (S-A-T-F) non-stationarity is proposed for sixth generation (6G) multiple-unmanned aerial vehicle (multi-UAV) cooperative communication systems with millimeter wave (mmWave) and massive multiple-input multiple-output (MIMO) technologies. To model the transmission propagation in multi-UAV integrated channels more accurately, the single-bouncing transmissions and multi-bouncing transmissions in multi-UAV integrated channels are simultaneously modeled and quantified by a cooperative cluster density index for the first time. Meanwhile, the transmissions through line-of-sight (LoS), ground reflection, single-bouncing, and multi-bouncing are captured. To jointly mimic cooperative S-A-T consistency and S-A-T-F non-stationarity in the integrated scattering environment (SE), a new cooperative consistent and non-stationary modeling algorithm is developed based on the frequency-dependent path gain, visibility region (VR), and birth-death (BD) survival probability. The channel parameters related to multi-UAVs are also taken into account in the developed algorithm. The corresponding multi-UAV cooperative channel statistical properties are derived by taking mixed-bouncing transmission into account. Meanwhile, the accuracy of the mixed-bouncing based multi-UAV integrated channel model with cooperative S-A-T consistency and S-A-T-F non-stationarity is validated as simulation results match well with ray-tracing results.

Automatic medical report generation is an essential task in applying artificial intelligence to the medical domain, which can lighten the workloads of doctors and promote clinical automation. The state-of-the-art approaches employ Transformer-based encoder-decoder architectures to generate reports for medical images. However, they do not fully explore the relationships between multi-modal medical data, and generate inaccurate and inconsistent reports. To address these issues, this paper proposes a Multi-modal Memory Transformer Network (MMTN) to cope with multi-modal medical data for generating image-report consistent medical reports. On the one hand, MMTN reduces the occurrence of image-report inconsistencies by designing a unique encoder to associate and memorize the relationship between medical images and medical terminologies. On the other hand, MMTN utilizes the cross-modal complementarity of the medical vision and language for the word prediction, which further enhances the accuracy of generating medical reports. Extensive experiments on three real datasets show that MMTN achieves significant effectiveness over state-of-the-art approaches on both automatic metrics and human evaluation.

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in the absence of expert annotations. However, existing contrastive approaches generally treat each instance independently, which leads to false negative pairs that share the same semantics. To tackle this problem, we propose MHCCL, a Masked Hierarchical Cluster-wise Contrastive Learning model, which exploits semantic information obtained from the hierarchical structure consisting of multiple latent partitions for multivariate time series. Motivated by the observation that fine-grained clustering preserves higher purity while coarse-grained one reflects higher-level semantics, we propose a novel downward masking strategy to filter out fake negatives and supplement positives by incorporating the multi-granularity information from the clustering hierarchy. In addition, a novel upward masking strategy is designed in MHCCL to remove outliers of clusters at each partition to refine prototypes, which helps speed up the hierarchical clustering process and improves the clustering quality. We conduct experimental evaluations on seven widely-used multivariate time series datasets. The results demonstrate the superiority of MHCCL over the state-of-the-art approaches for unsupervised time series representation learning.

The rapidly increasing adoption of Electronic Health Records (EHRs) has provided us with a comprehensive and reliable data repository, enabling the robust support for clinical decision making and the efficacious management of cardiovascular diseases. Patients may receive various treatment regimens due to the idiosyncratic dissimilarities in physical conditions. Hence, assigning specific category labels to treatment regimens for individual patients poses a challenge owing to the intricate nature of diverse medications and patient profiles. In this paper, we address this challenge by developing a novel model for Treatment Regimen Recommendations based on Siamese Neural Networks (TRRSNN). TRRSNN is harnessed to learn a global similarity metric from EHRs, facilitating the comparison and matching of target patients from unknown categories. The objective is to proffer recommendations of pre-existing treatments of patients that exhibit the highest semblance to those of target patients. Our proposed TRRSNN obviates the necessity for categorically labeling treatment regimens, and instead focuses on discerning the similarity among treatment regimens for pairwise patients. We conduct empirical evaluations on two real-world datasets, and the results demonstrate the superiority of our proposed TRRSNN over the baselines for treatment regimen recommendations.

Major depressive disorder (MDD) is the most common psychological disorder that affects mental and physical health. To narrow the gap in real world mental healthcare and improve the effectiveness of MDD treatment, an increasing number of artificial intelligence (AI) methods have been proposed to explore electroencephalography (EEG) features, including traditional signal features and measures of brain functional connectivity network (BFCN), for the recognition of depression-related patterns. However, these methods fail to capture long-term dependencies and limit the modeling ability of information transmission dependencies in MDD brain regions. To address these issues, we propose a novel brain functional residual temporal convolution network (BFRTCN) method for MDD recognition. On one hand, this model directly focuses on the connectivity weights of BFCNs to model the information transmission between brain regions, allowing for better differentiation of the differences in information transmission patterns between MDD and normal control (NC). On the other hand, we introduce a residual temporal convolution network (ResiTCN) that utilizes temporal convolution layers to capture short-term changes in brain regions and establish residual connections to help maintain long-term dependencies for improving ability to capture disease variations. Experimental results on benchmark datasets validate the superior performance and time complexity of BFRTCN. Analysis shows that the Beta band MDD transmission mode is relatively stable. There are defects in the brain functional connections between the frontal and right temporal (RT) regions on Alpha and Gamma bands, which can serve as potential biomarkers for MDD recognition.

Data are invaluable in machine learning (ML), yet they raise significant privacy concerns. In the real world, data are often distributed across isolated silos, challenging conventional ML methods that centralize data. Federated learning (FL) offers a privacy-preserving solution that enables learning without direct data transfer. Meanwhile, the “right to be forgotten” sparks privacy-preserving methods from another viewpoint as machine unlearning, enabling data owners to erase specific data contributions from ML models. However, the invisibility of data in FL scenarios complicates effective local data removal, necessitating tailored unlearning algorithms for FL. Existing federated unlearning methods fall into approximate unlearning, leaving residual memorization of target data, consequently diminishing user trust. To bridge this gap, we propose FedCIO, a novel framework for exact federated unlearning, designed to efficiently manage precise data removal requests in FL scenarios. Specifically, the framework involves client clustering, isolation among clusters, and one-shot aggregation of cluster models. This framework facilitates efficient unlearning by retraining only a relevant model subset rather than from scratch. To enhance the capability to handle Non-Independent and Identically Distributed (Non-IID) data, we further introduce an advanced spectral clustering implementation based on model similarity for better cluster partitioning. Comprehensive evaluation across common FL datasets with varied distributions demonstrates the superior performance of our proposed framework.

Narrative generation aims at producing fluent long texts from input data, which is widely used in event prediction, story generation and other fields. Previous work mainly relied on text data, picture data, knowledge graphs, etc. Unfortunately, these static data only focused on entities and their relationships, cannot reflect the dynamic development of events in the real world. In addition, because the language model itself does not have the ability of logical reasoning, the generated results often lack logical reasoning. To address these challenges, several studies incorporate logic event graphs into the task of narrative generation. The Logic Event Graph(LEG) is essentially an event logic knowledge base, which describes the event evolution law and development modes. With the help of the LEG, the narrative generation system will acquire the human "reasoning" ability, and generate narratives that better reflect the objective evolution laws of human behaviors and events. While significant research has been conducted in these areas, gaps in the surveying literature still exist. In this survey, we—(1)analyze the context of narrative generation; (2)discuss the advantages of joining the LEG in narrative generate; (3)review common strategies in narrative generation; (4)summarize the evaluation metricse of narrative generate, and the advantages and disadvantages of each evaluation metrics are discussed; (5)present current challenges and future research directions. This survey can guide researchers and practitioners to understand the research progress in these areas.

E-commerce live streaming as an increasingly popular sales model has generated a significant amount of gross merchandise value (GMV) for e-commerce platforms. Live streaming recommendation systems (LSRS) of e-commerce aim to recommend the most appropriate live channels for users to motivate them to buy products. Existing LSRS methods focus only on the user’s interaction behaviors on the live channel (live domain) while ignoring the user’s behaviors and intentions on the e-commerce product (product domain). As a result, the user’s consistent purchase intentions in the cross-domain are not being fully captured, especially when user present differentiated purchase intentions in the cross-domain. How to disentangle user’s consistent intentions and domain-specific intentions in the cross-domain poses a challenge to the LSRS of e-commerce platforms. In this paper, we present a live channel recommendation method, named eLiveRec, developed for Taobao, one of the largest e-commerce platform in the world. Specifically, eLiveRec employs the disentangled encoder module to learn user’s cross-domain consistent intentions and domain-specific intentions. Then, an adaptive multi-task learning framework is developed to jointly optimize the multiple objectives (e.g., stay time, click goods bag, and click products after entering channel) related to live streaming recommendation. In this way, the performance of live streaming recommendation can be further improved and con-form to standard industry RS paradigms. Extensive experiments are conducted on a large-scale industry dataset collected from Taobao Live platform have been performed. Both online and offline experimental results indicate that eLiveRec consistently outperforms existing state-of-the-art baseline methods.

Predicting Estimated Time of Arrival (ETA) for packages is a critical problem in e-commerce. The prediction is often made based on spatial (sending and receiving addresses), temporal (payment time), and context (merchants) attributes. Existing methods usually formalize this task as an Origin-Destination (OD) ETA prediction problem and exploit the attribute relations with graph learning. However, most existing methods make use of fixed and manually defined graph structures, which are often not optimal for downstream ETA task and hence lead to unsatisfactory prediction results. In addition, current ETA models tend to focus on prediction accuracy without considering fulfillment rate. This may lead to a low fulfillment rate in practice, i.e., actual delivery time is much longer than estimations provided by models, which consequently exacerbates the frustrating experiences for users. To address these issues, we propose a novel Graph Structure Learning-based Quantile Regression (GSL-QR) model for e-commerce ETA prediction in this paper. Specifically, we utilize graph structure learning to dynamically update the spatial and temporal relation graphs of orders and learn optimal graph structures and graph embeddings guided by downstream ETA prediction task. To guarantee both prediction accuracy and order fulfillment rate, we design a multi-objective quantile regression in GSL-QR that can find the Pareto solution of the problem. In order to extend GSL to large-scale real-world graphs, we devise a Fast Sampling-based Graph Structure Learning (FS-GSL) method, which can significantly reduce the computational complexity of graph structure learning. Finally, we conduct comprehensive experiments on three industrial datasets collected from Alibaba e-commerce platform. The results demonstrate that the proposed model can significantly outperform baselines on both ETA prediction accuracy and order fulfillment rate.

Edge computing has been widely used to deploy and service deep learning applications. Equipped with GPUs, edge nodes can process concurrent incoming inference requests of the deep learning model. However, existing methods for inference tasks do not allow efficient parallel handling of user requests. This paper investigates the popular Transformer deep learning model and develops ParaTra, a parallel transformer inference framework for providing parallel inference services to users. In the framework, the Transformer model is partitioned and deployed in users’ devices and the edge node to efficiently utilize their processing power. The concurrent inference tasks with different sizes are dynamically packaged in a scheduling queue and sent in batch to an encoder-decoder pipeline for processing. ParaTra can significantly reduce the overheads of parallel processing and the usage of GPU memory. Experiment results show that ParaTra can save up to 37.1% of GPU memory usage and improve 8.4 times of processing speed.

Addressing untrustworthy behavior in cross departmental business process collaboration is the focus of current research. The untrustworthiness of the business process not only leads to the misuse and leakage of business data, but also leads to cheating by the participants in the business process. This paper proposes a blockchain-based trustworthy cross-departmental business process collaboration service mechanism(TBPCS) to solve the above problems. This paper firstly maps the participants, data and data ownership of the business process to the blockchain, which prevents the business process from being tampered with. This method allows the participants in the business process to act under the constraints of a trusted environment, avoiding the illegal use of business data. Then this paper maps the business process to the blockchain in the form of smart contracts, which ensures crossdepartment business process collaboration is trustworthy and reduces the verification cost of business data. This paper innovatively proposes a rollback mechanism that supports business interruptions. The mechanism ensures that the business process is trustworthy even in abnormal situations.

The increasing popularity of crowdsourcing has resulted in the emergence of multiple crowdsourcing service providers (CSPs), such as Mechnical Turk and Crowdflower, which compete to attract crowd workers (CWs). CWs can share their experience working for various CSPs, which forms the basis of CSP reputation score. This information can be used for trust building and facilitating future CWs’ decisions on which CSP to work for. Existing reputation management research in crowdsourcing has mainly focused on controlling task quality and improving revenue from the perspective of CSPs. Little attention has been paid to helping CSPs manage their reputation to attract and retain CWs. In this paper, we propose the Crowdsourcing Service Provider Reputation Management (CSP-RM) framework to bridge this important gap. Based on the current reputation of CSPs, it dynamically balances the trade-off between the reputation maintenance cost and the long-term profit for a given CSP. It performs dynamic commission allocation for a CSP based on Lyapunov optimization to guide the recruitment of CWs, while considering the revenue and the changes in the number of CWs. Extensive experiments based on highly competitive crowdsourcing market demonstrate that CSP-RM makes the most advantageous cost-benefit trade-off compared to existing approaches, outperforming the best baseline by 23.83%, 39.21% and 3.36% in terms of average cumulative revenue, average number of CWs and public reputation, respectively. To the best of our knowledge, it is the first decision support framework for enabling CSPs to recruit more CWs in a highly competitive market, while maintaining their reputation and ensuring long-term benefit.

Human trajectories have explicit linkages to urban dynamics and functions. Therefore, learning urban region representations from human trajectories could help understand cities, and be used in various downstream tasks, e.g., land use classification and crime prediction, and ultimately assist city planning and management. However, previous works fall short in deeply mining the complete information embodied in human trajectories and neglect the data sparsity issue of some regions. We propose a multi-view graph contrastive learning (MVGCL) framework to learn urban region representations from human trajectories and the spatial adjacency between urban regions. First, we construct an outflow view based on human trajectories and devise data augmentation techniques to construct an inflow view. Then, we construct a spatial view based on the spatial adjacency between regions. Moreover, we use an MLP to extract spatial features from spatial view and model two graph encoders to learn complete region representation. Finally, we utilize a dual-multiplet loss function based on graph contrastive learning to maximize node consistency. Extensive experiments in Manhattan regions demonstrate that the performance of MVGCL outperforms the state-of-the-art methods.

Latent factor models are the most popular backbones for today's recommender systems owing to their prominent performance. Latent factor models represent users and items as real-valued embedding vectors for pairwise similarity computation, and all embeddings are traditionally restricted to a uniform size that is relatively large (e.g., 256-dimensional). With the exponentially expanding user base and item catalog in contemporary e commerce, this design is admittedly becoming memory-inefficient. To facilitate lightweight recommendation, reinforcement learning (RL) has recently opened up opportunities for identifying varying embedding sizes for different users/items. However, challenged by search efficiency and learning an optimal RL policy, existing RL-based methods are restricted to highly discrete, predefined embedding size choices. This leads to a largely overlooked potential of introducing finer granularity into embedding sizes to obtain better recommendation effectiveness under a given memory budget. In this paper, we propose continuous input embedding size search (CIESS), a novel RL-based method that operates on a continuous search space with arbitrary embedding sizes to choose from. In CIESS, we further present an innovative random walk-based exploration strategy to allow the RL policy to efficiently explore more candidate embedding sizes and converge to a better decision. CIESS is also model-agnostic and hence generalizable to a variety of latent factor RSs, whilst experiments on two real-world datasets have shown state-of-the-art performance of CIESS under different memory budgets when paired with three popular recommendation models.

