LLM's code generation capabilities have yielded substantial improvements in the effectiveness of programming tasks. However, LLM-generated code still suffers from compilation and runtime errors. Existing offline preference optimization methods primarily focus on enhancing LLMs' coding abilities using pass/fail signals in the preference data, overlooking the deep-level error types in the failed codes. To address this, we propose Adaptively Progressive Preference Optimization (AP2O) for coding (i.e., AP2O-Coder), a method that guides LLMs adaptively and methodically to reduce code errors for code generation. Specifically, we construct an error notebook from failed codes and progressively optimize the LLM to correct errors type by type. Furthermore, we adaptively replay error types to tailor to the LLM's evolving weaknesses throughout training. Through extensive experiments on both code and general LLMs (Llama, Qwen, and DeepSeek series) with parameters ranging from 0.5B to 34B, our AP2O-Coder improves code generation performance by up to 3% in pass@k while using less preference data.

User sequential behaviors are driven by a variety of complex and evolving intents. Capturing the dynamic change of user intents has become critical yet challenging in the next-item recommendation. Existing studies usually model the transition relationships among multiple intents within a session or integrate temporal information to capture the dynamic evolution of user intents. However, they struggle to identify the precise timing and magnitudes of intent changes, leading to ambiguity in providing consistent or violated recommendations and ultimately yielding subpar performance. To this end, we propose a novel framework called Dual Fluctuation Modeling of Multi-level Intent Evolution for Next-Item Recommendation (DFRec) in this paper. DFRec explicitly identifies the user intent changes and further quantifies the magnitude of the changes. Specifically, we assume that a user's intent fluctuates around an inherent intent, with the magnitude of fluctuations indicating the extent of changes in user intents. Thus, we design an Emerging Intent Generation Module that employs a normal distribution with dynamic variance to capture intent fluctuations at each time step. Furthermore, we introduce a dual-layer dynamic variance update mechanism to capture fluctuation characteristics at different temporal levels, enhancing the representation of possible emergent intents. Extensive experiments on three real-world datasets verify DFRec's superiority over state-of-the-art baselines.

Jianqi Gao, Hang Yu, Jian Cao, Ranran Bu, Jinghua Tang, Nengjun Zhu, Yonggang Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The surge in large language models (LLMs) has fundamentally reshaped the landscape of GPU usage patterns, creating an urgent need for more efficient management strategies. While cloud providers employ spot instances to reduce costs for low-priority (LP) tasks, existing schedulers still grapple with high eviction rates and lengthy queuing times. To address these limitations, we present GFS, a novel preemptive scheduling framework that enhances service-level objective (SLO) compliance for high-priority (HP) tasks while minimizing preemptions to LP tasks. Firstly, GFS utilizes a lightweight forecasting model that predicts GPU demand among different tenants, enabling proactive resource management. Secondly, GFS employs a dynamic allocation mechanism to adjust the spot quota for LP tasks with guaranteed durations. Lastly, GFS incorporates a preemptive scheduling policy that prioritizes HP tasks while minimizing the impact on LP tasks. We demonstrate the effectiveness of GFS through both real-world implementation and simulations. The results show that GFS reduces eviction rates by 33.0%, and cuts queuing delays by 44.1% for LP tasks. Furthermore, GFS enhances the GPU allocation rate by up to 22.8% in real production clusters. In a production cluster of more than 10,000 GPUs, GFS yields roughly $459,715 in monthly benefits.

Knowledge base question answering (KBQA) aims to answer natural language questions using large-scale knowledge bases (KBs). Among various KBQA approaches, semantic parsing-based (SP-based) methods have demonstrated strong effectiveness by generating concise logical forms (LFs) that capture complex subgraph structures and semantic information. Recent research suggests that integrating large language models (LLMs) with SP can achieve significant improvements in the performance and efficiency of KBQA by facilitating the direct generation of LFs with minimal retrieval. However, generating complete LFs with LLMs continues to pose a challenge due to the complexity of the required graph structures and constraints, leading to the significant issue of non-executability. To address these challenges, we propose GCA-KBQA, a step-wise fine-tuned LLM-based framework that employs hop-wise generation, knowledge-assisted calibration, and path-level assembly to construct complete LFs for KBQA. Specifically, we decompose the complex SP process into manageable steps: first, we iteratively generate LFs for each topic entity one hop at a time using a fine-tuned LLM, leveraging KB knowledge to calibrate intermediate outputs and mitigate error propagation. Subsequently, we guide the LLM in assembling path-level LFs from different topic entities, resulting in optimized final LF. We evaluate the proposed method on four KBQA benchmarks spanning two distinct KBs, demonstrating its superior performance compared to state-of-the-art baselines. The code is available at https://github.com/pvfeldt/GCA-KBQA.

As users' preferences evolve over time, personalized online services increasingly rely on sequential recommender systems to predict future interactions by modeling patterns in historical user behavior. However, existing methods for sequential recommendation (SR) face two key challenges: they struggle to simultaneously leverage collaborative, semantic, and rating information, and the use of hard labels during training provides limited supervision. In this paper, we introduce SEAR, an LLM-powered Sequential recommEndation framework via fusion of collAborative, semantic, and Rating information. The proposed deep model comprises an embedding layer and a sequence encoder. The embedding layer transforms user-item interactions into three types of embeddings: collaborative, semantic, and rating. The sequence encoder then integrates these embeddings and identifies sequential patterns to model user representations. To enhance the utilization of item semantics, we integrate a large language model (LLM) to extract LLM embeddings. These embeddings are then employed to initialize the semantic embedding layer, collaborative embedding layer, and item embeddings. To capture more nuanced user behavior patterns, we generate preference-weighted soft labels based on the next k interactions. Extensive experiments validate the effectiveness of SEAR, and ablation studies further highlight the distinct contributions of the collaborative, semantic, and rating information.

Knowledge base question answering (KBQA) refers to the task of answering natural language questions using factual information from large-scale knowledge bases (KBs). To obtain accurate answers, recent research optimizes semantic parsing methods, a major KBQA approach, with large language models (LLMs), where concise logical forms (LFs) are generated by LLMs and executed in KBs. Although these methods demonstrate superior performance, they still encounter the problem that some generated LFs fail to yield answers when executed, significantly limiting their effectiveness. To mitigate this issue, we propose KARV, a Knowledge-Assisted reasoning path Reconstruction and hierarchical Voting approach for non-executable LFs. This method extracts semantic knowledge from KBs as guidance to correct and reconstruct reasoning paths, deriving answers through a voting-based strategy. The insight is that non-executable LFs generated by LLMs still contain rich semantic information, and the knowledge retrieved from KBs can effectively correct them. Specifically, we fine-tune LLMs to generate high-quality LFs, and the nonexecutable LFs are decomposed into multiple path branches based on mentioned entities. Semantic knowledge from KBs is then leveraged to correct the entities and relations within these branches, effectively reconstructing the reasoning paths. To obtain precise final answers, we apply a hierarchical voting strategy both within and across the non-executable LFs. Our proposed method achieves state-of-the-art performance on benchmarks including WebQuestionSP (WebQSP), ComplexWebQuestions (CWQ), and FreebaseQA.

Detecting anomalies in business processes is imperative for achieving operational success, especially as multiple participants increasingly engage in collaborative efforts to complete processes, i.e., collaborative business processes, amidst rapid economic development. However, existing business process anomaly detection approaches are typically designed for centralized training, making them impractical for collaborative business processes that require stringent privacy measures. In this paper, we introduce a feDerated Unsupervised AnomaLy detection framework for collaborative business processes, named DUAL. DUAL enables participants to collaboratively detect anomalies via a third-party coordinator, which constructs a global view from the hidden representations of participants' local sub-traces without exposing the sub-traces themselves. To further strengthen privacy protection, DUAL injects differential privacy noise into the transmitted hidden representations. To mitigate the global-local discrepancy, we introduce novel event execution errors which indicate whether the client who is supposed to execute the reconstructed event is consistent with the observed one. Extensive experiments demonstrate that DUAL effectively detects anomalies in collaborative processes while preserving privacy, achieving performance comparable to a centralized setting that requires access to participants' raw sub-traces.