Federated Learning (FL) is a distributed machine learning technique that trains models on local devices to preserve data privacy. In FL, evaluating model quality is crucial for detecting malicious clients and improving model accuracy. However, existing methods typically require a representative public testing dataset on the server, which is often unavailable in practical federated learning scenarios. To address this problem, we propose a novel four-step framework, taking a crowdsourcing approach. The basic idea is to distribute the model to be evaluated as a task to a set of testing clients selected from the original clients pool, who evaluate the model quality using their local datasets. By consolidating these individual evaluations, we obtain the overall model quality. To select a suitable number of testing clients, we propose an exploration-exploitation-based framework. Furthermore, to safeguard against attacks from potential malicious testing clients, we introduce a Correlated Agreement (CA) mechanism. This is achieved by comparing correlations of accuracy among the same set of testing clients (who were selected for the aforementioned evaluation task). Extensive experiments demonstrate the effectiveness of our approach, which yields accuracy comparable to methods that rely on a public testing dataset on the server. Moreover, our approach can identify and filter out dishonest testing clients and thereby ensure model quality even in adversarial settings.

BACKGROUND: Cell-penetrating peptides (CPPs) have received considerable attention as a means of transporting pharmacologically active molecules into living cells without damaging the cell membrane, and thus hold great promise as future therapeutics. Recently, several machine learning-based algorithms have been proposed for predicting CPPs. However, most existing predictive methods do not consider the agreement (disagreement) between similar (dissimilar) CPPs and depend heavily on expert knowledge-based handcrafted features. RESULTS: In this study, we present SiameseCPP, a novel deep learning framework for automated CPPs prediction. SiameseCPP learns discriminative representations of CPPs based on a well-pretrained model and a Siamese neural network consisting of a transformer and gated recurrent units. Contrastive learning is used for the first time to build a CPP predictive model. Comprehensive experiments demonstrate that our proposed SiameseCPP is superior to existing baseline models for predicting CPPs. Moreover, SiameseCPP also achieves good performance on other functional peptide datasets, exhibiting satisfactory generalization ability.

Abstract Software resource allocation is an significant factor of system configuration which plays a critical role in guaranteeing the performance of multitier web service systems. Computing the optimal allocation of different software resources in order to meet performance requirements under dynamic workloads conditions is in highly challenging. Existing approaches mostly rely on translating domain knowledge from experts into computational solutions through heuristics‐based optimization techniques. While such techniques are useful, they cannot leverage actual usage data generated by system users which may contain allocation strategies that are not captured by domain experts' knowledge. In this paper, we propose an iterative feedback mechanism which solves the problem to some extent by optimizing software resource allocation of multitier web systems through imitating system users who have achieved excellent performance. Specifically, we propose a deep Q‐learning network‐based approach for performance prediction to deal with the dynamic changes of complex workloads. The performance prediction method involves the reinforcement learning method for capturing the dynamics of online software resource allocation, and then computing the current optimal policy. We implement the approach in the multitier web benchmark system, and the experimental results demonstrated significant improvement compared to models built based on domain knowledge.

Accurate diagnosis of cancer subtypes is crucial for precise treatment, because different cancer subtypes are involved with different pathology and require different therapies. Although deep learning techniques have made great success in computer vision and other fields, they do not work well on Lung cancer subtype diagnosis, due to the distinction of slide images between different cancer subtypes is ambiguous. Furthermore, they often over-fit to high-dimensional genomics data with limited samples, and do not fuse the image and genomics data in a sensible way. In this paper, we propose a hybrid deep network based approach LungDIG for Lung cancer subtype Diagnosis by fusing Image-Genomics data. LungDIG first tiles the tissue slide image into small patches and extracts the patch-level features by fine-tuning an Inception-V3 model. Since the patches may contain some false positives in non-diagnostic regions, it further designs a patch-level feature combination strategy to integrate the extracted patch features and maintain the diversity between different cancer subtypes. At the same time, it extracts the genomics features from Copy Number Variation data by an attention based nonlinear extractor. Next, it fuses the image and genomics features by an attention based multilayer perceptron (MLP) to diagnose cancer subtype. Experiments on TCGA lung cancer data show that LungDIG can not only achieve higher accuracy for cancer subtype diagnosis than state-of-the-art methods, but also have a high authenticity and good interpretability.

The Healthcare Internet-of-Things (IoT) framework aims to provide personalized medical services with edge devices. Due to the inevitable data sparsity on an individual device, cross-device collaboration is introduced to enhance the power of distributed artificial intelligence. Conventional collaborative learning protocols (e.g., sharing model parameters or gradients) strictly require the homogeneity of all participant models. However, real-life end devices have various hardware configurations (e.g., compute resources), leading to heterogeneous on-device models with different architectures. Moreover, clients (i.e., end devices) may participate in the collaborative learning process at different times. In this paper, we propose a Similarity-Quality-based Messenger Distillation (SQMD) framework for heterogeneous asynchronous on-device healthcare analytics. By introducing a preloaded reference dataset, SQMD enables all participant devices to distill knowledge from peers via messengers (i.e., the soft labels of the reference dataset generated by clients) without assuming the same model architecture. Furthermore, the messengers also carry important auxiliary information to calculate the similarity between clients and evaluate the quality of each client model, based on which the central server creates and maintains a dynamic collaboration graph (communication graph) to improve the personalization and reliability of SQMD under asynchronous conditions. Extensive experiments on three real-life datasets show that SQMD achieves superior performance.

With the accumulation of check-in data from location-based services, next Point-of-Interest (POI) recommendations are gaining increasing attention. It is well known that the spatio-temporal contextual information of user check-in behavior plays a crucial role in handling vital and inherent challenges in next POI recommendation, including capture of user dynamic preferences and the sparsity problem of check-in data. However, many studies either ignore or simply stack the context features with the embedding of POIs while relying only on POI recommendation loss to optimize the entire model, therefore failing to take full advantage of the potential information in contexts. Additionally, users’ interests are usually unstable and evolve over time, and accordingly recent studies have proposed various approaches to predict users’ next POIs by incorporating contextual information and modeling both their long- and short-term preferences, respectively. Yet many studies overemphasize the final POI recommendation performance, and the association between POI sequences and contextual information is not well embodied in data representations. In this article, we focus on the preceding problems and propose a unified attention framework for next POI recommendation by modeling users’ Long- and Short-term Preferences via Self-supervised Learning (LSPSL). Specifically, based on the self-attention network and two self-supervised optimization objectives, LSPSL first deeply exploits the intrinsic correlations between POI sequences and contextual information through pre-training, which strengthens data representations. Then, supported by pre-trained contextualized embeddings, LSPSL models and fuses users’ complex long- and short-term preferences in a unified way. Extensive experiments on real-world datasets demonstrate the superiority of our model compared with other state-of-the-art approaches.

In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.

Numerous electronic health records (EHRs) offer valuable opportunities for understanding patients' health status at different stages, namely health progression. Extracting the health progression patterns allows researchers to perform accurate predictive analysis of patient outcomes. However, most existing works on this task suffer from the following two limitations: 1) the diverse dependencies among heterogeneous medical entities are overlooked, which leads to the one-sided modeling of patients' status and 2) the extraction granularity of patient's health progression patterns is coarse, limiting the model's ability to accurately infer the patient's future status. To address these challenges, a pretrained Health progression network via heterogeneous medical information fusion, HealthNet, is proposed in this article. Specifically, a global heterogeneous graph in HealthNet is built to integrate heterogeneous medical entities and the dependencies among them. In addition, the proposed health progression network is designed to model hierarchical medical event sequences. By this method, the fine-grained health progression patterns of patients' health can be captured. The experimental results on real disease datasets demonstrate that HealthNet outperforms the state-of-the-art models for both diagnosis prediction task and mortality prediction task.

In this paper, a novel cooperative array-space-time-frequency (A-S-T-F) non-stationary multi-unmanned aerial vehicle (UAV) channel model with three-dimensional (3D) continuously arbitrary trajectory and self-rotation for sixth generation (6G) massive multiple-input multiple-output (MIMO) millimeter wave (mmWave) wireless communication systems is proposed. The channel impulse response (CIR) of the proposed multi-UAV cooperative channel model is derived, including line-of-sight (LoS), ground reflection, and non-LoS (NLoS) transmissions. To capture the 3D continuously arbitrary trajectories of multi-UAVs, the 3D time-varying accelerations of multi-UAVs, clusters, and ground station (GS) and the multi-UAVs’ self-rotations are taken into account. In addition, to model the non-stationarity of massive MIMO mmWave multi-UAV cooperative channels in the A-S-T-F domain, a new cooperative A-S-T-F non-stationary algorithm based on the birth-death (BD) process and the$K$-Means clustering algorithm is developed. Important cooperative channel statistical properties, including cooperative array-space-time-frequency correlation function (ASTF-CF), cooperative Doppler power spectral density (DPSD), cooperative time stationary interval, and singular value spread (SVS), are derived and investigated. The accuracy of the proposed multi-UAV cooperative channel model is verified by the close agreement between ray-tracing-based results and simulation results.

Automatic diagnosis for medical images is a significant research problem of computer-aided diagnosis to reduce the workload of doctors in recent years. However, existing deep learning approaches for diagnoses are usually black-box models with implicit decision-making processes that make them inexplainable. To alleviate the issue, in this paper, we propose a Knowledge-driven Interpretable Network (KdINet) for interpretable disease classification of medical images. KdINet first exploits the pretrained CNN module and the hierarchical representation module to learn two different disease feature representations (i.e., visual disease features and hierarchical disease features). Subsequently, the joint training of two disease features by KdINet’s disease classifier learns a hierarchical classification criterion to infer the diagnosis and generate corresponding interpretable justifications (i.e., ancestral disease paths of the diagnosis). Extensive experiments on three datasets demonstrate that our KdINet achieves significantly higher effectiveness than state-of-the-art approaches on disease classification metrics.

Disease risk prediction is an important component of clinical decision support systems. In order to predict disease risk, most studies attempt to extract features associated with disease risk from electronic health records (EHRs), however, the complex interactions between heterogeneous entities associated with disease risk (e.g., diseases, symptoms, medications, and other treatment items) are ignored, resulting in imprecise disease risk prediction. To tackle this issue, we propose a disease prediction method based on heterogeneous graph attention networks (HAN) in this paper. In our study, the EHRs are used to constructed the heterogeneous medical graph, in which the embedding vector of each node can be calculated via its directly connected neighbors’ features. The heterogeneous medical graph contains different types of nodes and links, and in our proposed model, the attention mechanism is adopted, which is used to learn the importance between a node and its meta-path connected neighboring nodes. The proposed method is good at mining the potential information of the electronic medical records. Experiment results on real datasets show that the performance of the poposed methods outperforms that of the baseline methods.

In the medical scenarios, the demand for secure sharing of medical data and trusted federated computing continues to increase, and blockchain technology can provide secure, credible, and tamper-resistant capabilities, which makes it necessary to combine the two. However, the full application of blockchain to medical scenarios faces two issues. Medical assets such as medical cohort data with strong data correlation and large scale are difficult to be accurately described and safely operated by blockchain. Transactions such as disease diagnosis and hospitalization prediction with many parameters are difficult to execute concurrently in blockchain. Therefore, we propose MAA model, which closely associates patients with assets, separates the logic of asset operations from its storage. At the same time, we propose OPE model with double-layer pipeline concurrency. By constructing the Dependency Graph, and generating multiple blocks with low conflict rates, which are executed simultaneously among multiple Execute Groups, OPE supports the high concurrent execution of medical transactions with high computing power requirements such as trusted federated learning. Experiments show that our model supports multiple types of medical data on-chain compared to existing models, and the concurrency is increased by at least 40% in a high-conflict medical environment.

Massive EHR (electronic health records) data contains rich health-related information and offers valuable opportunities for healthcare prediction tasks. Most existing works have achieved great success in improving the accuracy of prediction by leveraging deep learning to model sequential EHR data. However, entangled patient modeling results in inability of quantifying the importance of each type of feature. In this paper, we propose a feature-guided logical perception network FeLON for health risk prediction. FeLON is built on model-level explanation and consists of two main steps. The core part of the first step is a logical perception network to extract logical rules from patient features. In the second step, FeLON builds a fully-connected layer to integrate logical rules information to calculate health risk. Extensive experiments are conducted on two real disease datasets. The experimental results demonstrate that FeLON is able to maintain high prediction accuracy while bringing transparent reasoning process.

Clinical pathway recommendation aims to recommend a set of treatment modalities or treatment procedures for a patient. In order to achieve personalized clinical pathway recommendation, more and more researchers try to mine similar clinical paths from the statistical features of patient-related clinical data (such as electronic health records), while ignoring the high-order interactions between patient-related medical entities, and the time-series change pattern of this high-order interaction relationship, resulting in the inability of existing methods to fully describe patient characteristics and to accurately recommend personalized clinical pathways. To solve the above problems, we propose a new personalized clinical pathway recommendation model TempHRec. To model the complex high-order relationship in clinical pathway, hypergraph technology is introduced to solve the problem that clinical events are correlated at the same time window. On this basis, we propose a temporal hypergraph, to construct a hypergraph for each timestamp with the help of a sliding time window to capture the timing information at the clinical pathway. Extensive experimental results on real-world datasets show that the proposed model achieves the best results compared to baseline methods.

Real-world graphs are typically distributed across multiple data centers. When performing reachability queries on these distributed graphs, reachability labeling methods ensure fast query processing by using lightweight indexes. One of the best-known labeling methods is TOL; however, TOL is a serial algorithm and cannot handle distributed graphs. The main goal of this paper is to design new labeling methods that can work in parallel while producing the same index as TOL. To this end, we investigate the limitation of TOL and thus propose a filtering-and-refinement framework for index creation. This framework first obtains a super-set of each vertex's label sets and then eliminates the invalid elements. Based on this framework, we design distributed labeling algorithms and then use batch processing to improve efficiency. Experimental results on real-world graphs show that the proposed algorithms can index distributed graphs efficiently.

With the rapid growth of service requirements, the rising concern of resource allocation fairness (e.g., the actual gained Quality of Service(QoS)) leads to the popularity of studies for fair scheduling mechanisms in service systems. The Generalized Processor Sharing (GPS) mechanism has been widely utilized as the fair reference base in the resource allocation due to its fairness and flexible configuration (i.e. scheduling based on weights). The urgent objective of GPS is to accurately evaluate the QoS of each service. Due to the inherent interconnected feature of the GPS mechanism, it is challenging to accurately evaluate individual service’ obtained QoS metrics by analytical-based methods with the growing number of services. Besides, considering the burstiness of the service requests, self-similar process is utilized to delineate the arrival of the service. Therefore, we propose a deep learning based approach, terms as DLPE_GPS, to accurately compute the QoS metrics of individual services in multi-queue GPS under self-similar request traffic. Specifically, DLPE_GPS firstly leverages knowledge-driven features to characterize each service (i.e., arrival rates, weight assigned, etc), and then the representation of each service is computed by a well designed multi-head attention mechanism considering mutual effect be-tween different service subsystems. After that, the knowledge-driven features and intermediate capacities are fused for QoS evaluation. Finally, we conduct complex experiments to show the effectiveness of the proposed method in terms of various aspects.

The sequential recommendation systems capture users' dynamic behavior patterns to predict their next interaction behaviors. Most existing sequential recommendation methods only exploit the local context information of an individual interaction sequence and learn model parameters solely based on the item prediction loss. Thus, they usually fail to learn appropriate sequence representations. This paper proposes a novel recommendation framework, namely Graph Contrastive Learning for Sequential Recommendation (GCL4SR). Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data. Moreover, GCL4SR uses subgraphs of WITG to augment the representation of each interaction sequence. Two auxiliary learning objectives have also been proposed to maximize the consistency between augmented representations induced by the same interaction sequence on WITG, and minimize the difference between the representations augmented by the global context on WITG and the local representation of the original sequence. Extensive experiments on real-world datasets demonstrate that GCL4SR consistently outperforms state-of-the-art sequential recommendation methods.

Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling the data sparsity issue. A typical pipeline of CL-based recommendation models is first augmenting the user-item bipartite graph with structure perturbations, and then maximizing the node representation consistency between different graph augmentations. Although this paradigm turns out to be effective, what underlies the performance gains is still a mystery. In this paper, we first experimentally disclose that, in CL-based recommendation models, CL operates by learning more uniform user/item representations that can implicitly mitigate the popularity bias. Meanwhile, we reveal that the graph augmentations, which used to be considered necessary, just play a trivial role. Based on this finding, we propose a simple CL method which discards the graph augmentations and instead adds uniform noises to the embedding space for creating contrastive views. A comprehensive experimental study on three benchmark datasets demonstrates that, though it appears strikingly simple, the proposed method can smoothly adjust the uniformity of learned representations and has distinct advantages over its graph augmentation-based counterparts in terms of recommendation accuracy and training efficiency. The code is released at https://github.com/Coder-Yu/QRec.

Being a fundamental graph operator, reachability query has been widely studied by the data mining community in the past decades. In a directed acyclic graph (DAG), one vertex is reachable by another if there exists a chain of directed edges connecting the two vertexes. The state-of-the-art (SOTA) reachability query methods mostly first index all the vertexes in the underlying DAG and assign them with different labels, and then use these indexes and/or labels to efficiently filter out as many unreachable queries as possible. Thus, because a large portion of unreachable queries can be identified without evoking any tedious path-finding process, the overall time taken by a huge number of queries is much shortened with a tolerable compensation on the additional index and/or label preprocessing time and space. In this paper, we propose the Extreme Labeling Filter (ELF), which is a novel generic filter that can be applied to existing reachability query methods to additionally identify a large number of unreachable queries. Based on the analysis of the given DAG in a systematic and autonomous manner, ELF first determines whether to use predecessors or successors to label the vertexes. Based on such self-determined labels, ELF is then able to identify a large number of unreachable queries with a low time complexity of O(1). To evaluate the performance of ELF, we apply it on 4 reachability query methods (1 conventional and 3 SOTA, all designated for reachability query in DAGs) and conduct experiments on 17 datasets of different sizes. The experimental results show that by applying ELF, all methods significantly shorten the query time.

Due to the growing privacy concerns, decentralization emerges rapidly in personalized services, especially recommendation. Also, recent studies have shown that centralized models are vulnerable to poisoning attacks, compromising their integrity. In the context of recommender systems, a typical goal of such poisoning attacks is to promote the adversary's target items by interfering with the training dataset and/or process. Hence, a common practice is to subsume recommender systems under the decentralized federated learning paradigm, which enables all user devices to collaboratively learn a global recommender while retaining all the sensitive data locally. Without exposing the full knowledge of the recommender and entire dataset to end-users, such federated recommendation is widely regarded 'safe' towards poisoning attacks. In this paper, we present a systematic approach to backdooring federated recommender systems for targeted item promotion. The core tactic is to take advantage of the inherent popularity bias that commonly exists in data-driven recommenders. As popular items are more likely to appear in the recommendation list, our innovatively designed attack model enables the target item to have the characteristics of popular items in the embedding space. Then, by uploading carefully crafted gradients via a small number of malicious users during the model update, we can effectively increase the exposure rate of a target (unpopular) item in the resulted federated recommender. Evaluations on two real-world datasets show that 1) our attack model significantly boosts the exposure rate of the target item in a stealthy way, without harming the accuracy of the poisoned recommender; and 2) existing defenses are not effective enough, highlighting the need for new defenses against our local model poisoning attacks to federated recommender systems.

Question Generation (QG), as a challenging Natural Language Processing task, aims at generating questions based on given answers and context. Existing QG methods mainly focus on building or training models for specific QG datasets. These works are subject to two major limitations: (1) They are dedicated to specific QG formats (e.g., answer-extraction or multi-choice QG), therefore, if we want to address a new format of QG, a re-design of the QG model is required. (2) Optimal performance is only achieved on the dataset they were just trained on. As a result, we have to train and keep various QG models for different QG datasets, which is resource-intensive and ungeneralizable.

Chromosome is composed of many distinct chromatin domains, referred to variably as topological domains or topologically associating domains (TADs). The domains are stable across different cell types and highly conserved across species, thus these chromatin domains have been considered as the basic units of chromosome folding and regarded as an important secondary structure in chromosome organization. However, the identification of TAD boundaries is still a great challenge due to the high cost and low resolution of Hi-C data or experiments. In this study, we propose a novel ensemble learning framework, termed as StackTADB, for predicting the boundaries of TADs. StackTADB integrates four base classifiers including Random Forest, Logistic Regression, K-NearestNeighbor and Support Vector Machine. From the analysis of a series of examinations on the data set in the previous study, it is concluded that StackTADB has optimal performance in six metrics, AUC, Accuracy, MCC, Precision, Recall and F1 score, and it is superior to the existing methods. In addition, the comparison of the performance of multiple features shows that Kmers-based features play an essential role in predicting TADs boundaries of fruit flies, and we also apply the SHapley Additive exPlanations (SHAP) framework to interpret the predictions of StackTADB to identify the reason why Kmers-based features are vital. The experimental results show that the subsequences matching the BEAF-32 motif play a crucial role in predicting the boundaries of TADs. The source code is freely available at https://github.com/HaoWuLab-Bioinformatics/StackTADB and the webserver of StackTADB is freely available at http://hwtad.sdu.edu.cn:8002/StackTADB.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has spurred a boom in uncovering repurposable existing drugs. Drug repurposing is a strategy for identifying new uses for approved or investigational drugs that are outside the scope of the original medical indication. MOTIVATION: Current works of drug repurposing for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are mostly limited to only focusing on chemical medicines, analysis of single drug targeting single SARS-CoV-2 protein, one-size-fits-all strategy using the same treatment (same drug) for different infected stages of SARS-CoV-2. To dilute these issues, we initially set the research focusing on herbal medicines. We then proposed a heterogeneous graph embedding method to signaled candidate repurposing herbs for each SARS-CoV-2 protein, and employed the variational graph convolutional network approach to recommend the precision herb combinations as the potential candidate treatments against the specific infected stage. METHOD: We initially employed the virtual screening method to construct the 'Herb-Compound' and 'Compound-Protein' docking graph based on 480 herbal medicines, 12,735 associated chemical compounds and 24 SARS-CoV-2 proteins. Sequentially, the 'Herb-Compound-Protein' heterogeneous network was constructed by means of the metapath-based embedding approach. We then proposed the heterogeneous-information-network-based graph embedding method to generate the candidate ranking lists of herbs that target structural, nonstructural and accessory SARS-CoV-2 proteins, individually. To obtain precision synthetic effective treatments forvarious COVID-19 infected stages, we employed the variational graph convolutional network method to generate candidate herb combinations as the recommended therapeutic therapies. RESULTS: There were 24 ranking lists, each containing top-10 herbs, targeting 24 SARS-CoV-2 proteins correspondingly, and 20 herb combinations were generated as the candidate-specific treatment to target the four infected stages. The code and supplementary materials are freely available at https://github.com/fanyang-AI/TCM-COVID19.

Abstract Nowadays recording and sharing personal lives using mobile devices on the Internet is becoming increasingly popular, and successive POI recommendation is gaining growing attention from academia and industry. In mobile scenarios, multiple influencing factors including the diversity of user preferences, the changeability of user behavior and the dynamic of spatiotemporal context bring great challenges to the POI recommender system. In order to accurately capture both the stable and the contextual preferences of mobile users in dynamic contexts, we propose a fusion framework JANICP (Joint Attention Networks with Inherent and Contextual Preferences) for successive POI recommendation by jointly training an offline/nearline user inherent interest perception model and an online user contextual interest prediction model. The offline model is trained based on the global historical behavior data to achieve stable interest representation, while the online model is trained based on the instantly selected context-sensitive data to achieve dynamic interest perception. An attention aggregation and matching module is used to fully connect the two kinds of preference representations and generate the final POI recommendation. Extensive experiments were conducted on three real datasets and experimental results show that the proposed JANICP outperforms existing state-of-the-art methods.

We present a novel approach for estimating the proportional distributions of function types (i.e. functional distributions) in an urban area through learning semantics preserved embeddings of points-of-interest (POIs). Specifically, we represent POIs as low-dimensional vectors to capture (1) the spatial co-occurrence patterns of POIs and (2) the semantics conveyed by the POI hierarchical categories (i.e. categorical semantics). The proposed approach utilizes spatially explicit random walks in a POI network to learn spatial co-occurrence patterns, and a manifold learning algorithm to capture categorical semantics. The learned POI vector embeddings are then aggregated to generate regional embeddings with long short-term memory (LSTM) and attention mechanisms, to take account of the different levels of importance among the POIs in a region. Finally, a multilayer perceptron (MLP) maps regional embeddings to functional distributions. A case study in Xiamen Island, China implements and evaluates the proposed approach. The results indicate that our approach outperforms several competitive baseline models in all evaluation measures, and yields a relatively high consistency between the estimation and ground truth. In addition, a comprehensive error analysis unveils several intrinsic limitations of POI data for this task, e.g. ambiguous linkage between POIs and functions.

Dynamic vision sensors (event cameras) have recently been introduced to solve a number of different vision tasks such as object recognition, activities recognition, tracking, etc. Compared with the traditional RGB sensors, the event cameras have many unique advantages such as ultra low resources consumption, high temporal resolution and much larger dynamic range. However, these cameras only produce noisy and asynchronous events of intensity changes, i.e., event-streams rather than frames, where conventional computer vision algorithms can't be directly applied. In our opinion the key challenge for improving the performance of event cameras in vision tasks is finding the appropriate representations of the event-streams so that cutting-edge learning approaches can be applied to fully uncover the spatio-temporal information contained in the event-streams. In this paper, we focus on the event-based human gait identification task and investigate the possible representations of the event-streams when deep neural networks are applied as the classifier. We propose new event-based gait recognition approaches basing on two different representations of the event-stream, i.e., graph and image-like representations, and use graph-based convolutional network (GCN) and convolutional neural networks (CNN) respectively to recognize gait from the event-streams. The two approaches are termed as EV-Gait-3DGraph and EV-Gait-IMG. To evaluate the performance of the proposed approaches, we collect two event-based gait datasets, one from real-world experiments and the other by converting the publicly available RGB gait recognition benchmark CASIA-B. Extensive experiments show that EV-Gait-3DGraph achieves significantly higher recognition accuracy than other competing methods when sufficient training samples are available. However, EV-Gait-IMG converges more quickly than graph-based approaches while training and shows good accuracy with only few number of training samples (less than ten). So image-like presentation is preferable when the amount of training data is limited.

This paper proposes a novel three-dimensional (3D) mixed-bouncing based unmanned aerial vehicle (UAV) channel model with space-time-frequency (S-T-F) non-stationarity for sixth generation (6G) massive multiple-input-multiple-output (MIMO) millimeter wave (mmWave) wireless communication systems. In the proposed mixed-bouncing based model, the line-of-sight (LoS) transmission, single-bouncing transmission, and multi-bouncing transmission are simultaneously modeled. A new parameter, i.e., cluster density index, is defined and developed. The influence of communication scenarios, frequency, UAV’s height, and distance between transceivers on cluster density index is also analyzed. To capture the S-T-F non-stationarity, a mixed-bouncing based S-T-F non-stationary algorithm is developed based on the birth-death (BD) process and frequency-dependent factor for the first time. In the developed algorithm, the non-stationarity is captured from the perspectives of both single-clusters and twin-clusters. Meanwhile, the impact of UAV-related parameters, such as the UAV’s height and 3D moving velocity, on the non-stationary modeling is considered. Based on the simulation results, the impact of cluster density index on the important channel statistical properties, such as S-T-F correlation function (STF-CF) and Doppler power spectral density (PSD), is explored. Finally, the simulation results match well with the measurement and ray-tracing (RT)-based results, validating the accuracy of the proposed model.

Federated Learning (FL) bridges the gap between collaborative machine learning and preserving data privacy. To sustain the long-term operation of an FL ecosystem, it is important to attract high-quality data owners with appropriate incentive schemes. As an important building block of such incentive schemes, it is essential to fairly evaluate participants’ contribution to the performance of the final FL model without exposing their private data. Shapley Value (SV)–based techniques have been widely adopted to provide a fair evaluation of FL participant contributions. However, existing approaches incur significant computation costs, making them difficult to apply in practice. In this article, we propose the Guided Truncation Gradient Shapley (GTG-Shapley) approach to address this challenge. It reconstructs FL models from gradient updates for SV calculation instead of repeatedly training with different combinations of FL participants. In addition, we design a guided Monte Carlo sampling approach combined with within-round and between-round truncation to further reduce the number of model reconstructions and evaluations required. This is accomplished through extensive experiments under diverse realistic data distribution settings. The results demonstrate that GTG-Shapley can closely approximate actual Shapley values while significantly increasing computational efficiency compared with the state-of-the-art, especially under non-i.i.d. settings.

Clinical workflow of cardiac assessment on 2D echocardiography requires both accurate segmentation and quantification of the Left Ventricle (LV) from paired apical 4-chamber and 2-chamber. Moreover, uncertainty estimation is significant in clinically understanding the performance of a model. However, current research on 2D echocardiography ignores this vital task while joint segmentation with quantification, hence motivating the need for a unified optimization method. In this paper, we propose a multitask model with Task Relation Spatial co-Attention (referred as TRSA-Net) for joint segmentation, quantification, and uncertainty estimation on paired 2D echo. TRSA-Net achieves multitask joint learning by novelly exploring the spatial correlation between tasks. The task relation spatial co-attention learns the spatial mapping among task-specific features by non-local and co-excitation, which forcibly joints embedded spatial information in the segmentation and quantification. The Boundary-aware Structure Consistency (BSC) and Joint Indices Constraint (JIC) are integrated into the multitask learning optimization objective to guide the learning of segmentation and quantification paths. The BSC creatively promotes structural similarity of predictions, and JIC explores the internal relationship between three quantitative indices. We validate the efficacy of our TRSA-Net on the public CAMUS dataset. Extensive comparison and ablation experiments show that our approach can achieve competitive segmentation performance and highly accurate results on quantification.