Process discovery aims to derive a process model that accurately represents the observed behavior in an event log. As a state-of-the-art process discovery technique, Inductive Miner (IM) generates sound process models (i.e., free of deadlocks) while ensuring optimal replay fitness. However, IM may sometimes produce over-generalized process models with locally imprecise structures, often resulting in the creation of so-called flower structures. To address this limitation, this paper presents a novel technique that refines the process model generated by IM by optimizing its imprecise sub-processes. Specifically, the technique begins by identifying and extracting sub-logs corresponding to imprecise sub-processes in the initial IM-generated process model. Then, these imprecise sub-processes are iteratively optimized using a frequency-based filtering mechanism applied to the sub-logs. Once optimized, the imprecise sub-processes in the initial process model are replaced by the optimized ones, generating a set of candidates process models. Finally, the candidate with the best quality, in terms of fitness and precision, is selected as the final optimized process models. The proposed technique has been implemented as a plugin for the open-source process mining platform ProM. Through comparisons with state-of-the-art process discovery techniques using 10 publicly available real-life event logs, the experimental results demonstrate that the proposed method achieves an average absolute improvement of 0.173 in F-measure over its IMi variant, while also exhibiting competitive performance relative to other state-of-the-art approaches.

Knowledge base question answering (KBQA) refers to the system that produces answers to user queries by reasoning with a large-scale structured knowledge base. Advanced works have achieved great success either by generating logical forms (LF) or directly generating answers. Although the former typically yields better performance, these generated LF could be inaccurate, e.g., non-executable. In this regard, large language models (LLMs) have shown exciting potential for accurate generation. However, it is challenging to fine-tune LLMs to generate LF. This is because the context retrieved for prediction typically leads to an excessive number of reasoning paths. In this context, LLMs can generate numerous LF corresponding to these reasoning paths, but a few LF can result in correct answers. Thus, fine-tuning LLMs to generate answer-relevant LF would conflict with the prior knowledge of the LLMs. In this work, we propose a novel learning framework, FM-KBQA, to fine-tune LLMs using multi-task learning for KBQA. Specifically, we propose to fine-tune LLMs using an additional objective: generating the index of reasoning paths that lead to correct answers. This will direct LLMs to pay attention to answer-relevant paths among numerous reasoning paths by completing a simple task where the selected reasoning paths can be supplementary for non-executable LF. Directly generating answers can make LLMs pay attention to the answer-relevant reasoning paths, but it is much more challenging than generating the index of reasoning paths. To verify FM-KBQA's effectiveness, we conduct experiments on mainstream benchmarks, such as WebQuestionsSP (WQSP) and ComplexWebQuestions (CWQ). Extensive evaluations across two public benchmark datasets underscore the superiority of FM-KBQA over current state-of-the-art methods.

Detecting anomalies in business processes is crucial for ensuring operational success. While many existing methods rely on statistical frequency to detect anomalies, it's important to note that infrequent behavior doesn't necessarily imply undesirability. To address this challenge, detecting anomalies from a semantic viewpoint proves to be a more effective approach. However, current semantic anomaly detection methods treat a trace (i.e., process instance) as multiple event pairs, disrupting long-distance dependencies. In this paper, we introduce DABL, a novel approach for detecting semantic anomalies in business processes using large language models (LLMs). We collect 143,137 real-world process models from various domains. By generating normal traces through the playout of these process models and simulating both ordering and exclusion anomalies, we fine-tune Llama 2 using the resulting log. Through extensive experiments, we demonstrate that DABL surpasses existing state-of-the-art semantic anomaly detection methods in terms of both generalization ability and learning of given processes. Users can directly apply DABL to detect semantic anomalies in their own datasets without the need for additional training. Furthermore, DABL offers the ability to interpret anomalies' causes in natural language, providing valuable insights into the detected anomalies.

The end-to-end automated design of machine learning (ML) pipelines significantly reduces the workload for data scientists and democratizes ML for non-experts. Evolutionary algorithm (EA)-based automated ML (AutoML) systems, a prominent category of AutoML, often face inefficiencies due to the costly fitness evaluation of candidate ML pipelines. Although surrogate models have been employed to approximate the true performance of pipelines more quickly, a key challenge remains in effectively bridging the semantic gap between the heterogeneous features of datasets and pipelines. To address this issue, we propose ADELA, a novel accompanying surrogate-based optimization strategy that accelerates EA-based AutoML while retaining the performance of the resulting pipelines. ADELA operates in two phases: Offline, leveraging a high-quality curated pipeline corpus to meta-learn an accompanying surrogate model; and Online, selecting the accompanying pipeline and using the learned model to predict the performance of evaluation pipelines instead of executing them. The accompanying mechanism effectively mitigates the semantic gap between datasets and pipelines, enabling ADELA to reduce computation times by an average of 73.66% while retaining 98.78% of the final pipeline performance, as demonstrated in extensive experimental evaluations.

Practical applications often require forecasting the future states of short time series (STS) using multiple related long time series (LTS) as auxiliary data, a process known as few-shot prediction. The primary challenge, given the limited data on STS, is effectively capturing the pattern similarities between STS and LTS. Current methods, despite notable advancements, primarily focus on trans- ferring pattern characteristics from LTS to STS without explicitly addressing their similarities at various levels. To overcome this lim- itation, we propose a novel few-shot time series forecasting model called DANet. Drawing on the Retrieval-Augmented Generation (RAG) framework in large language models, DANet retrieves long and short sequences from LTS that closely resemble STS, thereby enhancing prediction accuracy while simultaneously reducing un- certainty through this retrieval process. First, we define two metrics to quantify pattern similarities between STS and LTS, addressing the issue of different representations of the same pattern due to variations in sequence length. Second, we propose a dual-attention mechanism which embeds the two similarities metrics to extract and integrate long and short sequences from LTS across variable and temporal levels for generating predictions. Our experiments across six scenarios show that DANet significantly outperforms six state-of-the-art (SOTA) methods.

The pursuit of personalized outfit recommendation, tailored to individual user preferences, has emerged as a central focus in research. Despite the propositions of various outfit recommendation methods, the modeling of fashion styles within outfits, a pivotal criterion for user selection, has been largely overlooked. Fashion styles are intricately embedded in multi-modal information, such as images and text. Unfortunately, current outfit recommendation methods predominantly focus on a single modality or employ simplistic fusion techniques, thus failing to capture the intricate interplay between different fashion data modalities, resulting in an inability to model fashion styles effectively. In this work, we devise a novel Personalized Outfit Recommender with Style-Guided Multi-Modal Feature Fusion scheme, denoted as POSM, aiming to maximize the utilization of multi-modal features in outfit recommendation. In particular, this scheme consists of three key components: modality-aware outfit modeling, feature separation network, and style mapping component. Extensive experiments conducted on the benchmark datasets validate the superiority of POSM over state-of-the-art methods.

Graph-based fraud detection has emerged as a pivotal tool in risk management, leveraging the power of graph neural networks to enhance node representations by aggregating information from neighboring nodes. However, this aggregation process can sometimes introduce noise by incorporating neighbors from different categories, potentially diluting the central node’s representation. To tackle this issue, we introduce an innovative Adversarial Confidence Reweighting (ACR) technique designed to allocate discriminative weights to samples automatically. This approach effectively minimizes the impact of noisy neighbors on the representation of nodes. By introducing controlled adversarial perturbations to the nodes being classified, we can assess the extent of representation dilution. Furthermore, we employ an adaptive node re-weighted learning objective, which dynamically adjusts node weights based on a confidence measure derived from prediction accuracy. Our experimental evaluations across three public datasets demonstrate that our adversarial strategy significantly surpasses the baseline model in terms of detection performance.

In recent years, leveraging pre-trained language models (PLMs) to generate embeddings for downstream tasks has achieved remarkable success. To further enhance the adaptability of PLMs to downstream tasks, the prevailing strategy involves incorporating auxiliary tasks as regularization terms, (e.g., contrastive learning), for fine-tuning the pre-trained models. However, this approach encounters challenges due to task conflicts between auxiliary tasks and specific downstream tasks. To overcome these issues, we introduce a novel strategy termed Consistency Adversarial Training (CAT). CAT first dynamically identifies the most inconsistent cases between specific and auxiliary tasks by introducing perturbations and then eliminates the inconsistency in an adversarial learning manner. Performance evaluations on the GLUE benchmark demonstrate that CAT minimizes task conflicts during the fine-tuning process of PLMs, leading to a notable improvement in the overall fine-tuning performance of PLMs.