Social recommender systems are expected to improve recommendation quality by incorporating social information when there is little user-item interaction data. However, recent reports from industry show that social recommender systems consistently fail in practice. According to the negative findings, the failure is attributed to: (1) A majority of users only have a very limited number of neighbors in social networks and can hardly benefit from social relations; (2) Social relations are noisy but they are indiscriminately used; (3) Social relations are assumed to be universally applicable to multiple scenarios while they are actually multi-faceted and show heterogeneous strengths in different scenarios. Most existing social recommendation models only consider the homophily in social networks and neglect these drawbacks. In this paper we propose a deep adversarial framework based on graph convolutional networks (GCN) to address these problems. Concretely, for (1) and (2), a GCN-based autoencoder is developed to augment the relation data by encoding high-order and complex connectivity patterns, and meanwhile is optimized subject to the constraint of reconstructing the social profile to guarantee the validity of the identified neighborhood. After obtaining enough purified social relations for each user, a GCN-based attentive social recommendation module is designed to address (3) by capturing the heterogeneous strengths of social relations. Finally, we adopt adversarial training to unify all the components by playing a Minimax game and ensure a coordinated effort to enhance recommendation performance. Extensive experiments on multiple open datasets demonstrate the superiority of our framework and the ablation study confirms the importance and effectiveness of each component.

Clinical pathways are standardized, evidence-based multidisciplinary management plans. Many countries propose their national clinical pathways to improve the quality of care, reduce variation in clinical practice, and increase the efficient use of healthcare resources. Nevertheless, clinical pathways are typically not prescriptive, and the patient’s care journey is an individual one, therefore how to handle the variances of clinical pathways is an important issue. Previous methods construct clinical pathway recommendation models either using national standard clinical pathways to obtain the guidance, or using real-world clinical datasets to obtain clinical experience. However, few research tries to use both of them. This will result in existing algorithms that cannot accurately recommend personalized clinical pathway. To overcome the above problems, we propose P ersonalized C linical P athway Rec ommendation(PCPRec). On the one hand, to obtain general clinical pathway recommendations, we built a novel module to pre-train the self-attention model based on the national standard clinical pathway. So that we can use it as a guide to enhance the accuracy of recommending personalized clinical pathway. On the other hand, we obtain the patient’s treatment history sequence from real-world clinical datasets, and use the self-attention model for training. The purpose is to learn from the experience of the relationship between clinical items to meet patient’s individual needs. Extensive experimental results show that the proposed model achieves the best results compared to state-of-art methods on benchmark datasets.

With the current raging spread of the COVID19, early forecasting of the future epidemic trend is of great significance to public health security. The COVID-19 is virulent and spreads widely. An outbreak in one region often triggers the spread of others, and regions with relatively close association would show a strong correlation in the spread of the epidemic. In the real world, many factors affect the spread of the outbreak between regions. These factors exist in the form of multimodal data, such as the time-series data of the epidemic, the geographic relationship, and the strength of social contacts between regions. However, most of the current work only uses historical epidemic data or single-modal geographic location data to forecast the spread of the epidemic, ignoring the correlation and complementarity in multi-modal data and its impact on the disease spread between regions. In this paper, we propose a Multimodal InformatioN fusion COVID-19 Epidemic forecasting model (MINE). It fuses inter-regional and intra-regional multi-modal information to capture the temporal and spatial relevance of the COVID-19 spread in different regions. Extensive experimental results show that the proposed method achieves the best results compared to state-of-art methods on benchmark datasets.

Hypergraphs have been becoming a popular choice to model complex, non-pairwise, and higher-order interactions for recommender systems. However, compared with traditional graph-based methods, the constructed hypergraphs are usually much sparser, which leads to a dilemma when balancing the benefits of hypergraphs and the modelling difficulty. Moreover, existing sequential hypergraph recommendation overlooks the temporal modelling among user relationships, which neglects rich social signals from the recommendation data. To tackle the above shortcomings of the existing hypergraph-based sequential recommendations, we propose a novel architecture named Hyperbolic Hypergraph representation learning method for Sequential Recommendation (H2SeqRec) with the pre-training phase. Specifically, we design three self-supervised tasks to obtain the pre-training item embeddings to feed or fuse into the following recommendation architecture (with two ways to use the pre-trained embeddings). In the recommendation phase, we learn multi-scale item embeddings via a hierarchical structure to capture multiple time-span information. To alleviate the negative impact of sparse hypergraphs, we utilize a hyperbolic space-based hypergraph convolutional neural network to learn the dynamic item embeddings. Also, we design an item enhancement module to capture dynamic social information at each timestamp to improve effectiveness. Extensive experiments are conducted on two real-world datasets to prove the effectiveness and high performance of the model.

Session-based recommendation targets next-item prediction by exploiting user behaviors within a short time period. Compared with other recommendation paradigms, session-based recommendation suffers more from the problem of data sparsity due to the very limited short-term interactions. Self-supervised learning, which can discover ground-truth samples from the raw data, holds vast potentials to tackle this problem. However, existing self-supervised recommendation models mainly rely on item/segment dropout to augment data, which are not fit for session-based recommendation because the dropout leads to sparser data, creating unserviceable self-supervision signals. In this paper, for informative session-based data augmentation, we combine self-supervised learning with co-training, and then develop a framework to enhance session-based recommendation. Technically, we first exploit the session-based graph to augment two views that exhibit the internal and external connectivities of sessions, and then we build two distinct graph encoders over the two views, which recursively leverage the different connectivity information to generate ground-truth samples to supervise each other by contrastive learning. In contrast to the dropout strategy, the proposed self-supervised graph co-training preserves the complete session information and fulfills genuine data augmentation. Extensive experiments on multiple benchmark datasets show that, session-based recommendation can be remarkably enhanced under the regime of self-supervised graph co-training, achieving the state-of-the-art performance.

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains open. In this paper, we propose a noise-resistant training technique for DML, which we name Probabilistic Ranking-based Instance Selection with Memory (PRISM). PRISM identifies noisy data in a minibatch using average similarity against image features extracted by several previous versions of the neural network. These features are stored in and retrieved from a memory bank. To alleviate the high computational cost brought by the memory bank, we introduce an acceleration method that replaces individual data points with the class centers. In extensive comparisons with 12 existing approaches under both synthetic and real-world label noise, PRISM demonstrates superior performance of up to 6.06% in Precision@1.

Crowdsourcing is a popular and relatively economic way to harness human intelligence to process computer-hard tasks. Due to diverse factors (i.e., task difficulty, worker capability, and incentives), the collected answers from various crowd workers are of different quality. Many approaches have been proposed to manage high quality answers and to reduce the budget by modelling tasks, workers, or both. However, most of the existing approaches implicitly assume that the capability of workers is fixed during the crowdsourcing process. But in practice, such capability can be improved by gradually completing easy to hard tasks, alike human beings’ intrinsic self-paced learning ability. In this paper, we investigate crowdsourcing with self-paced workers, whose capability can be gradually boosted as he/she scrutinises and completes easy to hard tasks. Our proposed SPCrowd (Self-Paced Crowd worker) first asks workers to complete a set of golden tasks with known annotations; provides feedback to assist workers with capturing the raw modes of tasks and to spark the self-paced learning, which in turn facilitates the estimation of workers’ quality and tasks’ difficulty. It then introduces a task difficulty model to quantify the difficulty of tasks and rank them from easy to hard, and a benefit maximization criterion for task assignment, which can dynamically monitor the quality of self-paced workers and assign the sorted tasks to capable workers. In this way, a worker can successfully complete hard tasks after he/she completes easier and related tasks. Experimental results on semi-simulated and real crowdsourcing projects show that SPCrowd can better control the quality and save the budget compared to competitive baselines.

Partial multi-label learning (PML) aims at learning a robust multi-label classifier by training on ambiguous data, where each sample is associated with a set of candidate labels, among which only a subset are valid labels. A basic premise of existing PML solutions is to obtain enough partial multi-label samples for inducing the classification model. However, when dealing with new tasks, we may only have a few PML samples for those tasks. Furthermore, existing few-shot learning approaches assume the support (training) samples are precisely labeled; as such, irrelevant labels in the candidate label set may seriously mislead the meta-learner and thus result in a compromised performance. How to achieve PML with limited few-shot support samples is an important and practical problem, but not yet well studied. In this paper, we propose an approach called FsPML (Few-shot PML) to tackle this problem. Specifically, FsPML first performs adaptive distance metric learning via an embedding network using both sample features and label semantics in the embedding space. Next it rectifies the positive and negative prototypes of each new label of the target task in the embedding space. An unseen example can then be classified via its distances to the positive and to the negative prototypes. Experimental results on widely-used multi-label datasets (MS COCO and NUS-WIDE) demonstrate that our FsPML outperforms competitive baselines across different settings, and it can quickly generalize to new tasks with fewer training samples.

Visual storyline generation is the problem of selecting and sequencing a set of visual materials (i.e. images and video clips) to produce a video to elicit certain cognitive or emotional responses from viewers. In this paper, we enhance the viewing experience of generated visual storylines with the Shot Composition, Selection and Plotting (ShotCSP) approach. Designed for generating promotional videos in ecommerce settings, ShotCSP considers three key film-making principles into the visual storyline generation pipeline: a) proximity-aware scene transition, b) sound logic flow, and c) graphic discontinuity. We propose two novel metrics to enhance viewing experience: 1) Semantic Distance, which measures how related a shot is to the product being promoted; and 2) Salient Region Ratio, which estimates attention to product details in a shot. Through large-scale user evaluation involving 1,748 pairwise comparisons against five state-of-the-art approaches, ShotCSP achieves significantly improved viewing experience. It is a promising approach to enable AI generated promotional videos to benefit e-commerce businesses.

Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of existing PLL solutions is that there are sufficient partial-label (PL) samples for training. However, it is more common than not to have just few PL samples at hand when dealing with new tasks. Furthermore, existing few-shot learning algorithms assume precise labels of the support set; as such, irrelevant labels may seriously mislead the meta-learner and thus lead to a compromised performance. How to enable PLL under a few-shot learning setting is an important problem, but not yet well studied. In this paper, we introduce an approach called FsPLL (Few-shot PLL). FsPLL first performs adaptive distance metric learning by an embedding network and rectifying prototypes on the tasks previously encountered. Next, it calculates the prototype of each class of a new task in the embedding network. An unseen example can then be classified via its distance to each prototype. Experimental results on widely-used few-shot datasets demonstrate that our FsPLL can achieve a superior performance than the state-of-the-art methods, and it needs fewer samples for quickly adapting to new tasks.

Hyperbolic space and hyperbolic embeddings are becoming a popular research field for recommender systems. However, it is not clear under what circumstances the hyperbolic space should be considered. To fill this gap, This paper provides theoretical analysis and empirical results on when and where to use hyperbolic space and hyperbolic embeddings in recommender systems. Specifically, we answer the questions that which type of models and datasets are more suited for hyperbolic space, as well as which latent size to choose. We evaluate our answers by comparing the performance of Euclidean space and hyperbolic space on different latent space models in both general item recommendation domain and social recommendation domain, with 6 widely used datasets and different latent sizes. Additionally, we propose a new metric learning based recommendation method called SCML and its hyperbolic version HSCML. We evaluate our conclusions regarding hyperbolic space on SCML and show the state-of-the-art performance of hyperbolic space by comparing HSCML with other baseline methods.

LAMMPS is one of the most popular Molecular Dynamic (MD) packages and is widely used in the field of physics, chemistry and materials simulation. Layered Materials Force Field (LMFF) is our expansion of the LAMMPS potential function based on the Tersoff potential and inter-layer potential (ILP) in LAMMPS. LMFF is designed to study layered materials such as graphene and boron hexanitride. It is universal and does not depend on any platform. We have also carried out a series of optimizations on LMFF and the optimization work is carried out on the new generation of Sunway supercomputer, called SWLMFF. Experiments show that our implementation is efficient, scalable and portable. When generic LMFF is ported to Intel Xeon Gold 6278C, 2X performance improvement is achieved. For the optimized SWLMFF, the overall performance improvement is nearly 200--330X compared to the original ILP and Tersoff potentials. And SWLMFF has good parallel efficiency of 95%-100% under weak scaling with 2.7 million atoms on a single process. The maximum atomic system simulated by SWLMFF is close to 231 atoms. And nanosecond simulations in one day can be realized.

In recent years, recommender systems play a pivotal role in helping users identify the most suitable items that satisfy personal preferences. As user-item interactions can be naturally modelled as graph-structured data, variants of graph convolutional networks (GCNs) have become a well-established building block in the latest recommenders. Due to the wide utilization of sensitive user profile data, existing recommendation paradigms are likely to expose users to the threat of privacy breach, and GCN-based recommenders are no exception. Apart from the leakage of raw user data, the fragility of current recommenders under inference attacks offers malicious attackers a backdoor to estimate users’ private attributes via their behavioral footprints and the recommendation results. However, little attention has been paid to developing recommender systems that can defend such attribute inference attacks, and existing works achieve attack resistance by either sacrificing considerable recommendation accuracy or only covering specific attack models or protected information. In our paper, we propose GERAI, a novel differentially private graph convolutional network to address such limitations. Specifically, in GERAI, we bind the information perturbation mechanism in differential privacy with the recommendation capability of graph convolutional networks. Furthermore, based on local differential privacy and functional mechanism, we innovatively devise a dual-stage encryption paradigm to simultaneously enforce privacy guarantee on users’ sensitive features and the model optimization process. Extensive experiments show the superiority of GERAI in terms of its resistance to attribute inference attacks and recommendation effectiveness.

The prediction of peptide secondary structures is fundamentally important to reveal the functional mechanisms of peptides with potential applications as therapeutic molecules. In this study, we propose a multi-view deep learning method named Peptide Secondary Structure Prediction based on Multi-View Information, Restriction and Transfer learning (PSSP-MVIRT) for peptide secondary structure prediction. To sufficiently exploit discriminative information, we introduce a multi-view fusion strategy to integrate different information from multiple perspectives, including sequential information, evolutionary information and hidden state information, respectively, and generate a unified feature space. Moreover, we construct a hybrid network architecture of Convolutional Neural Network and Bi-directional Gated Recurrent Unit to extract global and local features of peptides. Furthermore, we utilize transfer learning to effectively alleviate the lack of training samples (peptides with experimentally validated structures). Comparative results on independent tests demonstrate that our proposed method significantly outperforms state-of-the-art methods. In particular, our method exhibits better performance at the segment level, suggesting the strong ability of our model in capturing local discriminative information. The case study also shows that our PSSP-MVIRT achieves promising and robust performance in the prediction of new peptide secondary structures. Importantly, we establish a webserver to implement the proposed method, which is currently accessible via http://server.malab.cn/PSSP-MVIRT. We expect it can be a useful tool for the researchers of interest, facilitating the wide use of our method.

MOTIVATION: N7-methylguanosine (m7G) is an important epigenetic modification, playing an essential role in gene expression regulation. Therefore, accurate identification of m7G modifications will facilitate revealing and in-depth understanding their potential functional mechanisms. Although high-throughput experimental methods are capable of precisely locating m7G sites, they are still cost ineffective. Therefore, it's necessary to develop new methods to identify m7G sites. RESULTS: In this work, by using the iterative feature representation algorithm, we developed a machine learning based method, namely m7G-IFL, to identify m7G sites. To demonstrate its superiority, m7G-IFL was evaluated and compared with existing predictors. The results demonstrate that our predictor outperforms existing predictors in terms of accuracy for identifying m7G sites. By analyzing and comparing the features used in the predictors, we found that the positive and negative samples in our feature space were more separated than in existing feature space. This result demonstrates that our features extracted more discriminative information via the iterative feature learning process, and thus contributed to the predictive performance improvement.

Origins of replication sites (ORIs), which refers to the initiative locations of genomic DNA replication, play essential roles in DNA replication process. Detection of ORIs' distribution in genome scale is one of key steps to in-depth understanding their regulation mechanisms. In this study, we presented a novel machine learning-based approach called Stack-ORI encompassing 10 cell-specific prediction models for identifying ORIs from four different eukaryotic species (Homo sapiens, Mus musculus, Drosophila melanogaster and Arabidopsis thaliana). For each cell-specific model, we employed 12 feature encoding schemes that cover nucleic acid composition, position-specific and physicochemical properties information. The optimal feature set was identified from each encoding individually and developed their respective baseline models using the eXtreme Gradient Boosting (XGBoost) classifier. Subsequently, the predicted scores of 12 baseline models are integrated as a novel feature vector to train XGBoost and develop the final model. Extensive experimental results show that Stack-ORI achieves significantly better performance as compared with their baseline models on both training and independent datasets. Interestingly, Stack-ORI consistently outperforms existing predictor in all cell-specific models, not only on training but also on independent test. Moreover, our novel approach provides necessary interpretations that help understanding model success by leveraging the powerful SHapley Additive exPlanation algorithm, thus underlining the most important feature encoding schemes significant for predicting cell-specific ORIs.

MOTIVATION: Anticancer peptides (ACPs) have recently emerged as effective anticancer drugs in cancer therapy. Machine learning-based predictors have been developed to identify ACPs and achieve satisfactory performance. However, existing methods suffer from experience-based feature engineering, which not only restricts the representation ability of the models to a certain extent but also lacks adaptivity for different data, limiting the further improvement of the predictive performance and impacting the robustness of the predictive models. To alleviate the above problems, we propose a novel deep-learning-based predictor named ACPred-LAF, in which we propose a novel multisense and multiscaled embedding algorithm to automatically learn and extract context sequential characteristics of ACPs. RESULTS: Through the feature comparative analysis, we demonstrate that our learnable and self-adaptive embedding features are better than hand-crafted features in capturing discriminative information, which can effectively benefit the performance improvement for ACP prediction. In addition, benchmarking comparison results demonstrate that our ACPred-LAF outperforms the state-of-the-art methods both on existing benchmark datasets and our newly constructed dataset. Furthermore, we also prove and validate the robustness of the model via the data interference experiment. To avoid potential evaluation bias, here, we construct a new ACP benchmark dataset named ACP-Mixed by integrating existing datasets. We expect our newly constructed dataset to be a golden standard benchmark dataset in this field. To facilitate the use of our model, we develop a web server as the implementation of ACPred-LAF. AVAILABILITY AND IMPLEMENTATION: Our proposed ACPred-LAF, newly constructed benchmark dataset ACP-Mixed are open source collaborative initiatives available in the GitHub repository (https://github.com/TearsWaiting/ACPred-LAF). Besides, a webserver as the implementation of ACPred-LAF that can be accessed via: http://server.malab.cn/ACPred-LAF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: DNA methylation plays an important role in epigenetic modification, the occurrence, and the development of diseases. Therefore, identification of DNA methylation sites is critical for better understanding and revealing their functional mechanisms. To date, several machine learning and deep learning methods have been developed for the prediction of different DNA methylation types. However, they still highly rely on manual features, which can largely limit the high-latent information extraction. Moreover, most of them are designed for one specific DNA methylation type, and therefore cannot predict multiple methylation sites in multiple species simultaneously. In this study, we propose iDNA-ABT, an advanced deep learning model that utilizes adaptive embedding based on Bidirectional Encoder Representations from Transformers (BERT) together with transductive information maximization (TIM). RESULTS: Benchmark results show that our proposed iDNA-ABT can automatically and adaptively learn the distinguishing features of biological sequences from multiple species, and thus perform significantly better than the state-of-the-art methods in predicting three different DNA methylation types. In addition, TIM loss is proven to be effective in dichotomous tasks via the comparison experiment. Furthermore, we verify that our features have strong adaptability and robustness to different species through comparison of adaptive embedding and six handcrafted feature encodings. Importantly, our model shows great generalization ability in different species, demonstrating that our model can adaptively capture the cross-species differences and improve the predictive performance. For the convenient use of our method, we further established an online webserver as the implementation of the proposed iDNA-ABT. AVAILABILITY AND IMPLEMENTATION: Our proposed iDNA-ABT and data are freely accessible via http://server.wei-group.net/iDNA_ABT and our source codes are available for downloading in the GitHub repository (https://github.com/YUYING07/iDNA_ABT). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Abstract Microtask crowdsourcing is a form of crowdsourcing in which work is decomposed into a set of small, self-contained tasks, which each can typically be completed in a matter of minutes. Due to the various capabilities and knowledge background of the voluntary participants on the Internet, the answers collected from the crowd are ambiguous and the final answer aggregation is challenging. In this process, the choice of quality control strategies is important for ensuring the quality of the crowdsourcing results. Previous work on answer estimation mainly used expectation–maximization (EM) approach. Unfortunately, EM provides local optimal solutions and the estimated results will be affected by the initial value. In this paper, we extend the local optimal result of EM and propose an approximate global optimal algorithm for answer aggregation of crowdsourcing microtasks with binary answers. Our algorithm is expected to improve the accuracy of real answer estimation through further likelihood maximization. First, three worker quality evaluation models are presented based on static and dynamic methods, respectively, and the local optimal results are obtained based on the maximum likelihood estimation method. Then, a dominance ordering model (DOM) is proposed according to the known worker responses and worker categories for the specified crowdsourcing task to reduce the space of potential task-response sequence while retaining the dominant sequence. Subsequently, a Cut-point neighbor detection algorithm is designed to iteratively search for the approximate global optimal estimation in a reduced space, which works on the proposed dominance ordering model (DOM). We conduct extensive experiments on both simulated and real-world datasets, and the experimental results illustrate that the proposed approach can obtain better estimation results and has higher performance than regular EM-based algorithms.

Emotion recognition has become an important component of human–computer interaction systems. Research on emotion recognition based on electroencephalogram (EEG) signals are mostly conducted by the analysis of all channels' EEG signals. Although some progresses are achieved, there are still several challenges such as high dimensions, correlation between different features and feature redundancy in the realistic experimental process. These challenges have hindered the applications of emotion recognition to portable human–computer interaction systems (or devices). This paper explores how to find out the most effective EEG features and channels for emotion recognition so as to only collect data as less as possible. First, discriminative features of EEG signals from different dimensionalities are extracted for emotion classification, including the first difference, multiscale permutation entropy, Higuchi fractal dimension, and discrete wavelet transform. Second, relief algorithm and floating generalized sequential backward selection algorithm are integrated as a novel channel selection method. Then, support vector machine is employed to classify the emotions for verifying the performance of the channel selection method and extracted features. At last, experimental results demonstrate that the optimal channel set, which are mostly located at the frontal, has extremely high similarity on the self-collected data set and the public data set and the average classification accuracy is achieved up to 91.31% with the selected 10-channel EEG signals. The findings are valuable for the practical EEG-based emotion recognition systems.

With the increasingly available electronic medical records (EMRs), disease prediction has recently gained immense research attention, where an accurate classifier needs to be trained to map the input prediction signals (e.g., symptoms, patient demographics, etc.) to the estimated diseases for each patient. However, existing machine learning-based solutions heavily rely on abundant manually labeled EMR training data to ensure satisfactory prediction results, impeding their performance in the existence of rare diseases that are subject to severe data scarcity. For each rare disease, the limited EMR data can hardly offer sufficient information for a model to correctly distinguish its identity from other diseases with similar clinical symptoms. Furthermore, most existing disease prediction approaches are based on the sequential EMRs collected for every patient and are unable to handle new patients without historical EMRs, reducing their real-life practicality. In this paper, we introduce an innovative model based on Graph Neural Networks (GNNs) for disease prediction, which utilizes external knowledge bases to augment the insufficient EMR data, and learns highly representative node embeddings for patients, diseases and symptoms from the medical concept graph and patient record graph respectively constructed from the medical knowledge base and EMRs. By aggregating information from directly connected neighbor nodes, the proposed neural graph encoder can effectively generate embeddings that capture knowledge from both data sources, and is able to inductively infer the embeddings for a new patient based on the symptoms reported in her/his EMRs to allow for accurate prediction on both general diseases and rare diseases. Extensive experiments on a real-world EMR dataset have demonstrated the state-of-the-art performance of our proposed model.

Obstructive Sleep Apnea (OSA) is a highly prevalent but inconspicuous disease that seriously jeopardizes the health of human beings. Polysomnography (PSG), the gold standard of detecting OSA, requires multiple specialized sensors for signal collection, hence patients have to physically visit hospitals and bear the costly treatment for a single detection. Recently, many single-sensor alternatives have been proposed to improve the cost efficiency and convenience. Among these methods, solutions based on RR-interval (i.e., the interval between two consecutive pulses) signals reach a satisfactory balance among comfort, portability and detection accuracy. In this paper, we advance RR-interval based OSA detection by considering its real-world practicality from energy perspectives. As photoplethysmogram (PPG) pulse sensors are commonly equipped on smart wrist-worn wearable devices (e.g., smart watches and wristbands), the energy efficiency of the detection model is crucial to fully support an overnight observation on patients. This creates challenges as the PPG sensors are unable to keep collecting continuous signals due to the limited battery capacity on smart wrist-worn devices. Therefore, we propose a novel Frequency Extraction Network (FENet), which can extract features from different frequency bands of the input RR-interval signals and generate continuous detection results with downsampled, discontinuous RR-interval signals. With the help of the one-to-multiple structure, FENet requires only one-third of the operation time of the PPG sensor, thus sharply cutting down the energy consumption and enabling overnight diagnosis. Experimental results on real OSA datasets reveal the state-of-the-art performance of FENet.

In this article, we propose, LeaD , a new vibration-based communication protocol to Lea rn the unique patterns of vibration to D ecode the short messages transmitted to smart IoT devices. Unlike the existing vibration-based communication protocols that decode the short messages symbol-wise, either in binary or multi-ary, the message recipient in LeaD receives vibration signals corresponding to bits-groups. Each group consists of multiple symbols sent in a burst and the receiver decodes the group of symbols as a whole via machine learning-based approach. The fundamental behind LeaD is different combinations of symbols (1 s or 0 s) in a group will produce unique and reproducible patterns of vibration. Therefore, decoding in vibration-based communication can be modeled as a pattern classification problem. We design and implement a number of different machine learning models as the core engine of the decoding algorithm of LeaD to learn and recognize the vibration patterns. Through the intensive evaluations on large amount of datasets collected, the Convolutional Neural Network (CNN)-based model achieves the highest accuracy of decoding (i.e., lowest error rate), which is up to 97% at relatively high bits rate of 40 bits/s. While its competing vibration-based communication protocols can only achieve transmission rate of 10 bits/s and 20 bits/s with similar decoding accuracy. Furthermore, we evaluate its performance under different challenging practical settings and the results show that LeaD with CNN engine is robust to poses, distances (within valid range), and types of devices, therefore, a CNN model can be generally trained beforehand and widely applicable for different IoT devices under different circumstances. Finally, we implement LeaD on both off-the-shelf smartphone and smart watch to measure the detailed resources consumption on smart devices. The computation time and energy consumption of its different components show that LeaD is lightweight and can run in situ on low-cost smart IoT devices, e.g., smartwatches, without accumulated delay and introduces only marginal system overhead.

Hospital readmission prediction employs reliable predictive models to evaluate the readmission risk of patients upon discharge. Identifying patients with high readmission risk and paying additional attention to them can ease the burden on both patients and society. Recently, considerable attention has been paid to personalized readmission predictions, i.e., building an independent model for each target patient. However, existing personalized predictive models can be easily affected by data insufficiency and provide poor generalization capabilities. To address these challenges, in this paper, we propose the CLusterbased mUlti-task lEarning model (CLUE) to achieve personalized hospital readmission prediction. CLUE groups patients into different clusters based on a multi-angle similarity metric to preserve the interrelated information of patients with highly similar clinical behaviors. Due to different group characteristics of patients, the clusters of patients are imbalanced. Given that, CLUE treats the hospital readmission prediction for each cluster of patients as one task and learns multiple tasks jointly by parameter sharing mechanisms. In this way, not only can the data insufficiency problem be alleviated by supplementing individual models with the shared information from other clusters, but also the specific information of each cluster can be preserved for personalization. We conduct extensive experiments on a real-world dataset of electronic health records, and show that CLUE significantly outperforms competitive comparative methods.

Detecting epistasis between single nucleotide poly-morphisms (SNPs) is crucial to explain the missing heritability of complex diseases in genome-wide association studies (GWAS). Many methods have been proposed for detecting SNP interactions, most of them only focus on reducing search space but ignore the relations of SNP with other bio-molecules. In this paper, we proposed a heterogeneous molecular network based method called EpiNet to detect high-order SNP interactions. EpiNet firstly uses samples (case/control) data to construct an SNP statistical network to capture the SNP distribution information in samples. In addition, EpiNet applies meta-path based similarity search in a heterogeneous molecular network composed with SNPs, genes, lncRNAs, miRNAs and diseases to construct an SNP relational network, which mines diverse associations between molecules and diseases to supplement the SNP statistical network and search the most associated SNPs. Next, EpiNet combines the two networks to get a composite SNP network, utilizes modularity based clustering to group all SNPs into different clusters and finally detects SNP interactions within each cluster. Simulation experiments on two-locus and three-locus disease models show that EpiNet has a better performance than competitive methods, even without the heterogeneous network. It also shows expressive power to identify high-order SNP interactions from real WTCCC breast cancer data.

Software resource allocation has a significant impact on the quality of service and the performance of multi-tier web systems. It poses a great challenge to compute the allocation of different software resources in order to meet performance requirements under dynamic workloads conditions. To this end, this paper proposes an iterative feedback mechanism to optimize software resource allocation of multi-tier web systems. Specifically, we propose a Q-learning network-based approach for performance prediction. The predictor involves a deep Q-learning network for capturing the dynamics of online software resource allocation, and then computing the current optimal policy. We implement the approach in the RUBiS benchmark system, and the experimental results demonstrate its significant advantages.

Commonsense knowledge is critical in human reading comprehension. While machine comprehension has made significant progress in recent years, the ability in handling commonsense knowledge remains limited. Synonyms are one of the most widely used commonsense knowledge. Constructing adversarial dataset is an important approach to find weak points of machine comprehension models and support the design of solutions. To investigate machine comprehension models' ability in handling the commonsense knowledge, we created a Question and Answer Dataset with common knowledge of Synonyms (QADS). QADS are questions generated based on SQuAD 2.0 by applying commonsense knowledge of synonyms. The synonyms are extracted from WordNet. Words often have multiple meanings and synonyms. We used an enhanced lesk algorithm to perform word sense disambiguation to identify synonyms for the context. ELECTRA achieves the state-of-art result on the SQuAD 2.0 dataset in 2019. With about 1/10 scale, ELECTRA can achieve similar performance as BERT does. However, QADS shows that ELECTRA has little ability to handle commonsense knowledge of synonyms. In our experiment, ELECTRA-small can achieve 70% accuracy on SQuAD 2.0, but only 20% on QADS. ELECTRA-large did not perform much better. Its accuracy on SQuAD 2.0 is 88% but dropped significantly to 26% on QADS. In our earlier experiments, BERT, although also failed badly on QADS, was not as bad as ELECTRA. The result shows that even top-performing NLP models have little ability to handle commonsense knowledge which is essential in reading comprehension.