When processing multi-view data, conflicts may occur since different views have unique insights. Existing studies always consider conflict as a bad factor and thus adopt a negative operation, i.e., eliminating or minimizing conflicts. However, in a multi-view decision-making scenario, conflict can highlight view differences and reveal the reliability of individual and collective decisions. To this end, we propose a novel trusted collective learning method (TrustCL) that can actively handle conflicts between individuals and obtain a collective opinion and its reliability by considering conflicts. Specifically, TrustCL first learns view-specific evidence supporting individual opinions. To deal with conflicting opinions across views, TrustCL assembles a reliability-oriented collective learning phase to determine which view owns a higher priority. It further combines priority and view-specific evidence to conclude the final collective opinion and its reliability. Experiments on a real-world multidisciplinary consultation dataset demonstrate the superiority of our method and exhibit some interesting findings regarding conflictive multi-view decision-making. Our code is available at https://github.com/ifbettrer/TrustCL

The rise of generative APIs has fueled interest in privacy-preserving synthetic data generation. While the Private Evolution (PE) algorithm generates Differential Privacy (DP) synthetic images using diffusion model APIs, it struggles with few-shot private data due to the limitations of its DP-protected similarity voting approach. In practice, the few-shot private data challenge is particularly prevalent in specialized domains like healthcare and industry. To address this challenge, we propose a novel API-assisted algorithm, Private Contrastive Evolution (PCEvolve), which iteratively mines inherent inter-class contrastive relationships in few-shot private data beyond individual data points and seamlessly integrates them into an adapted Exponential Mechanism (EM) to optimize DP’s utility in an evolution loop. We conduct extensive experiments on four specialized datasets, demonstrating that PCEvolve outperforms PE and other API-assisted baselines. These results highlight the potential of leveraging API access with private data for quality evaluation, enabling the generation of high-quality DP synthetic images and paving the way for more accessible and effective privacy-preserving generative API applications. Our code is available at https://github.com/TsingZ0/PCEvolve.

Machine Unlearning (MU) technology facilitates the removal of the influence of specific data instances from trained models on request. Despite rapid advancements in MU technology, its vulnerabilities are still underexplored, posing potential risks of privacy breaches through leaks of ostensibly unlearned information. Current limited research on MU attacks requires access to original models containing privacy data, which violates the critical privacy-preserving objective of MU. To address this gap, we initiate the innovative study on recalling the forgotten class memberships from unlearned models (ULMs) without requiring access to the original one. Specifically, we implement a Membership Recall Attack (MRA) framework with a teacher-student knowledge distillation architecture, where ULMs serve as noisy labelers to transfer knowledge to student models. Then, it is translated into a Learning with Noisy Labels (LNL) problem for inferring correct labels of the forgetting instances. Extensive experiments on state-of-the-art MU methods with multiple real datasets demonstrate that the proposed MRA strategy exhibits high efficacy in recovering class memberships of unlearned instances. As a result, our study and evaluation have established a benchmark for future research on MU vulnerabilities.

Large deep learning models have achieved significant success in various tasks. However, the performance of a model can significantly degrade if it is needed to train on datasets with noisy labels with misleading or ambiguous information. To date, there are limited investigations on how to restore performance when model degradation has been incurred by noisy label data. Inspired by the "forgetting mechanism" in neuroscience, which enables accelerating the relearning of correct knowledge by unlearning the wrong knowledge, we propose a robust model restoration and refinement (MRR) framework COLUR, namely Confidence-Oriented Learning, Unlearning and Relearning. Specifically, we implement COLUR with an efficient co-training architecture to unlearn the influence of label noise, and then refine model confidence on each label for relearning. Extensive experiments are conducted on four real datasets and all evaluation results show that COLUR consistently outperforms other SOTA methods after MRR.

As AI evolves, collaboration among heterogeneous models helps overcome data scarcity by enabling knowledge transfer across institutions and devices.Traditional Federated Learning (FL) only supports homogeneous models, limiting collaboration among clients with heterogeneous model architectures.To address this, Heterogeneous Federated Learning (HtFL) methods are developed to enable collaboration across diverse heterogeneous models while tackling the data heterogeneity issue at the same time.However, a comprehensive benchmark for standardized evaluation and analysis of the rapidly growing HtFL methods is lacking.Firstly, the highly varied datasets, model heterogeneity scenarios, and different method implementations become hurdles to making easy and fair comparisons among HtFL methods.Secondly, the effectiveness and robustness of HtFL methods are under-explored in various scenarios, such as the medical domain and sensor signal modality.To fill this gap, we introduce the first Heterogeneous Federated Learning Library (HtFLlib), an easy-to-use and extensible framework that integrates multiple datasets and model heterogeneity scenarios, offering a robust benchmark for research and practical applications.Specifically, HtFLlib integrates (1) 12 datasets spanning various domains, modalities, and data heterogeneity scenarios; (2) 40 model architectures, ranging from small to large, across three modalities;(3) a modularized and easy-to-extend HtFL codebase with implementations of 10 representative HtFL methods; and (4) systematic evaluations in terms of accuracy, convergence, computation costs, and communication costs.We emphasize the advantages and potential of state-of-the-art HtFL methods and hope that HtFLlib will catalyze advancing HtFL research and enable its broader applications.The code is released at https://github.com/TsingZ0/HtFLlib.

There are a large number of text processing tasks in web applications, such as sentiment classification, summary extraction, and question answering. Recently, fine-tuning pre-trained language models (PLMs) to adapt to downstream text-processing tasks has attracted much attention. However, due to the differences in data, model, and tasks between the pre-training and fine-tuning processes, the fine-tuning process may suffer from catastrophic forgetting of pre-training knowledge, which may implicitly limit the model's performance and generalization ability. To address these challenges, we propose a novel dual-model framework, termed as consistency alignment (CoAi). The insight of CoAi lies in building an auxiliary model that simulates the distribution of pre-training knowledge in real-time according to the current task, and co-training the task-specific model and the auxiliary model to balance the pre-training knowledge and task-specific knowledge during fine-tuning. Specifically, the auxiliary model is constructed on-the-fly to maintain the pre-training knowledge. Subsequently, CoAi simulates the pre-training process by performing distributional exploration in the parameter space, which is built upon our novel insight into the transformation between data and model parameter space. However, the objectives leveraged to construct the auxiliary model lead to the misalignment between the pre-training and task-specific knowledge. To alleviate the inconsistency, we employ an auxiliary variable to align the prediction distribution of the task-specific and the auxiliary models, inspired by constrastive clustering. We validate the effectiveness of CoAi on nine classic classification tasks and three generation tasks, showing consistent and significant improvements compared with state-of-the-art methods.

Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL) has gained significant prominence as a research direction within the FL domain. Whereas traditional FL (tFL) focuses on jointly learning a global model, pFL aims to balance each client's global and personalized goals in FL settings. To foster the pFL research community, we started and built PFLlib, a comprehensive pFL library with an integrated benchmark platform. In PFLlib, we implemented 37 state-of-the-art FL algorithms (8 tFL algorithms and 29 pFL algorithms) and provided various evaluation environments with three statistically heterogeneous scenarios and 24 datasets. At present, PFLlib has gained more than 1600 stars and 300 forks on GitHub.

An effective auto-scaling framework is essential for microservices to ensure performance stability and resource efficiency under dynamic workloads. As revealed by many prior studies, the key to efficient auto-scaling lies in accurately learning performance patterns, i.e., the relationship between performance metrics and workloads in data-driven schemes. However, we notice that there are two significant challenges in characterizing performance patterns for large-scale microservices. Firstly, diverse microservices demonstrate varying sensitivities to heterogeneous machines, causing difficulty in quantifying the performance difference in a fixed manner. Secondly, frequent version upgrades of microservices result in uncertain changes in performance patterns, known as pattern drifts, leading to imprecise resource capacity estimation issues. To address these challenges, we propose Humas, a heterogeneity- and upgrade-aware auto-scaling framework for large-scale microservices. Firstly, Humas quantifies the difference in resource efficiency among heterogeneous machines for various microservices online and normalizes their resources in standard units. Additionally, Humas develops a least-squares density-difference (LSDD) based algorithm to identify pattern drifts caused by upgrades. Lastly, Humas generates capacity adjustment plans for microservices based on the latest performance patterns and predicted workloads. The experiment results conducted on 50 real microservices with over 11,000 containers demonstrate that Humas improves resource efficiency and performance stability by approximately 30.4% and 48.0%, respectively, compared to state-of-the-art approaches.

The popularity of open source has witnessed significant growth in the past two decades. The sustainability and success of open source projects rely heavily on the active community of contributors, who have the freedom to join or depart voluntarily. The churn of core developers can have detrimental effects on the continuous development and progress of these communities. Therefore, previous studies have aimed to identify the factors that influence developer churn and reveal its impact on open source communities. However, there is currently a lack of research on predicting whether a developer will leave or retain within a given timeframe. This article aims to bridge this gap by introducing a novel model called context-aware dynamic graph neural network (ConDyGNN), which is designed specifically for predicting developer churn in open source communities. By leveraging historical data, this model takes into consideration various factors such as developers’ activities, collaborative networks, and community context information. To capture both temporal dependencies and spatial correlations among different developers, temporal convolutional network (TCN) and graph convolutional network (GCN) modules are employed inConDyGNN. Furthermore, a context-aware module based on a multihead attention mechanism is proposed to effectively integrate macrolevel community information and enhance the predictive performance. The superiority of the proposed model is empirically demonstrated through extensive comparative experiments and an ablation study.