Group Recommendation (GR) is the task of suggesting relevant items/events for a group of users in online systems, whose major challenge is to aggregate the preferences of group members to infer the decision of a group. Prior group recommendation methods applied predefined static strategies for preference aggregation. However, these static strategies are insufficient to model the complicated decision making process of a group, especially for occasional groups which are formed adhoc. Compared to conventional individual recommendation task, GR is rather dynamic and each group member may contribute differently to the final group decision. Recent works argue that group members should have non-uniform weights in forming the decision of a group, and try to utilize a standard attention mechanism to aggregate the preferences of group members, but they do not model the interaction behavior among group members, and the decision making process is largely unexplored.In this work, we study GR in a more general scenario, that is Occasional Group Recommendation (OGR), and focus on solving the preference aggregation problem and the data sparsity issue of group-item interactions. Instead of exploring new heuristic or vanilla attention-based mechanism, we propose a new social self-attention based aggregation strategy by directly modeling the interactions among group members, namely Group Self-Attention (GroupSA). In GroupSA, we treat the group decision making process as multiple voting processes, and develop a stacked social self-attention network to simulate how a group consensus is reached. To overcome the data sparsity issue, we resort to the relatively abundant user-item and user-user interaction data, and enhance the representation of users by two types of aggregation methods. In the training process, we further propose a joint training method to learn the user/item embeddings in the group-item recommendation task and the user-item recommendation task simultaneously. Finally, we conduct extensive experiments on two real-world datasets. The experimental results demonstrate the superiority of our proposed GroupSA method compared to several state-of-the-art methods in terms of HR and NDCG.

In micro-task crowdsourcing, the answers collected from the crowd are ambiguous and the final answer aggregation is challenging due to the various capabilities and knowledge background of the voluntary participants on the Internet. In this paper, we extend the local optimal result of Expectation-Maximization(EM) approach and propose an approximate global optimal algorithm for answer aggregation of crowdsourcing microtasks with binary answers. Our algorithm is expected to improve the accuracy of real answer estimation through further likelihood maximization. We conduct extensive experiments on both simulated and real-world datasets, and the experimental results illustrate that the proposed approach can obtain better estimation results and has higher performance than regular EM-based algorithms.

Video editing is currently a highly skill- and time-intensive process. One of the most important tasks in video editing is to compose the visual storyline. This paper outlines Visual Storyline Generator (VSG), an artificial intelligence (AI)-empowered system that automatically generates visual storylines based on a set of images and video footages provided by the user. It is designed to produce engaging and persuasive promotional videos with an easy-to-use interface. In addition, users can be involved in refining the AI-generated visual storylines. The editing results can be used as training data to further improve the AI algorithms in VSG.

Cross-domain recommendation methods usually transfer knowledge across different domains implicitly, by sharing model parameters or learning parameter mappings in the latent space. Differing from previous studies, this paper focuses on learning explicit mapping between a user's behaviors (i.e. interaction itemsets) in different domains during the same temporal period. In this paper, we propose a novel deep cross-domain recommendation model, called Cycle Generation Networks (CGN). Specifically, CGN employs two generators to construct the dual-direction personalized itemset mapping between a user's behaviors in two different domains over time. The generators are learned by optimizing the distance between the generated itemset and the real interacted itemset, as well as the cycle-consistent loss defined based on the dual-direction generation procedure. We have performed extensive experiments on real datasets to demonstrate the effectiveness of the proposed model, comparing with existing single-domain and cross-domain recommendation methods.

Nowadays, with the rapid growth of microblogging networks for news propagation, there are increasingly more people accessing news through such emerging social media. In the meantime, fake news now spreads at a faster pace and affects a larger population than ever before. Compared with traditional text news, the news posted on microblog often has attached images in the context. So how to correctly and autonomously detect fakes news in a multi-modal manner becomes a prominent challenge to be addressed. In this paper, we propose an end-to-end model, named BERT-based domain adaptation neural network for multi-modal fake news detection (BDANN). BDANN comprises three main modules: a multi-modal feature extractor, a domain classifier and a fake news detector. Specifically, the multi-modal feature extractor employs the pretrained BERT model to extract text features and the pretrained VGG-19 model to extract image features. The extracted features are then concatenated and fed to the detector to distinguish fake news. The role of the domain classifier is mainly to map the multi-modal features of different events to the same feature space. To assess the performance of BDANN, we conduct extensive experiments on two multimedia datasets: Twitter and Weibo. The experimental results show that BDANN outperforms the state-of-the-art models. Moreover, we further discuss the existence of noisy images in the Weibo dataset that may affect the results.

In recent years, recommender system has become an indispensable function in all e-commerce platforms. The review rating data for a recommender system typically comes from open platforms, which may attract a group of malicious users to deliberately insert fake feedback in an attempt to bias the recommender system to their favour. The presence of such attacks may violate modeling assumptions that high-quality data is always available and these data truly reflect users' interests and preferences. Therefore, it is of great practical significance to construct a robust recommender system that is able to generate stable recommendations even in the presence of shilling attacks. In this paper, we propose GraphRfi - a GCN-based user representation learning framework to perform robust recommendation and fraudster detection in a unified way. In its end-to-end learning process, the probability of a user being identified as a fraudster in the fraudster detection component automatically determines the contribution of this user's rating data in the recommendation component; while the prediction error outputted in the recommendation component acts as an important feature in the fraudster detection component. Thus, these two components can mutually enhance each other. Extensive experiments have been conducted and the experimental results show the superiority of our GraphRfi in the two tasks - robust rating prediction and fraudster detection. Furthermore, the proposed GraphRfi is validated to be more robust to the various types of shilling attacks over the state-of-the-art recommender systems.

As considerable amounts of POI check-in data have been accumulated, successive point-of-interest (POI) recommendation is increasingly popular. Existing successive POI recommendation methods only predict where user will go next, ignoring when this behavior will occur. In this work, we focus on predicting POIs that will be visited by users in the next 24 hours. As check-in data is very sparse, it is challenging to accurately capture user preferences in temporal patterns. To this end, we propose a category-aware deep model CatDM that incorporates POI category and geographical influence to reduce search space to overcome data sparsity. We design two deep encoders based on LSTM to model the time series data. The first encoder captures user preferences in POI categories, whereas the second exploits user preferences in POIs. Considering clock influence in the second encoder, we divide each user’s check-in history into several different time windows and develop a personalized attention mechanism for each window to facilitate CatDM to exploit temporal patterns. Moreover, to sort the candidate set, we consider four specific dependencies: user-POI, user-category, POI-time and POI-user current preferences. Extensive experiments are conducted on two large real datasets. The experimental results demonstrate that our CatDM outperforms the state-of-the-art models for successive POI recommendation on sparse check-in data.

Summary In the mobile computing environment, how to make the data access more efficient is a challenge due to the narrow communication bandwidth, the frequent disconnections of network, and the limited resources. Therefore, it is necessary to cache data on the client side. Besides, a good cache consistency method is essential to ensure the correctness. In this article, a row‐based semantic cache with incremental versioning consistency (RSCVC) is proposed. In RSCVC, we designed a semantic cache algorithm, a query trimming and optimizing algorithm, and a version‐based consistency strategy. This RSCVC cache mainly has two advantages. On one hand, it can obviously improve the response time of query and the hit ratio of the cache. On the other hand, the version‐based consistency enhances the stability of the system especially in high‐concurrency situations. Experiments demonstrate the efficacy of our proposed method and its superiority to state‐of‐the‐art methods.

Since ancient Greece, handshaking has been commonly practiced between two people as a friendly gesture to express trust and respect, or form a mutual agreement. In this article, we show that such physical contact can be used to bootstrap secure cyber contact between the smart devices worn by users. The key observation is that during handshaking, although belonged to two different users, the two hands involved in the shaking events are often rigidly connected, and therefore exhibit very similar motion patterns. We propose a novel key generation system, which harvests motion data during user handshaking from the wrist-worn smart devices such as smartwatches or fitness bands, and exploits the matching motion patterns to generate symmetric keys on both parties. The generated keys can be then used to establish a secure communication channel for exchanging data between devices. This provides a much more natural and user-friendly alternative for many applications, e.g., exchanging/sharing contact details, friending on social networks, or even making payments, since it doesn’t involve extra bespoke hardware, nor require the users to perform pre-defined gestures. We implement the proposed key generation system on off-the-shelf smartwatches, and extensive evaluation shows that it can reliably generate 128-bit symmetric keys just after around 1s of handshaking (with success rate >99%), and is resilient to different types of attacks including impersonate mimicking attacks, impersonate passive attacks, or eavesdropping attacks. Specifically, for real-time impersonate mimicking attacks, in our experiments, the Equal Error Rate (EER) is only 1.6% on average. We also show that the proposed key generation system can be extremely lightweight and is able to run in-situ on the resource-constrained smartwatches without incurring excessive resource consumption.

In artificial intelligence (AI) mediated workforce management systems (e.g., crowdsourcing), long-term success depends on workers accomplishing tasks productively and resting well. This dual objective can be summarized by the concept of productive laziness. Existing scheduling approaches mostly focus on efficiency but overlook worker wellbeing through proper rest. In order to enable workforce management systems to follow the IEEE Ethically Aligned Design guidelines to prioritize worker wellbeing, we propose a distributed Computational Productive Laziness (CPL) approach in this paper. It intelligently recommends personalized work-rest schedules based on local data concerning a worker's capabilities and situational factors to incorporate opportunistic resting and achieve superlinear collective productivity without the need for explicit coordination messages. Extensive experiments based on a real-world dataset of over 5,000 workers demonstrate that CPL enables workers to spend 70% of the effort to complete 90% of the tasks on average, providing more ethically aligned scheduling than existing approaches.

Abnormal co-occurrence medical visit behavior refers to the fraudulent behavior of fraudsters who hold multiple medical insurance cards and frequently purchase medicines within the same time period at the same location to defraud insurance medical insurance fund. Identifying abnormal co-occurrence medical visit behaviors plays a critical role in automated medical insurance fraud detection. However, the conventional methods mainly focus on the mining of frequent patterns, which may lead to misjudgement of normal patients who regularly seek medical treatment for a long time. In order to address this problem, we propose a novel biclustering algorithm, which finds suspicious patient groups who frequent purchased medicines within the same time period at the same location, and filters out normal patients from suspicious patients. Experimental results show that Biclutering-sim outperforms the competitor in detecting medical insurance fraud.

The information of the real world is stored as triplets (head entity, relation, tail entity) in knowledge graphs. They are extremely useful resources for many intelligent applications but suffer from incompleteness. This paper proposes a knowledge graph representation model to infer latent privacy based on the existing data in attribute network. In our model, considering the nodes are heterogeneous, we classify the nodes into attribute nodes and entity nodes. In order to protect the privacy of entities, we don't follow the previous methods to learn and store the feature embedding of each entity in knowledge graph. Our model focuses in capturing the restriction patterns of attribute nodes, which is safe when merging data from various sources. Given a triplet (entity node, relation, attribute node), firstly, we get the embedding of the entity node by using a sophisticated way to utilize all the information of the node, not only the node connections but also the external text information. Then, we infer the attribute node for the entity node in a certain relation. Finally, we calculate the probability that the triplet is exist. In experiments, we evaluate our model on the tasks of triplet classification and link prediction. Evaluation results show that our approach outperforms the state-of-the-art methods with an accuracy rate of 90.0% in the task of triplet classification on the person attribute knowledge graph FB13. Besides, our model reaches promising performance by MeanRank =5.10, Hits@l = 35.14% and Hits@5=64.94% in the task of conference prediction on the academic network DBLP.

Video contents have become a critical tool for promoting products in E-commerce. However, the lack of automatic promotional video generation solutions makes large-scale video-based promotion campaigns infeasible. The first step of automatically producing promotional videos is to generate visual storylines, which is to select the building block footage and place them in an appropriate order. This task is related to the subjective viewing experience. It is hitherto performed by human experts and thus, hard to scale. To address this problem, we propose WundtBackpack, an algorithmic approach to generate storylines based on available visual materials, which can be video clips or images. It consists of two main parts, 1) the Learnable Wundt Curve to evaluate the perceived persuasiveness based on the stimulus intensity of a sequence of visual materials, which only requires a small volume of data to train; and 2) a clustering-based backpacking algorithm to generate persuasive sequences of visual materials while considering video length constraints. In this way, the proposed approach provides a dynamic structure to empower artificial intelligence (AI) to organize video footage in order to construct a sequence of visual stimuli with persuasive power. Extensive real-world experiments show that our approach achieves close to 10% higher perceived persuasiveness scores by human testers, and 12.5% higher expected revenue compared to the best performing state-of-the-art approach.

The increasing momentum of service-oriented architecture has led to the emergence of divergent delivered services, where service selection is meritedly required to obtain the target service fulfilling the requirements from both users and service providers. Despite many existing works have extensively handled the issue of service selection, it remains an open question in the case where requests from multiple users are performed simultaneously by a certain set of shared candidate services. Meanwhile, there exist some constraints enforced on the context of service selection, e.g. service placement location and contracts between users and service providers. In this paper, we focus on the QoS-aware service selection with constraints from a fairness aspect, with the objective of achieving max-min fairness across multiple service requests sharing candidate service sets. To be more specific, we formulate this problem as a lexicographical maximization problem, which is far from trivial to deal with practically due to its inherently multi-objective and discrete nature. A fairness-aware algorithm for concurrent service selection (FASS) is proposed, whose basic idea is to iteratively solve the single-objective subproblems by transforming them into linear programming problems. Experimental results based on real-world datasets also validate the effectiveness and practicality of our proposed approach.

Crowdsourcing emerges as a promising means of solution generation, which creates tremendous value by leveraging the intelligence of crowds in the web services. With the rise of the business of crowdsourcing services, both crowdsourcers and workers expect to gain better Quality of Experience, as well as more profits. But there is a contradiction between the incentives of the crowdsourcer and the quality of result of the crowds. In order to balance this conflict, the paper develops a profit optimization model for all parties in crowdsourcing by employing Tullock Contests. The model consists of two parts. Firstly, optimized incentives are provided by crowdsourcer to encourage workers to achieve a better quality of result. Secondly, an optimal fee schedule is provided as guidance to workers. The visualization of the equilibria of benefits is helpful to reach a win-win situation for crowdsourcer and crowds, which in turn impacts the development of crowdsourcing services. In addition, we simulate the acquisition of Nash-equilibrium as a repeated crowdsourcing task. The effectiveness of our model is testified by the experimental results.

In order to provide high-quality services, wireless network providers deploy a large number of base stations per unit area and maintain these base stations operating over a long period of time invariably. This situation resulted in tremendous energy waste and economic cost to service providers. Owing to the conflict between energy consumption and economic benefits, simply reducing energy consumption may cut the profits of network providers. In order to effectively balance the Quality-of-Service (QoS), energy consumption, and profits of wireless networks, we propose a new sleeping scheme for base stations by using Tullock Contest. In the proposed game-theoretical framework, each player is a base station which competes for service revenue by providing services while consuming energy. The stations are classified into two categories, running mode and sleeping mode. The eventual sleeping strategy can be obtained by applying Nash equilibrium. The proposed scheme adjusts the number of sleeping stations to balance the energy consumption and profits of wireless network providers with the premise of ensuring user QoS. The performance of the proposed scheme is evaluated and compared under different system configurations and user traffic patterns.