Map matching is crucial to facilitating location-based services, and recent advancements in map matching have demonstrated excellent performance with high-quality data. However, the use of low-precision devices often introduces high measurement noise, and the slow update rate of maps may result in errors in digital maps. Consequently, multiple types of noise significantly impact the performance of map matching algorithms. To tackle this issue, this paper presents a novel multi-noise perception framework, named MPF, aiming to enhance the performance and robustness of existing map matching algorithms. The main challenge lies in detecting anomalies during map matching, identifying the root causes, and devising appropriate solutions. Firstly, we propose a matching quality assessment (MQA) method that assesses abnormal variance in matching probability. Secondly, we introduce a multiple noise discrimination (MND) mechanism to effectively differentiate between measurement noise and map errors. Thirdly, we present a missing segment generation (MSG) scheme that dynamically fills in map gaps to prevent significant detours. To validate the effectiveness of MPF, we conduct experiments using real-world taxi trajectories from four cities, covering a total distance of 79,670.6 km. MPF is compare with seven online map matching algorithms and is used to optimize their performance. The experiments show that MPF outperforms the top baselines by 15.6%-26.9% and enhances their performance by 18.7%-38.2%.

The recent years have witnessed a surge in the development of traffic flow prediction methods, often deployed on cloud platforms to offer predictive services for entire transportation networks. However, the processes of training and executing a model for the entire traffic network are both time-consuming and computationally expensive. As a result, the utilization of edge servers for local sub-network prediction services has gained prominence. Nevertheless, training prediction models for numerous sub-networks within the extensive traffic network remains a time-intensive and computing resource-consuming task. To tackle this challenge, this article introduces the Pre-trained model REcommendation Framework for Edge computing enabled tRaffic flow prediction (PREFER). PREFER trains a set of traffic flow prediction models on selected sub-networks, then recommends optimal pre-trained models for edge servers. The recommendation is specifically based on performance prediction, integrating neural collaborative filtering and traffic flow characteristics. Experiments conducted on real datasets reveal that the pre-trained models recommended by PREFER perform close to the actual optimal ones and significantly outperform existing recommendation algorithms.

Event sequence anomaly detection has garnered considerable attention in research, encompassing applications such as identifying anomalies in system logs, anomalous transaction users, and so on. Yet, prevailing anomaly detection methods often rely solely on local data for training, potentially leading to imperfect detection performance. In this article, we introduce a personalized Federated anomaly detection framework for discrete event Sequences, named FeadSeq. Specifically, we propose a separate architecture for sequence reconstruction networks (SEPRE) which partitions the network into two parts: a shared part and a standalone part, better suited for federated learning schemes. In tandem, we propose a novel partial shared federated learning scheme that employs a mask strategy to alleviate communication overhead and produce personalized local models to address the statistical heterogeneity of data among clients. This scheme dictates that a subset of weights is communicated between clients and servers for collaborative training, while the remaining weights are trained exclusively locally. To evaluate the effectiveness of FeadSeq, we conduct extensive experiments on both system logs and business process event logs. The results affirm the superiority of FeadSeq over existing personalized federated learning algorithms, showcasing not only improved performance but also reduced communication overhead.

Multivariate time series forecasting is applied in many domains, such as finance, transportation, and industry. The main challenge of precise forecasting lies in accurately capturing latent dependencies. Recent studies develop various frameworks to reduce computational complexity or to enhance the learning of intricate relationships, while lacking interpretability and generality. In this article, we aim to elucidate the capture of dependencies as the recognition of patterns. We believe that patterns can be formally described from two aspects: the shapes of segments that frequently repeat and the corresponding forms of repetitions. Drawing upon this idea, we design a multivariate time series forecasting model named PRformer , 1 which incorporates a pattern-oriented attention mechanism and a pattern-based projector. The attention mechanism can perceive different forms of repetitions by embedded with various similarity evaluation metrics between segments, and filter out noise from segments to extract potential patterns with a statistical-driven weighting scheme. The pattern-based projector is employed to form the forecasting results by deriving the representative patterns from the set of potential ones. By incorporating explicit definitions of patterns, PRformer is interpretable and general to various time series scenarios. Experimental results on seven datasets demonstrate that PRformer outperforms six state-of-the-art models by about 10.7% in forecasting accuracy.

Data imputation is crucial in the analysis of incomplete time series, such as forecasting and classification, which involves learning dependencies among the observed values to infer missing ones. As there are no ground truths for missing values, the challenge of time series imputation lies in preventing the model from overfitting to spurious correlations. In this article, we believe that ensuring dependency consistency between observed and imputed values in a sequence is paramount for data imputation. Based on this idea, we propose a model called IR 2 -Net , 1 which combines an incomplete representation mechanism (IRM) with an iterative reconstruction framework (IRF) to establish a closed-loop learning-validation imputation paradigm. Firstly, IRM facilitates the representation of dependencies in incomplete sequences while preserving their distributions and semantics, effectively preventing the model from capturing spurious correlations. Secondly, IRF enables the model to reconstruct identical complete sequences separately based on imputed and observed values, ensuring that the dependencies of imputed values remain consistent with those of the observed ones. We conduct experiments on four datasets and compare IR 2 -Net with seven state-of-the-art imputation models. The experiment results show that IR 2 -Net outperforms all the baselines by 4.1%–23.4% in terms of accuracy. Moreover, IRF and IRM are two general modules that can be easily integrated into two existing models, significantly enhancing their performance by 18.3%–42.0%.

Effective management of business processes is crucial for organizational success. However, despite meticulous design and implementation, anomalies are inevitable and can result in inefficiencies, delays, or even significant financial losses. Numerous methods for detecting anomalies in business processes have been proposed recently. However, there is no comprehensive benchmark to evaluate these methods. Consequently, the relative merits of each method remain unclear due to differences in their experimental setup, choice of datasets and evaluation measures. In this paper, we present a systematic literature review and taxonomy of business process anomaly detection methods. Additionally, we select at least one method from each category, resulting in 16 methods that are cross-benchmarked against 32 synthetic logs and 19 real-life logs from different industry domains. Our analysis provides insights into the strengths and weaknesses of different anomaly detection methods. Ultimately, our findings can help researchers and practitioners in the field of process mining make informed decisions when selecting and applying anomaly detection methods to real-life business scenarios. Finally, some future directions are discussed in order to promote the evolution of business process anomaly detection.

Multi-access edge computing has become an effective paradigm to provide offloading services for computation-intensive and delay-sensitive tasks on vehicles. However, high mobility of vehicles usually incurs spatio-temporal load-imbalances among edge servers. Therefore, task migration is employed to maintain dynamic workload balancing by transmitting excessive tasks from overloaded to underloaded servers. Recent studies adopt deep reinforcement learning approaches to generate offloading and migration decisions based on current observations of systems. However, we argue that the migration direction is highly dependent on vehicular movements, and task migration towards the wrong direction could lead to additional delays. Therefore, we emphasize the importance of guiding task migration via exploring prospective trajectories of vehicles. We propose a Mobility-Aware Cooperative Multi-Agent (MCMA) deep reinforcement learning approach to make vehicle-by-vehicle decisions in multi-edge computation offloading scenarios. A two-stage decision framework is designed to solve the joint optimization problem of computation offloading and resource allocation. Additionally, an Informer-based multi-step vehicular trajectory prediction module is incorporated to enhance the capability of forecasting vehicular movements. Extensive experiments and analysis are conducted on synthetic and realistic scenarios, showing that our approach consistently outperforms both heuristic and DRL-based methods. The simulation scenarios and source codes are publicly available here.

With the explosive growth of online information, recommendation systems have become essential tools for alleviating information overload. In recent years, researchers have increasingly focused on centralized recommendation systems, capitalizing on the powerful computing capabilities of cloud servers and the rich historical data they store. However, the rapid development of edge computing and mobile devices in recent years has provided new alternatives for building recommendation systems. These alternatives offer advantages such as privacy protection and low-latency recommendations. To leverage the advantages of different computing nodes, including cloud servers, edge servers, and terminal devices, researchers have proposed recommendation systems that involve the collaboration of these nodes, known as distributed recommendation systems. This survey provides a systematic review of distributed recommendation systems. Specifically, we design a taxonomy for these systems from four perspectives and comprehensively summarize each study by category. In particular, we conduct a detailed analysis of the collaboration mechanisms of distributed recommendation systems. Finally, we discuss potential future research directions in this field.