Collaborative filtering (CF) has become one of the most popular and widely used methods in recommender systems, but its performance degrades sharply for users with rare interaction data. Most existing hybrid CF methods try to incorporate side information such as review texts to alleviate the data sparsity problem. However, the process of exploiting and integrating side information is computationally expensive. Existing hybrid recommendation methods treat each user equally and ignore that the pure CF methods have already achieved both effective and efficient recommendation performance for active users with sufficient interaction records and the little improvement brought by side information to these active users is ignorable. Therefore, they are not cost-effective solutions. One cost-effective idea to bypass this dilemma is to generate sufficient "real" interaction data for the inactive users with the help of side information, and then a pure CF method could be performed on this augmented dataset effectively. However, there are three major challenges to implement this idea. Firstly, how to ensure the correctness of the generated interaction data. Secondly, how to combine the data augmentation process and recommendation process into a unified model and train the model end-to-end. Thirdly, how to make the solution generalizable for various side information and recommendation tasks. In light of these challenges, we propose a generic and effective CF model called AugCF that supports a wide variety of recommendation tasks. AugCF is based on Conditional Generative Adversarial Nets that additionally consider the class (like or dislike) as a feature to generate new interaction data, which can be a sufficiently real augmentation to the original dataset. Also, AugCF adopts a novel discriminator loss and Gumbel-Softmax approximation to enable end-to-end training. Finally, extensive experiments are conducted on two large-scale recommendation datasets, and the experimental results show the superiority of our proposed model.

This paper presents a mixed reality storytelling system, which takes handicrafts as tangible interaction tools. Via the system, users can learn handicraft and then use the handicraft pieces to design, create and tell stories with HoloLens iteratively. In order to overcome the limitations of HoloLens gesture interaction, the system uses hand tracking with Kinect to implement a touch-like effect on the desktop. User study shows that our system has good usability, and it is welcomed by users. In addition, it can stimulate users interest in handicraft and storytelling, and even promote parent-child interaction effectively.

With the explosive growth of multimedia applications, heterogeneous cellular networks (HetNets) are widely deployed to meet the increasingly impressing demands on communication capacity. However, supporting the massive real-time traffic generated by always-on multimedia applications in HetNets causes enormous energy consumptions. The tradeoff between energy consumptions and profits of service providers while maintaining satisfied quality-of-service (QoS) has become a significant objective. To this end, this paper proposes a novel framework of power rationing in HetNets to achieve maximal profit and guaranteed service performance. A dynamic power rationing strategy that employs Tullock contest is developed to model the power control of multiple cells into a game and solve the contradiction of profits and energy consumption as the tradeoff between QoS and cost. Two principal challenges in gaming, incomplete information, and the curse of dimensionality are resolved by the designed virtual repeated game that adopts the Monte-Carlo method and particle swarm optimization (PSO) to obtain the Nash equilibrium. The equilibrium of power rationing balances the energy consumptions and profits of cells, which ensures the optimal solution for the multimedia service providers and HetNets operators. The experimental results demonstrate that the developed model can serve as an efficient tool for power rationing in multimedia HetNets.

The users of Twitter-like social media normally use the "@'' sign to select a suitable person to mention. It is a significant role in promoting the user experience and information propagation. To help users easily find the usernames they want to mention, the mention recommendation task has received considerable attention in recent years. Previous methods only incorporated textual information when performing this task. However, many users not only post texts on social media but also the corresponding images. These images can provide additional information that is not included in the text, which could be helpful in improving the accuracy of a mention recommendation. To make full use of textual and visual information, we propose a novel cross-attention memory network to perform the mention recommendation task for multimodal tweets. We incorporate the interests of users with external memory and use the cross-attention mechanism to extract both textual and visual information. Experimental results on a dataset collected from Twitter demonstrated that the proposed method can achieve better performance than state-of-the-art methods that use textual information only.

Computing $$k\text {-}core$$ s is a fundamental and important graph problem, which can be applied in many areas, such as community detection, network visualization, and network topology analysis. Due to the complex relationship between different entities, dual graph widely exists in the applications. A dual graph contains a physical graph and a conceptual graph, both of which have the same vertex set. Given that there exist no previous studies on the $$k\text {-}core$$ in dual graphs, we formulate a k-connected core ( $$k\text {-}CCO$$ ) model in dual graphs. A $$k\text {-}CCO$$ is a $$k\text {-}core$$ in the conceptual graph, and also connected in the physical graph. Given a dual graph and an integer k, we propose a polynomial time algorithm for computing all $$k\text {-}CCO$$ s. We also propose three algorithms for computing all maximum-connected cores ( $$MCCO$$ ), which are the existing $$k\text {-}CCO$$ s such that a $$(k+1)$$ - $$CCO$$ does not exist. We further study a subgraph search problem, which is computing a $$k\text {-}CCO$$ that contains a set of query vertices. We propose an index-based approach to efficiently answer the query for any given parameter k. We conduct extensive experiments on six real-world datasets and four synthetic datasets. The experimental results demonstrate the effectiveness and efficiency of our proposed algorithms.

Smart traffic prediction system provides significant benefits in solving the city traffic congestion. However, existing smart transportation system needs a lot of real-time traffic data and accurate location information to display the traffic condition. We hope that we can use the data which is easy to be obtained, and then predict a reliable congestion time. To address this problem, this paper studied a smart traffic forecasting system based on SWARIMA model. The system includes three steps: 1) use the sliding windows to calculate and process real-time data stream; 2) establish the SWARIMA model and make regression analysis; and 3) from a statistical point of view, calculate the elastic interval and predict the congestion trend. Our system is capable of accepting the real-time traffic data stream for the congestion prediction, in addition, we reduce the actual running parameters to three attributes: 1) speed; 2) time; and 3) location information. When faced with the challenges of real-time traffic congestion, the system can timely and effectively calculate the congestion trends and provide three reliable elastic intervals: 1) warning; 2) congestion; and 3) mitigation, which has significance to improve traffic condition and alleviate urban road congestion.

Privacy issues have become a major concern in the web of resource sharing, and users often have difficulty managing their information disclosure in the context of high-quality experiences from social media and Internet of Things. Recent studies have shown that users’ disclosure decisions may be influenced by heuristics from the crowds, leading to inconsistency in the disclosure volumes and reduction of the prediction accuracy. Therefore, an analysis of why this influence occurs and how to optimize the user experience is highly important. We propose a novel heuristic model that defines the data structures of items and participants in social media, utilizes a modified decision-tree classifier that can predict participants’ disclosures, and puts forward a correlation analysis for detecting disclosure inconsistences. The heuristic model is applied to real-time dataset to evaluate the behavioral effects. Decision-tree classifier and correlation analysis indeed prove that some participants’ behaviors in information disclosures became decreasingly correlated during item requesting. Participants can be “persuaded” to change their disclosure behaviors, and the users’ answers to the mildly sensitive items tend to be more variable and less predictable. Using this approach, recommender systems in social media can thus know the users better and provide service with higher prediction accuracy.

The proliferation of cloud computing allows users to flexibly store, re-compute or transfer large generated datasets with multiple cloud service providers. However, due to the pay-as-you-go model, the total cost of using cloud services depends on the consumption of storage, computation and bandwidth resources which are three key factors for the cost of IaaS-based cloud resources. In order to reduce the total cost for data, given cloud service providers with different pricing models on their resources, users can flexibly choose a cloud service to store a generated dataset, or delete it and choose a cloud service to regenerate it whenever reused. However, finding the minimum cost is a complicated yet unsolved problem. In this paper, we propose a novel algorithm that can calculate the minimum cost for storing and regenerating datasets in clouds, i.e., whether datasets should be stored or deleted, and furthermore where to store or to regenerate whenever they are reused. This minimum cost also achieves the best trade-off among computation, storage and bandwidth costs in multiple clouds. Comprehensive analysis and rigid theorems guarantee the theoretical soundness of the paper, and general (random) simulations conducted with popular cloud service providers' pricing models demonstrate the excellent performance of our approach.

Cloud computing is a promising distributed computing platform for big data applications, e.g., scientific applications, since excessive resources can be obtained from cloud services for processing and storing both existing and generated application datasets. However, when tasks process big data stored in distributed data centers, the inevitable data movements will cause huge bandwidth cost and execution delay. In this paper, we construct a tripartite graph based model to formulate the data replica placement problem and propose a genetic algorithm based data replica placement strategy for scientific applications to reduce data transmissions in cloud. Our approach can reduce 1) the size of moved data, 2) the time of data movement and 3) the number of movements. We conduct experiments to compare the proposed strategy with the random placement strategy used in Hadoop Distributed Files System (HDFS), which demonstrates that our strategy has better performance for scientific applications in clouds.

For several reasons, the cloud computing paradigm, e.g., mobile edge computing (MEC), is suffering from the problem of privacy issues. MEC servers provide personalization services to mobile users for better QoE qualities, but the ongoing migrated data from the source edge server to the destination edge server cause users to have privacy concerns and unwillingness of self‐disclosure, which further leads to a sparsity problem. As a result, personalization services ignore valuable user profiles across edges where users have accounts in and tend to predict users’ potential purchases with insufficient sources, thereby limiting further improvement of QoE through personalization of the contents. This paper proposes a novel model, called CEPTM, which (1) collects mobile user data across multiple MEC edge servers, (2) improves the users’ experience in personalization services by loading collected diverse data, and (3) lowers their privacy concern with the improved personalization. This model also reveals that famous topics in one edge server can migrate into several other edge servers with users’ favorite content tags and that the diverse types of items could increase the possibility of users accepting the personalization service. In the experiment section, we use exploratory factor analysis to mathematically evaluate the correlations among those factors that influence users’ information disclosure in the MEC network, and the results indicate that CEPTM (1) achieves a high rate of personalization acceptance due to the availability of more data as input and highly diverse personalization as output and (2) gains the users’ trust because it collects user data while respecting individual privacy concerns and providing better personalization. It outperforms a traditional personalization service that runs on a single‐edge server. This paper provides new insights into MEC diverse personalization services and privacy problems, and researchers and personalization providers can apply this model to merge popular users’ like trends throughout the MEC edge servers and generate better data management strategies.

The rapidly increasing availability of healthcare data from multiple heterogeneous sources has spearheaded the adoption of data-driven approaches for improved clinical research, decision making, and patient management. The patient healthcare data are usually longitudinal and can be expressed as medical event sequences, where the events include clinical diagnosis, medications, laboratory reports, etc. Because healthcare data has both longitudinal and heterogeneous attributes, analyzing healthcare data is an inherently difficult challenge. In this paper, we propose a hospital readmission prediction method using temporal phenotypes, namely the Tephe. Specifically, each patient's medical event sequence is first represented by a temporal graph, which captures temporal relationships of the medical events in each event sequence and makes the raw data more intuitive. Based on graph pattern mining, we define more significant frequent subgraphs as temporal phenotypes. This enables us to better understand the disease evolving patterns and treatment approach. In addition, we designed an improved greedy algorithm to find the optimal expression coefficient of frequent subgraphs for each patient. Finally, based on the optimal expression coefficient of the frequent subgraph, random forests are used to perform prediction tasks. The experimental results show that our proposed method is more accurate in the prediction tasks compared with the baselines.

Today, Pareto-optimal objects finding has been applied in various fields, such as group decision making and opinion collection. Many of the existing solutions to this problem require explicit attributes for objects. However, these attributes cannot be obtained sometimes. To address this issue, we propose an algorithm, which uses preference relations given by crowdsourcing, to find Pareto-optimal objects with shorter latency and lower monetary costs. It employs two multi-pairwise-comparison question models: BEST-form and BETTER-form questions. Multiple BEST (or BETTER) questions can be sent to crowds concurrently. Extensive experimental results show that the number of questions reduces greatly. In addition, the numerical results show that the latency is significantly shortened at a reasonable monetary cost, compared with the existing methods.

In multi-tier cloud service systems, performance evaluation relies on numerous experiments in order to collect key metrics such as resources usage. The approach may result in highly time-consuming in practice. In this paper, we propose an automated framework for performance tracking, data management and analysis to minimize human intervention in multi-tier cloud service systems. The framework support fine-grained analysis of the mixed workloads through the Discrete-time Markov-modulated Poisson process (DMMPP). A general multi-tier application is theoretically formulated as a queueing network to evaluate the performance. The effectiveness of the model has been validated through extensive experiments conducted in the RUBiS benchmark system.

QoS aware service composition necessitates an effective pricing mechanism in regulating service providers in public cloud computing environments. However, due to the fact that service providers are usually autonomous, strategic and self-motivated, it is far from trivial to deal with the pricing issues between them. In this paper we formulate a non-cooperative service pricing game to understand the performance of a QoS aware service composition model, for which multiple providers strategically bid how to provide and price their elementary services and establish the Nash equilibrium as the final service composition scheme. We also develop a proportional revenue division rule to incentivize elementary service providers to contribute in improving the QoS of the final composite service delivered to end users. Concerning privacy conservation, we develop a decentralized and recursive bidding algorithm, allowing service providers to reach an equilibrium without disclosing their private information. Through theoretical analysis, we show that a Nash equilibrium exists in a QoS aware service composition game. Through extensive simulations, we show that the proposed recursive bidding process can converge quickly to a Nash equilibrium service composition scheme, and its efficiency is generally high.

Soft resource allocation is an important factor of system configuration which plays a critical role in guaranteeing the performance of multi-tier web service systems. There is a tradeoff between real-time performance and resource consumption, and thus the real-time adjustment of soft resource allocation in response to dynamic workload is quite challenging. In this paper, we propose a real-time soft resource allocation method that integrates both model-based analysis and real-time optimization. Specifically, a multi-tier web service system is firstly formulated by a queueing network model, and theoretical analyses are provided. Then, an optimization approach for real-time soft resource allocation is designed by applying sliding window techniques, in order to cope with dynamic workloads and performance demands. Based on the RUBiS benchmark system, model parameters are obtained by measurements and the efficacy of our approach is finally validated.

Software Defined Networking (SDN) is emerging as a new paradigm in which the control plane is decoupled from the data plane. SDN architectures enable the abstraction of network elements from the chaos of infrastructures to be service resources. The deployment of applications and network services can be largely simplified by taking advantage of the standardized open Application Program Interface (API). In the open literature, many efforts have been taken to evaluate the forwarding performance of the data plane. Jackson model is frequently employed to characterize the feature of such architectures. Further, network traffic frequently exhibits self-similar characteristic that has got a universal recognition. Analytical models without taking the traffic self-similarity into account may lead to unexpected results. To this end, this paper has proposed an analytical model to evaluate the Quality of Service (QoS) of SDN data plane with self-similar input traffic. Priority service is employed in data plane to decrease the sojourn time of the packets not matched. This is because packets traveled across the control plane are more sensitive to stringent delay bound. The QoS of the model can be evaluated by a decomposition approach. Extensive experimental results suggest that our model has a great accuracy and applicability.

In the case of a cloud-based remote control system such as SCADA (Supervisory Control and Data Acquisition) that enables users to collect data from cloud-connected machines deployed anywhere at any time. However, machine data models may not be updated in a timely manner after the devices are upgrades or modified. This leads to mismatches between the machine data and data models. A key obstacle of the matching is that the machines can be modified. To address this, we present a self-evolving method for machine data model. We give the description of the evolution of machine data models and the self-evolving method for the models in details. The method detects the conflicts between the machine data and models, and transfer or derive models if necessary. Our method can thus facilitate the evolution of machine data models and ensure that every machine in the cloud corresponds to the correct machine data model automatically. At last, we present two case studies to validate our method.

As many countries in the world start to experience population aging, there are an increasing number of people relying on medical insurance to access healthcare resources. Medical insurance frauds are causing billions of dollars in losses for public healthcare funds. The detection of medical insurance frauds is an important and difficult challenge for the artificial intelligence (AI) research community. This paper outlines HFDA, a hybrid AI approach to effectively and efficiently identify fraudulent medical insurance claims which has been tested in an online medical insurance claim system in China.

Soft resources, which are system software components that use hardware or synchronize the use of hardware, are playing a critical role in the performance of multi-tier web systems, and thus it is quite important to tune the soft resource allocation for using the limited hardware resources to obtain maximum effectiveness. In this paper, we integrate both theoretical and experimental studies to the soft resource allocation problem. Specifically, we apply the queueing network model for formulating multi-tier web systems, and conduct experimental measurements based on the RUBiS benchmark system to obtain precise model parameters. Quantitative analysis is carried out, based on which an optimization model as well as an algorithm are put forward for soft resource allocation. The efficacy of our approach is validated by both theoretical analyses and experimental results.

In cloud computing services, according to the customized privacy protection policy by the tenant and the sub chunk-confusion based on privacy protection technology, we can partition the tenant’s data into many chunks and confuse the relationships among chunks, which makes the attacker cannot infer tenant’s information by simply combining attributes. But it still has security issues. For example, with the amount of data growing, there may be a few hidden association rules among some attributes of the data chunks. Through these rules, it is possible to get some of the privacy information of the tenant. To address this issue, the paper proposes a privacy protection mechanism based on chunk-confusion privacy protection technology for association rules. The mechanism can detect unidimensional and multidimensional attributes association rules, hide them by adding fake data, re-chunking and re-grouping, and then ensure the privacy of tenant’s data. In addition, this mechanism also provides evaluation formulas. They filter detected association rules, remove the invalid and improve system performance. They also evaluate the effect of privacy protection. The experimental evaluation proves that the mechanism proposed in this paper can better protect the data privacy of tenant and has feasibility and practicality in real world applications.

The rapid growth of data makes it possible for us to study human behavior patterns. Knowing the patterns of human behavior is of great use to help us detect the unusual fraud human behavior. Existing fraud detection methods can be divided into two categories: pattern based and outlier detection based methods. However, because of the sparsity and complex granularity of big data, these methods have high false positive in fraud detection. In this paper, we propose an effective hybrid fraud detection method. We propose SSIsomap which improves isomap to cluster behaviors into behavior classes and propose SimLOF which improves LOF to conduct outlier detection, then we use Dempster-Shafer evidence Theory for combining behavior pattern evidence and outlier evidence, which yields a degree of belief of fraud to the new coming claim. The experiment result shows our method has significantly higher accuracy than exsiting methods in medical insurance fraud detection.

An enormous number of applications have been developed for Android in recent years, making it one of the most popular mobile operating systems. However, it is obvious that more vulnerabilities would appear along with the booming amounts of applications. Poorly designed applications may contain security vulnerabilities that can dramatically undermine users' security and privacy. In this paper, we studied a kind of recently reported application vulnerability named confused deputy - a specific type of privilege escalation vulnerability, which can result in unauthorized operations, and so on. We proposed a novel system with code-level static analysis to analyze the applications and automatically detect possible confused deputy vulnerabilities. To tackle analysis challenges imposed by Android's component-based programming paradigm, we employed special control flow graph construction techniques to build call relations among components and function call graph within components. We developed a prototype of this system named PaddyFrog and evaluated with 7190 real world Android applications from two of the most popular markets in China. We found 1240 applications with confused deputy vulnerability and proved to be exploitable. The median execution time of this system on an application is 14.4s, which is fast enough to be used in volumes of applications testing scenarios. Copyright © 2015 John Wiley & Sons, Ltd.

In an open e-commerce PaaS platform, there are many different kinds of applications, such as online stores, online payment systems and online logistics. For each of these application types, multiple applications are delivered by different ISVs and tenanted by e-commerce participants. Generally, there are frequent and extensive collaborations among the SaaS applications with multiple roles involved during trading processes. Such situations bring great challenges to traditional application interaction based on explicitly specified relationships and pre-defined interfaces, due to dynamic and uncertainty features of the collaborations among large number of potential applications. Current PaaS platform does not consider any mechanisms to support dynamic and uncertain collaborations among deployed SaaS applications at platform level. We propose an enhanced framework for e-commerce PaaS platform to support autonomous collaborations among deployed applications. Two software layers are constructed and incorporated into general PaaS platform, a collaboration-enabled layer and a component layer. In our framework, applications can be supported to collaborate with each other autonomously based on business goal and context. The framework also enables multiple roles perform corporative application development, deployment and utilization with higher efficiency and lower cost.

Mashup is becoming a powerful approach for end-users to meet their ad-hoc requirements based on existing services. Quite a few researches have been performed to achieve rapid, on-demand, intuitive development of mashups, which mainly focus on finding suitable quality components from a large number of available services. However, for mashups with procedure and context features, it is more crucial and difficult to construct an effective mashup structure, rather than selecting individual components. In this paper, we propose a context-based autonomous construction approach for procedural mashup based on pattern mining. In our approach, the mashup composition process is divided into 2 phases: schema construction phase and component binding phase. First, context-based mashup schemas with probability are extracted and recovered by applying pattern mining tasks to historical mashup logs. Then, according to user goal and awareness of user context, an optimal mashup schema is composed progressively by top-k recommendations for the next behavior/activity, which will be grounded to Web-API based components later. The proposed approach can autonomously generate context-based mashup schema with quality components and high probability of success without dependence on user professionalism.

Massive computation power and storage capacity of cloud computing systems allow scientists to deploy computation and data intensive applications without infrastructure investment, where large application data sets can be stored in the cloud. Based on the pay-as-you-go model, storage strategies and benchmarking approaches have been developed for cost-effectively storing large volume of generated application data sets in the cloud. However, they are either insufficiently cost-effective for the storage or impractical to be used at runtime. In this paper, toward achieving the minimum cost benchmark, we propose a novel highly cost-effective and practical storage strategy that can automatically decide whether a generated data set should be stored or not at runtime in the cloud. The main focus of this strategy is the local-optimization for the tradeoff between computation and storage, while secondarily also taking users' (optional) preferences on storage into consideration. Both theoretical analysis and simulations conducted on general (random) data sets as well as specific real world applications with Amazon's cost model show that the cost-effectiveness of our strategy is close to or even the same as the minimum cost benchmark, and the efficiency is very high for practical runtime utilization in the cloud.

Platform-as-a Service (PaaS) provides a new pattern of software design, development, testing, deployment and hosting for organizations such as ISV, business department and so on. When the PaaS platform brings together lots of software services from various organizations; it's a challenging work to construct dynamically and intelligently new application with these service resources to meet application request. This paper pays more attention on application cooperation, namely business service process cooperation due to business process is the main form of application, in PaaS Platform based on planning method. Our approach comprises the following steps: construct abstract business process for cooperation based on the hierarchical task network planning and semantic model of service cooperation; construct executable serviceflow based on candidate services and use graph planning to verify dataflow in executable serviceflow. This approach can ensures not only the semantic consistency between the business objectives and business process logic, but also the dataflow consistency in process. This approach can provide more available executable serviceflow for business cooperation of different organizations in PaaS Platform. The correctness and necessity of this approach are verified through experiments and some cases.

In order to support workflow-oriented application on multiple data centers, this paper describes a workflow-oriented cloud computing framework, called WfOC. WfOC can run workflow jobs composed of multiple user defined task-functions extracted by java annotation. This framework includes workflow-oriented cloud computing programming language, tasks extraction and composition, tasks and data sources registration, tasks functions mapper/reducer and other components, and enables users to especially focus on workflow definition and workflow tasks logic implementation without needing to worry about the distribution of data and target execution systems. A mechanism is offered in building workflow-oriented data intensive applications, with multiple heterogeneous java runtime environments as the underlying computation platform. A case in social security application on multiple databases shows this framework can streamline complex computational workflow.

Cross domain collaboration is now more and more universal in real world. This paper proposes a platform named SMART (Service Requirement-AwaRe Decentralized Services Computing Infrastructure) which supports decentralized collaboration of cross-domain organizations. The SMART can be deployed on any domain participant's center server, and make all the participants become peer-entities. All the domain participants can communication with each other directly through an overlay network which is constructed by the SMART. SMART helps users to discover any other domain participants, build cross domain business process dynamically and execute business process in a decentralized way. The paper also introduces the SMART system design and prototype implementation.

In the distributed cross-organization business process, each organization only knows its private orchestration and partial public choreography, It doesn't have any information about the global process. If one organization has to change, it is difficult to compute the impact imposed on other organizations. In this paper, we propose a method to get the global services dependency matrix automatically through analysing the orchestrations and choreography. Then we introduces the service impact analysis model based dependency matrix and intraservice and inter-service change propagation, through which we can ascertained the impact caused by the changes.

Software design and development process is essentially cooperative, and involves multiple groups. There are many specific requirements differing common cooperative works. In order to support such specific cooperative activity involved multiple groups, a multi-group cooperative organization-activity model is proposed. Based on this model, conflicts among the members of multi-groups can be automatically detected, and groups executing cooperative activities can be automatically generated. In practice, a workflow system supporting multi-group cooperative software design and development process based on above framework had been developed. The results show these technologies can avoid the task conflicts in multi-group cooperation while minimizing the cost in project tracking, and can reduce the repetitions in software interfaces design and development.

Virtual enterprise has been a topic of increasing interests in recent years meanwhile parts library sharing among participant enterprises has become a challenge. This paper analyzes its two demands. one is dynamic and open; the other is the share of domain knowledge. Based on these requirements, it proposes a framework for sharing parts library in virtual enterprise. The framework uses web service technologies to implement the first requirement and ontology technologies to achieve the second one. The analysis indicates that it can improve the flexibility and maintainability of the share of parts library among collaborating members and facilitate the rapid development of product to meet the market demands. At last, an example of parts library description in OWL is given.

The emerging semantic web service provides a promising way to address the challenge of building collaborative design system over heterogeneous resources. Efficient services discovery method is a significant challenge for semantic web service. This paper proposes a semantic web service matching algorithm based not only on functions of services but also the world state related to services which is most important for web service in collaboration environment. Functions matching make sure that the selected services can fulfill the tasks users required, while the state matching can make sure that the selected services are executable and applying the selected services achieves the desired effects.

Current systems for real-time distributed CSCW are largely rooted in traditional GUI-based groupware. These groupware applications generally lag behind in features and compatibility with single-user applications. As a result, having to learn new GUIs for a sporadic task discourages many users. Many researchers agree that TUIs (tangible user interfaces) are especially suited for collocated collaboration. We conclude that sketching with pencil and eraser together for early design is suited for remote collaboration and communication. Current sketching systems are largely for single-user and sketching with pencil. In this paper, we present a method supporting sketching with pencil and eraser together for remote collaboration.

Team with uncertain members and synchronous collaboration are two salient features among the many groupware-supported requirements in the business processes of electric power enterprise. Traditional workflow management systems have difficulties in supporting such features. Through extending ordinary workflow model in modeling method and groupware-supporting mechanism, we designed and implemented a groupware-supported workflow management system. Compared with traditional workflow modeling method, this method has more capabilities in describing groupware activities and makes modeling simpler. This paper introduces the modeling method for groupware activity and the mechanism supporting synchronous collaboration in our workflow management system. The applications of the system in electric power enterprise are also introduced.

With the growth of web service in quantity, it has become an urgent issue how to compose web service with effective method so as to capacitate web service providers to work cooperatively and exert greater function. The paper introduces web service composition method based on rules and meta-services. Meta services are the abstraction of web services with similar functions, while rules are used to describe logic relation and data dependence relation among meta-services. An algorithm that generates the abstract service composition process based on the rules and meta-services is designed. The abstract service composition process is converted into executable process by employing web service discovery. The method proposed in this paper is proved to be feasible by the application in travel platform.

As infrastructure of shared services, Web Services provides possibility for business coordination and interoperability under distributed computing environment. However, the traditional centralized Web Services architecture has its limitation and peer-to-peer computing has become a new mode for network computing on the current Internet. This paper presents an collaboratively design method of Web Services composition process towards virtual enterprise coalition based peer-to-peer architecture, describes its system framework, the organization of peer-to-peer service nodes as well as the corresponding service discovery, binding mechanism and process generation method. And then, the performance analysis and evaluation of the method has been discussed. Finally, it prospects for the future research.

With the rapid development of the Semantic Web, the ontology technology has played an increasingly important role in collaborative System. The concept relatedness measure of heterogeneous ontology can be used to support information retrieval and information sharing among different users. Traditional method to solve the question of similarity between the concepts is based on the concept distance or information content between the two concepts of a single ontology concept tree. This paper presents a hybrid method to calculate the concept relatedness of heterogeneous ontologies. It is divided into two parts: The first is a fixed weighted measure based on the concept of the tree which was combined by multiple heterogeneous ontologies in a mapping way; the other variable calculation is based on users' communications. We have applied this method in our experimental platform IPVita and been proved to be a good one.

Web services can be managed and coordinated by business processes while computer application systems are more and more based on Internet. Services binding in these business processes evolve autonomously and their coupling is highly loose. Accordingly, exception handling of business processes execution under the Internet environment is one key to ensure the reliability of application systems. In this paper, we analyze the types of exceptions in business process execution and propose several corresponding handling strategies. We also analyze the role of chorographic which business process plays during execution and present a collaborative approach for exception handling in business process execution by cooperative works. In our opinion, cooperative works are based on strategies ontology which is related to different types of exception. We describe the approach and illustrate it with examples to show its functions. The major concern addressed by our approach is the support to anticipated and unexpected exceptions handling with cooperative works.

A key to maintain competitiveness is the ability of an enterprise to interact with or adapt to customers agilely. This paper proposes a new user-oriented business process model, named customized process, to cater for multitudinous individual demand. Firstly, the characteristics or requirements of customized process are analyzed and presented. Then, we describe how to generate agile user interface based on self-adapting template technique, to create customized process according to user's demand by using artificial intelligence technique CBR, and to cooperate between domain exports to deliberate such customized process. At last, matching web services for designed process is briefly introduced.

Clustering learners into groups according to the customized features in e-learning environment is an important step to build a personalization learning system. Though clustering e-learners is important for better cooperation between teachers and students in e-learning, it is a challenge job to group learners flexibly and exactly. Since there are already many models for the features which are used for the basis of the clustering methods, this paper proposes an improvement of Matrix-based Clustering Method which preformed efficiently without extra comparison in contrast to k-means clustering algorithm. The improvement of the Matrix-based Clustering Method proposes the concept "Agglomerate Strength" for further cluster cohesion measurement in contrast to the previous Matrix-based Clustering Method in precision. And the comparison experiments between the improvement Matrix-based Clustering Method and the other methods, i.e. the previous Matrix-based Clustering Method and K-means algorithm, are investigated. The results of experiments show that this method is feasible and efficient.

The development of collaborative design raised new demands for sharing and integrating among collaborating groups. In this paper, these demands are analyzed and a framework based on semantic Web services is introduced. The framework can improve the flexibility and maintainability of integration of collaborating systems and provide support for dynamic alliance oriented integrated product development.