Event matching is a key component in a large-scale content-based publish/subscribe system. The performance of most existing algorithms is easily affected by the subscription matching probability. In this paper, we propose a new data structure, named AWAW B+-Tree, which is based on the width of the predicates, to efficiently index the subscriptions. The most notable feature ofAW B+-Treeis its ability to combine the advantages of different matching methods, thus achieving high and robust performance in dynamic environments. First, we implement both a forward matching method (AFM) and a backward matching method (ABM) based onAW B+-Tree. Then, we introduce a hybrid matching method (AHM) that combines AFM and ABM. Moreover, we extendAW B+-Treein three aspects: approximate matching, string type matching, and fine-grained parallelization. We conducted extensive experiments to evaluate the performance of the proposed matching algorithms on synthetic and real-world datasets. The experiment results reveal that AHM achieves a reduction in matching time by up to 53.8% compared to the state-of-the-art method. Additionally, AHM exhibits improved performance robustness, with up to a 76.9% reduction in terms of the standard deviation of matching time. Particularly in dynamic scenarios, AHM is at least 2.3 times faster and 41.3% more stable than its counterparts. Furthermore, by implementing parallelization, the matching speed of 8 threads can be accelerated by 4.16 times compared to the single-thread matching speed.

Predictive Process Monitoring (PPM) aims to predict the future state of running process instances to enable timely interventions to mitigate potential risks. As one of the most fundamental tasks in PPM, process remaining time prediction focuses on preventing timeout occurrences. While various deep learning-based approaches have been developed for this purpose, they often rely on pre-established static prediction models and struggle to maintain accurate predictions when the process undergoes dynamic changes, such as an expanding sales channels. To tackle this challenge, this paper proposes an incremental process remaining time prediction framework by continuously updating the prediction model based on an incremental event log. Specifically, a feature selection strategy is first introduced to extract effective features from event logs. Leveraging effective features can significantly improve the prediction quality by capturing the changes in process information. Then, three incremental log-based updating mechanisms, including period-based updating, quantity-based updating, and concept-drift-based updating, along with a reconstruction strategy, are proposed to dynamically adjust the prediction model in response to business changes. Finally, LSTM, Transformer, and Auto-encoder models are adapted and integrated into the proposed framework. The approach has been implemented and publicly released. Experimental evaluation using nine real-life event logs demonstrate that the proposed framework and its three instantiations (i.e., LSTM-based, Transformer-based, and Auto-encoder-based ones) outperform state-of-the-art techniques in terms of prediction accuracy.

Recently, Heterogeneous Federated Learning (HtFL) has attracted attention due to its ability to support heterogeneous models and data. To reduce the high communication cost of transmitting model parameters, a major challenge in HtFL, prototype-based HtFL methods are proposed to solely share class representatives, a.k.a, prototypes, among heterogeneous clients while maintaining the privacy of clients’ models. However, these prototypes are naively aggregated into global prototypes on the server using weighted averaging, resulting in suboptimal global knowledge which negatively impacts the performance of clients. To overcome this challenge, we introduce a novel HtFL approach called FedTGP, which leverages our Adaptive-margin-enhanced Contrastive Learning (ACL) to learn Trainable Global Prototypes (TGP) on the server. By incorporating ACL, our approach enhances prototype separability while preserving semantic meaning. Extensive experiments with twelve heterogeneous models demonstrate that our FedTGP surpasses state-of-the-art methods by up to 9.08% in accuracy while maintaining the communication and privacy advantages of prototype-based HtFL. Our code is available at https://github.com/TsingZ0/FedTGP.

Heterogeneous Federated Learning (HtFL) enables collaborative learning on multiple clients with different model architectures while preserving privacy. Despite recent research progress, knowledge sharing in HtFL is still difficult due to data and model heterogeneity. To tackle this issue, we leverage the knowledge stored in public pretrained generators and propose a new upload-efficient knowledge transfer scheme called Federated Knowledge-Transfer Loop (Fed-KTL). Our FedKTL can produce client-task-related prototypical image-vector pairs via the generator's inference on the server. With these pairs, each client can transfer preexisting knowledge from the generator to its local model through an additional supervised local task. We conduct extensive experiments on four datasets under two types of data heterogeneity with 14 kinds of models including CNNs and ViTs. Results show that our upload-efficient FedKTL surpasses seven state-of-the-art methods by up to 7.31% in accuracy. Moreover, our knowledge transfer scheme is applicable in scenarios with only one edge client. Code: https://github.com/TsingZ0/FedKTL

Recent trends in next-item recommendation systems have focused on modeling user intents. Traditional methods often extract users' inherent intents from the most representative items in a session, overlooking “unexpected items” that deviate from the majority in various contextual aspects. These unexpected items, frequently present, can be crucial indicators of a user's inclination towards exploring new options, signaling emerging intents that warrant significant attention. In response, we introduce DbMei, a novel approach that decouples user behaviors and emphasizes the modeling of emerging intents. DbMei distinguishes between two user behavior types: “focused shopping”, which aligns with users' inherent intents, and”wandering shopping”, which aligns with emerging intents. Focused shopping is analyzed using topic modeling and hypergraph learning while wandering shopping is explored through session neighbor retrieval. An exploitation-exploration mechanism is employed to determine the behavioral probability distribution for upcoming items. This integrated modeling of focused and wandering shopping behaviors drives our recommendation process. Extensive empirical studies on two real-world datasets, Amazon-KDD and Beauty, showcase DbMei's superiority over leading methods regarding Recall and MRR metrics. Our code is publicly available at https://github.com/sunlingdan-123/DbMei.

Content-based publish/subscribe systems have the capability to achieve fine-grained data distribution, rapidly forwarding data from publishers to subscribers with specific requirements. The event matching algorithm is a fundamental component, quickly searching for subscriptions that match an event based on constraints defined by subscribers. As data scales continue to expand, there is a heightened demands for more efficient, robust, and versatile event matching algorithms. In this paper, we propose a novel data structure called the Dual-ended Interval Tree (DI-Tree). Firstly, given the splitting point, this data structure classifies intervals into three categories based on the joint distribution of their left and right endpoints in the attribute value domain. Furthermore, the DI-Tree utilizes blue and green nodes to store these three categories of intervals, resulting in enhanced indexing efficiency. Moreover, by utilizing the DITree to efficiently search matching and unmatching intervals, we develop innovative forward and backward event matching algorithms. Additionally, to enhance matching efficacy and reduce memory usage, we introduce key optimization techniques, focusing on improving node balance and bitset optimization. We conduct extensive experiments to evaluate the performance of DITree. When compared with five state-of-the-art event matching algorithms, the DI-Tree demonstrates an average reduction of up to 76.8 % in terms of matching time. This significant improvement highlights the effectiveness of our proposed strategies and the potential of DI-Tree in optimizing event matching performance.

Co-locating online latency-critical (LC) services with best-effort (BE) batch jobs in the same server has been widely adopted by modern data centers to improve resource utilization. Various approaches have been proposed to maximize the resources allocated to the BE jobs without SLO (service level objective) violation. However, when facing bursty workloads, existing solutions suffer from poor performance because they cannot react promptly to the sudden and sharp increase of LC service requests. Consequently, these methods result in either a high violation rate of the SLO constraint or low resource utilization caused by conservative allocation strategies.

It is time-consuming and knowledge-intensive for scientists to find practical workflows from the massive number of scientific workflow models. Currently, the retrieval approaches are mainly based on text matching between natural language queries and the descriptions of candidate workflows. Notably, the workflow structure also provides essential semantics, but the challenge lies in effectively matching these two pieces of heterogeneous information. To address this issue, we propose a Proxy-based Scientific workflow retrieval approach, ProSwats, which selects a workflow as the Proxy for each text query to bridge the gap between textual and structural semantics. ProSwats consists of two stages: workflow pre-selection based on text similarity and workflow ranking based on a matching degree prediction model. The textual and structural features are integrated by the proxy in this model, which is used to predict and rank the degree of semantic matching between the user query and candidate workflows. Crucially, ProSwats incorporates a confidence-aware learning mechanism to adapt to the varying reliability of proxies, enhancing generalizability. Extensive experimental results on two real-world datasets demonstrate that ProSwats outperforms state-of-the-art methods with statistical significance.

In business processes, anomalies are prevalent, arising from diverse factors, such as software malfunctions and operator errors. Detecting these anomalies is imperative, as it significantly influences not only the financial well-being of a business but also the dependability of event logs for subsequent analysis. However, existing deep business process anomaly detection approaches either lack effective temporal dependency modeling between events or encounter challenges associated with gradient vanishing. In this paper, we introduce COMB, which stands for an interConnected transfOrmers-based autoencoder for Multi-perspective Business process anomaly detection. Considering the interdependent nature of multi-perspectives, COMB leverages multiple parallel and interconnected transformers, facilitated by the inclusion of aggregation layers. These layers serve as integration points for information from various perspectives. Notably, considering how control flow influences other perspectives, COMB incorporates innovative mask adapters to enhance its detection performance. Furthermore, we propose a novel method for calculating anomaly scores, which effectively mitigates the influence of varying numbers of potential attribute values. Our extensive experimental evaluation encompasses both synthetic and real-life logs, and the results clearly demonstrate that COMB outperforms state-of-the-art methods in both trace-level and attribute-level anomaly detection.

Summary Finding similar scientific workflow modules that can substitute essential components of the privacy workflows from public repositories to create a personalized workflow is growing in popularity. This is a cost‐effective and error‐free strategy for the scientific community. Currently, module alignment approaches heavily depend on syntactic information such as modules' names and types. However, the contextual semantic information of modules, which encompasses inputs, outputs, and datalinks connecting modules, can also convey their functions. Unfortunately, this information is scarcely utilized during the module alignment process. In this work, we propose a module alignment method based on neighbor information for scientific workflow (MANSOR). Specifically, we present a rule‐based attribute similarity computation approach for calculating initial module‐pair similarity in two workflows. The relation similarity is then employed to iteratively fine‐tune the matching degree with uncertainty of module pairs by considering the contextual semantics until reaching a steady state. After pairwise comparison of workflows, the module alignment results are determined based on their module‐pair similarity. Experimental results on the human‐curated corpus of ratings indicate that MANSOR outperforms the existing state‐of‐the‐art approaches with statistical significance.

The role of focal packages in packaging ecosystems is crucial for the development of the entire ecosystem, as they are the packages on which other packages depend. However, the evolution of dependency groups in packaging ecosystems has not been systematically investigated. In this study, we examine the downstream dependency package groups (DDGs) in three typical packaging ecosystems—Cargo for Rust, Comprehensive Perl Archive Network for Perl, and RubyGems for Ruby—to identify their features and evolution. We also identify and analyze a special type of DDG, the collaborative downstream dependency package group (CDDG), which requires shared contributors. Our findings show that the overall development of DDGs, particularly CDDGs, is consistent with the status of the whole ecosystem, and the size of DDGs and CDDGs follows a power law distribution. Furthermore, the interaction mechanisms between focal packages and downstream packages differ between ecosystems, but focal packages always play a leading role in the development of DDGs and CDDGs. Finally, we investigate predictive models for the development of CDDGs in the next stage based on their features, and our results show that random forest and Gradient Boosting Regression Tree achieve acceptable prediction accuracy. We provide the raw data and scripts used for our analysis at https://github.com/onion616/DDG .

Security and trust have become the key issues in the Internet of Things (IoT) environment. Characterized by the centralized control and high-energy consumption, the traditional trust management schemes are not suitable for the IoT systems, in which most of the interactions are short-duration, random and maybe one-time, and the terminal devices always have resource constraints. Therefore, this article proposes a distributed and two-layered trust management framework based on blockchain architecture for IoT. The hierarchical architecture of the cloud, the edge, the IoT subgroups, and devices solves the resource limitation problem and improves the privacy protection of the IoT applications. And a novel lightweight$Q$-learning improved DPoS consensus algorithm named QV-DPoS is proposed to solve the problems of large energy consumption and high complexity of consensus mechanism of blockchain. Ethereum is used to build a blockchain-based IoT prototype system, and some experiments were designed to verify whether the proposed platform can successfully conduct trust management and achieve identity and behavior authentication between the IoT entities. Moreover, the simulation experiments based on NetLogo is also designed to test the performance of the trust and consensus mechanisms. The results of the experiments show that the proposed mechanisms can effectively enhance the credibility of the interactions in the IoT environments, improve the transaction success rate, and reduce energy consumption at least 10% compared with the traditional algorithms.

With the wide application of recommender systems, the potential impacts of recommender systems on customers, item providers and other parties have attracted increasing attention. Fairness, which is the quality of treating people equally, is also becoming important in recommender system evaluation and algorithm design. Therefore, in the past years, there has been a growing interest in fairness measurement and assurance in recommender systems. Although there are several reviews on related topics, such as fairness in machine learning and debias in recommender systems, they do not present a systematic view on fairness in recommender systems, which is context aware and has a multi-sided meaning. Therefore, in this review, the concept of fairness is discussed in detail in the various contexts of recommender systems. Specifically, a comprehensive framework to classify fairness metrics is proposed from four dimensions, i.e.,Fairness for Whom,Demographic Unit,Time Frame, andQuantification Method. Then the strategies for eliminating unfairness in recommendations, fairness in different recommendation tasks and datasets are reviewed and summarized. Finally, the challenges and future work are discussed.

The ability to detect anomalies in business processes is crucial for achieving success in business operations. While unsupervised anomaly detection approaches have gained popularity in recent years due to their label-free nature, in some cases, a limited number of labelled anomalies can be provided and using them can improve the performance of anomaly detection. To address this issue, we propose a novel framework for anomaly detection that uses a pre-trained autoencoder to extract feature representations of traces. An anomaly score generator based on a multi-layer perceptron is utilized to evaluate the extracted features. The entire framework is trained using a joint loss that ensures the generated anomaly scores satisfy a specific distribution without compromising the autoencoder's ability to reconstruct normal traces. The feature encoder is fine-tuned to provide insights into the cause of anomalies. Additionally, we design a novel technique for calculating anomaly scores to mitigate the effects of varying numbers of potential attribute values. We conduct extensive experiments on both synthetic and real-life logs, and our results demonstrate that our proposed method, WAKE, outperforms state-of-the-art unsupervised deep business process anomaly detection methods by a significant margin. Additionally, it outperforms other weakly supervised anomaly detection methods as well

When only users’ preferences and interests are considered by a recommendation algorithm, it will lead to the severe long-tail problem over items. Therefore, the unfair exposure phenomenon of recommended items caused by this problem has attracted widespread attention in recent years. For the first time, we reveal the fact that there is a more serious unfair exposure problem in session-based recommender systems (SRSs), which learn the short-term and dynamic preferences of users from anonymous sessions. Considering the fact that in SRSs, recommendations are provided multiple times and item exposures are accumulated over interactions in a session, we define new metrics both for the fairness of item exposure and recommendation quality among sessions. Moreover, we design a dynamic F airness- A ssurance ST rategy for s E ssion-based R ecommender systems ( FASTER ). FASTER is a post-processing strategy that tries to keep a balance between item exposure fairness and recommendation quality. It can also maintain the fairness of recommendation quality among sessions. The effectiveness of FASTER is verified on three real-world datasets and five original algorithms. The experiment results show that FASTER can generally reduce the unfair exposure of different session-based recommendation algorithms while still ensuring a high level of recommendation quality.

For software-defined networking (SDN), multi-field packet classification plays a key role in the processing of flows, mainly involving fast packet classification and dynamic rule updates. Due to the increasing complexity and size of rulesets, it is becoming more difficult to design a packet classification algorithm which achieves fast lookup and update. In this paper, we propose a novel structure, PT-Tree, for packet classification with high overall performance. PT-Tree cascades the prefixes of multiple discriminatory bytes to achieve efficient partitioning of the ruleset, thereby reducing the search space and ensuring the performance of both lookup and update. Meanwhile, a multi-granularity priority-aware pruning mechanism (MPPM) based on PT-Tree filters out most of the candidate subsets, which further improves the lookup speed. In addition, we propose an auxiliary tree-based optimization method (ATOM) to cope with severely overlapping rules in the search space. Therefore, PT-Tree can better handle the case where the rules in certain fields are skewed. We conduct comprehensive experiments to evaluate the performance of PT-Tree. The results show that compared with the state-of-the-art, the lookup time of PT-Tree is reduced by at least 49.95% on average. Moreover, PT-Tree is also at least 7.13x and 33x faster than the baselines in terms of the update and construction speed on average, respectively. Meanwhile, the performance stability of PT-Tree on multiple rulesets improves by up to 13.68 times.

Packet classification, as a crucial function of networks, has been extensively investigated. In recent years, the rapid advancement of software-defined networking (SDN) has introduced new demands for packet classification, particularly in supporting dynamic rule updates and fast lookup. This paper presents a novel structure called DBTable for efficient packet classification to achieve high overall performance. DBTable integrates the strengths of conventional packet classification methods and neural network concepts. Within DBTable, a straightforward indexing scheme is proposed to eliminate rule replication, thereby ensuring high update performance. Additionally, we propose an iterative method for generating a discriminative bitset (DBS) to evenly partition rules. By utilizing the DBS, rules can be efficiently mapped in a hash table, thus achieving exceptional lookup performance. Moreover, DBTable incorporates a hybrid structure to further optimize the worst-case lookup performance, primarily caused by data skewness. The experiment results on 12 256k rulesets show that, compared to seven state-of-the-art schemes, DBTable achieves an overall lookup speed improvement ranging from 1.53x to 7.29x, while maintaining the fastest update speed.

Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification. The limitation is evident in the application stage as the heavy computation for extracting patch-level features is inevitable. In this paper, we develop RLogist, a benchmarking deep reinforcement learning (DRL) method for fast observation strategy on WSIs. Imitating the diagnostic logic of human pathologists, our RL agent learns how to find regions of observation value and obtain representative features across multiple resolution levels, without having to analyze each part of the WSI at the high magnification. We benchmark our method on two whole-slide level classification tasks, including detection of metastases in WSIs of lymph node sections, and subtyping of lung cancer. Experimental results demonstrate that RLogist achieves competitive classification performance compared to typical multiple instance learning algorithms, while having a significantly short observation path. In addition, the observation path given by RLogist provides good decision-making interpretability, and its ability of reading path navigation can potentially be used by pathologists for educational/assistive purposes. Our code is available at: https://github.com/tencent-ailab/RLogist.

Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities. Recently, personalized FL (pFL) has received attention for its ability to address statistical heterogeneity and achieve personalization in FL. However, from the perspective of feature extraction, most existing pFL methods only focus on extracting global or personalized feature information during local training, which fails to meet the collaborative learning and personalization goals of pFL. To address this, we propose a new pFL method, named GPFL, to simultaneously learn global and personalized feature information on each client. We conduct extensive experiments on six datasets in three statistically heterogeneous settings and show the superiority of GPFL over ten state-of-the-art methods regarding effectiveness, scalability, fairness, stability, and privacy. Besides, GPFL mitigates overfitting and outperforms the baselines by up to 8.99% in accuracy.

Medical tests are crucial for treatment decision making. However, over-testing can often occur in any medical speciality or level of expertise. Since over-testing usually results in a financial burden for patients and is also a waste of medical resources, this naturally leads to the question: which medical test items (MTIs) are necessary and should be prioritized for the target patients? It is a nontrivial task to identify the right MTIs due to the diversified health status of patients and the complicated prerequisites of therapies. To this end, in this paper, we propose a data-driven approach to evaluate the priority which should be given to MTIs by modeling the relationships between MTIs and therapies. Specifically, we first develop a dual hierarchical topic model (DHTM), which views the adopted hierarchical therapies as labeled topics and the MTI reports, i.e., the set of hierarchical attribute-value pairs (AVPs), as documents. Then, with the therapy-AVP distribution and the partial MTI reports of the target patient, we can scope the candidate therapies, which are further utilized to evaluate the accumulated gain of MTIs to be tested. Moreover, the next MTI recommendation is conducted based on the gains. Finally, extensive experiments on real-world medical data validate the effectiveness of our approach, and some interesting observations are also provided. The code is available at https://github.com/mtirec/MtiRec.

Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities. However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and further degenerate generic representations during local training, i.e., the representation degeneration phenomenon. To address these issues, we propose a general framework Domain Bias Eliminator (DBE) for FL. Our theoretical analysis reveals that DBE can promote bi-directional knowledge transfer between server and client, as it reduces the domain discrepancy between server and client in representation space. Besides, extensive experiments on four datasets show that DBE can greatly improve existing FL methods in both generalization and personalization abilities. The DBE-equipped FL method can outperform ten state-of-the-art personalized FL methods by a large margin. Our code is public at https://github.com/TsingZ0/DBE.

Content-based publish/subscribe systems are widely used in many fields.Event matching is the core component to achieve fine-grained content-based data distribution.Many efficient algorithms have been proposed to improve event matching performance.However, in large-scale content-based publish/subscribe systems, event matching is still the performance bottleneck of the entire system due to the need to perform a lot of operations, such as additions, comparisons and bitmarkings.In this paper, we explore to convert various nonlogical operations into efficient logical ones, and propose a bitsetbased optimization paradigm (BOP) for matching algorithms.On the one hand, BOP can eliminate expensive operations in the matching process, greatly improving matching performance.On the other hand, BOP can stabilize the performance of matching algorithms, ensuring the quality of service of data distribution.We apply BOP to optimize two existing matching algorithms, namely TAMA and REIN.The experimental results show that BOP shortens the matching time of TAMA and REIN by more than 60%.In addition, the performance of optimized versions is more stable than the original matching algorithms.

The active participation of contributors is key to the success of any open source software (OSS) projects.In the open source community, it can be found that some developers have participated together in multiple projects and also built social connections so that they form an independent team.Independent teams can be high-quality developer candidates for OSS projects.By modeling the developers and independent teams, we design approaches to recommend independent teams to OSS projects.We used the interaction data between developers to build the developers' social connection network, on which independent teams can be discovered by utilizing the community discovery algorithm.Based on the graph attention network, we designed a team recommendation model GAT-team.The performance of the GAT-team is evaluated on a real-world dataset.GAT-team achieves much better results compared with the other algorithms in the experiments.We provide the data and the code at https://

Accurately forecasting workloads in terms of throughput that is quantified as queries per second (QPS) is essential for microservices to elastically adjust their resource allocations. However, long-term QPS prediction is challenging in two aspects: 1) generality across various services with different temporal patterns, 2) characterization of intricate QPS sequences which are entangled by multiple components. In this paper, we propose a knowledge auto-embedding Informer network (KAE-Informer) for forecasting the long-term QPS sequences of microservices. By analyzing a large number of microservice traces, we discover that there are two main decomposable and predictable components in QPS sequences, namely global trend & dominant periodicity (TP) and low-frequency residual patterns with long-range dependencies. These two components are important for accurately forecasting long-term QPS. First, KAE-Informer embeds the knowledge of TP components through mathematical modeling. Second, KAE-Informer designs a convolution ProbSparse self-attention mechanism and a multi-layer event discrimination scheme to extract and embed the knowledge of local context awareness and event regression effect implied in residual components, respectively. We conduct experiments based on three real datasets including a QPS dataset collected from 40 microservices. The experiment results show that KAE-Informer achieves a reduction of MAPE, MAE and RMSE by about 16.6%, 17.6% and 23.1% respectively, compared to the state-of-the-art models.

Summary When large‐scale content‐based publish/subscribe systems face dynamic workloads, it is challenging to stabilize event delivery latency. In this article, we propose a latency‐aware parallelism framework (Lap) to address this challenge. Specifically, we propose a lightweight parallelism method called PhSIH for event matching algorithms. In addition, we design a reactive parallelism degree adjustment (RPDA) mechanism in the backpressure way to determine the parallelism degree. We implement Lap in Apache Kafka and evaluate the parallelism effect of PhSIH and the adaptability of RPDA on trace data. The experiment results demonstrate that PhSIH achieves linear speedup on three existing algorithms and RPDA possesses a desirable adaptability to the dynamic workloads.

The efficient cloud resource provisioning for the execution of complex workflow applications has always been one of the important research issues. Most of the existing approaches focus on the resource provisioning of single-type virtual machine (VM) instances for the single or multiple workflows, while few consider the situation of provisioning multi-type VM instances simultaneously. As a result, the executing performance of complex workflows degrades. Different from the existing work, this paper proposes an adaptive cloud bundle provisioning and multi-workflow scheduling model to dynamically perform both the horizontal and vertical cloud resource scaling on multi-type VM instances for the execution of complex workflows. Among the model, a depth-first-search coalition reinforcement learning (DFSCRL) provisioning policy is presented to realize the resource scaling, which integrates the physical machine (PM) coalition formation with the Q-learning algorithm, then dynamically generates an optimal multi-type VM instance bundle from the PM coalition, and finally provisions these instances to the concurrent execution of multiple workflows. The theoretical proofs and various experiments with the multifaceted metrics demonstrate that the performance of the proposed algorithms is superior to that of the state-of-the-art relevant policies.

Online map matching is essential for some location-based services, such as car navigation. However, due to GPS measurement errors and/or the lack of sufficient information, the performance of most existing online algorithms will degrade in the increasingly complex traffic environment. In this paper, we propose an adaptive online map matching algorithm called AMM. The basic idea is that AMM should be able to calibrate GPS observation data for various measurement errors and under complex urban conditions. First, we establish a collaborative evaluation model between GPS points and candidate points to effectively filter low-quality GPS measurement points, dynamically set the weights of different features and comprehensively select the best candidate points. Second, we propose a retrospective correction mechanism to correct the previous matching results when more information is available, which will help improve the accuracy of future GPS points. Furthermore, we define parameter self-tuning rules for AMM to enhance its portability by avoiding time-consuming parameter tuning steps. We conduct extensive experiments to evaluate the performance of AMM on real vehicle trajectory datasets. The experiment results show that AMM outperforms its counterparts by up to 32% in terms of accuracy and its performance in different traffic conditions is more stable.

A session-based recommendation system (SRS) tries to predict the next possible choice of anonymous users. In recent years, graph neural network (GNN) models have been successfully applied to SRSs and have achieved great success. Using GNN models in SRSs, each session graph is processed successively to obtain the embedding of the node (i.e, each action on an item), which is then imported into the prediction module to generate recommendation results. However, solely depending on the session graph to obtain the node embeddings is not sufficient because each session only involves a few items. Therefore, neighbor sessions have been used to extend the session graph to learn more informative node representations. In this paper, we introduce a S ession-based recommendation MO del based on N eighbor sessions with similar probabilistic int E ntions(SMONE). SMONE models the intentions behind sessions in a probabilistic way and retrieves the neighbor sessions with similar intentions. After the neighbor sessions are found, the target session and its neighbor sessions are modeled as a hypyergraph to learn the contextualized embeddings, which are combined with item embeddings through GNN to produce the final item recommendations. Experiments on real-world datasets prove the effectiveness and superiority of SMONE.

Predictive monitoring of business processes aims at forecasting the future information of a business process and has gained increasing attention in recent years. With the development of cloud computing, prediction models, including remaining time prediction models, can be provided as cloud services. Reducing the number of invocation times of a remaining time prediction service is necessary since a large quantity of business process instances may be initiated and monitored every day. However, most of the current research focuses on designing new algorithms to improve prediction accuracy but there is no approach available to decide when to invoke a prediction service for each business process instance. In this article, we propose a deep reinforcement learning based strategy that can learn the policies of selecting prediction points for the remaining time prediction. Specifically, the learned policies can dynamically decide the next prediction point at which the remaining time prediction service will be invoked for a business process instance. We performed extensive experiments on five real-world datasets. The experiment results show this strategy can reduce the number of prediction points significantly and still maintain the high prediction accuracy.

Finding scientific workflow models that can be reused or repurposed from public repositories is becoming popular in the scientific community. Currently, the retrieval approaches for workflow models are mainly based on text matching between queries and the descriptions of models. However, the structure information of these models, which includes inputs, outputs, data processing modules, and datalinks connecting modules, expresses their functions in a more detailed manner, yet this information is not used in the model retrieval process. Therefore, we propose a two-stage framework for Scientific WOrkflow Retrieval by learning Textual and Structural semantics (SWORTS). The framework comprises a workflow pre-selection step and a workflow ranking step. Specifically, we use text similarity approaches to quickly identify candidate workflow models in the first step. Then, a hierarchy-based matching degree prediction model, which takes both textual and structural features into account, is trained to predict and rank the degree of semantic matching between requirement specifications and candidate workflows. The experiment results on real-world datasets demonstrate that SWORTS achieves the best performance with relatively balanced effectiveness and efficiency among state-of-the-art methods.

In process-aware information systems (PAISs), anomalies are ubiquitous, having a number of different underlying causes, such as software malfunctions or operator errors. The presence of anomalies not only has an enormous impact on the economic well-being of the business, but also interferes with our ability to mine useful information from event logs. In this article, we propose GRASPED, aGRU-AE Network based multi-perSpective business ProcEss anomalyDetection model. GRASPED can detect anomalies not only from the control flow but also from the data perspective of a business process. GRASPED is based on an autoencoder (AE) with gated recurrent units (GRU) which is trained in an unsupervised fashion (i.e., does not require any labeling of the data). In addition, GRASPED introduces the teacher forcing method as well as the attention mechanism to improve its detection performance. GRASPED does not require training on a clean log (i.e., it can be trained and perform anomaly detection directly on logs containing anomalies). We conduct extensive experiments on synthetic logs as well as real-life logs. The experiment results show that GRASPED outperforms the state-of-the-art methods for both trace-level and attribute-level anomaly detection.

Multi-task learning (MTL) aims at solving multiple related tasks simultaneously and has experienced rapid growth in recent years. However, MTL models often suffer from performance degeneration with negative transfer due to learning several tasks simultaneously. Some related work attributed the source of the problem is the conflicting gradients. In this case, it is needed to select useful gradient updates for all tasks carefully. To this end, we propose a novel optimization approach for MTL, named GDOD, which manipulates gradients of each task using an orthogonal basis decomposed from the span of all task gradients. GDOD decomposes gradients into task-shared and task-conflict components explicitly and adopts a general update rule for avoiding interference across all task gradients. This allows guiding the update directions depending on the task-shared components. Moreover, we prove the convergence of GDOD theoretically under both convex and non-convex assumptions. Experiment results on several multi-task datasets not only demonstrate the significant improvement of GDOD performed to existing MTL models but also prove that our algorithm outperforms state-of-the-art optimization methods in terms of AUC and Logloss metrics.

Multi-task learning (MTL) has experienced rapid growth in recent years. A typical way of conducting MTL with deep neural networks (DNNs) is either establishing a sort of global feature sharing mechanism across all tasks or assigning each task an individual set of parameters with cross-connections. However, these existing approaches leverage DNNs only to share features of a certain order. Several modelsdemonstrated that explicitly modeling feature sharing with both low-order and high-order features can boost performance. To this end, we propose a model-agnostic sparse routing architecture called MASR, which emphasizes arbitrary order feature sharing for multi-task learning. It is able to choose specific orders of features to route for a given task through learnable latent variables. Moreover, MASR is model-agnostic and can be combined with existing MTL models to share features of both low-order and high-order. Extensive experimental results on several real-world datasets not only confirm the significant improvement of MASR performed to existing MTL models but also outperform existing hybrid architectures in terms of AUC metric.

When incoming events arrive too quickly, edge nodes cannot process all events since they only have limited resources. Therefore, we propose a CLoud-edge dynamic cOllaborative Strategy for complex Event Detection (CLOSED). We consider the case where a composite event may involve primitive events from more than one edge node and model the composite event detection task allocation as an optimization problem to minimize the communication costs for both event detection and event notification among cloud centers and edge nodes. We propose the MINimized Event Transmission time-based detection node selection algorithm (MINET) to solve this problem. Moreover, we propose a Reward-based composite event detection Task Migration Algorithm (RTMA) to migrate event detection tasks when edge nodes are overloaded. By evaluating CLOSED on a simulated dataset and different workload patterns , we prove that this strategy can significantly improve event detection efficiency.

Data analysis reveals that passengers can only endure a few minutes before taking a taxi. However, most existing route recommendation systems are not adequate to satisfy impatient customers due to two shortcomings: inaccurate demand forecast and the lack of an efficient supply-demand balance mechanism. In this paper, we propose a recommendation system called @ Me, which aims to dispatch vacant taxis to the vicinity of potential customers at the right time. To achieve minute-level demand forecasting, we ensemble a contextualized spatial-temporal network (CSTN) with an LSTM network to optimize prediction accuracy. In addition, we characterize the attractiveness of the road grid to vacant taxis as a force model, on which a taxi scheduling algorithm is proposed to dynamically balance supply and demand. Extensive experiments on real datasets clearly indicate that our method is superior to the selected baselines. Vacant taxis that follow the routes suggested by @ME can catch more impatient customers in a shorter cruising time. The 7 -day experimental results on the Manhattan dataset show that @Me can carry an additional 48,332 passengers and increase drivers' revenue by $570,317.

Content-based publish/subscribe systems are an effective paradigm for implementing on-demand event distribution.Each event needs to be matched against subscriptions to identify the target subscribers.To improve the matching performance, many novel data structures have been proposed.However, the predicates included in subscriptions are handled the same way in most existing data structures, which is not efficient given the matching probability of predicates.In this paper, we propose a parallel ensemble matching framework called PEM, which uses multiple algorithms with complementary behavior on predicate matching probabilities.To achieve the performance balance of parallel matching, we design an elastic subscription classification method.We implement a prototype of PEM based on two existing algorithms.The experiment results show that PEM improves the matching performance by 43%.

The content-based publish/subscribe system is an effective paradigm for implementing on-demand event distribution. Each event needs to be matched against subscriptions to identify the target subscribers. To improve the matching performance, many novel data structures have been proposed. However, the predicates contained in subscriptions are handled the same way in most existing data structures, without considering their differences in matching probability. In this paper, we propose the concept of parallel ensemble matching (PEM) based on subscription partitioning. The basic idea is that we have the right algorithm handling the right subscriptions at the right time. First of all, we design a PEM framework by classifying subscriptions according to their matching probabilities and use the proper algorithms to process each subscription category. Furthermore, to deal with high-dimensional subscriptions, we propose a fine-grained PEM (fgPEM) that exploits matching algorithms with complementary behaviors by partitioning subscriptions into sub-subscriptions. We implement the prototype of PEM and fgPEM based on two existing algorithms. The experiment results show that PEM improves the matching performance by 43%. On the basis of PEM, fgPEM further improves the performance by 31%.

Researchers have proposed many novel methods to detect abnormal taxi trajectories. However, most of the existing methods usually adopt a counting-based strategy, which may cause high false positives due to imprecisely identifying diverse trajectories as anomalies and therefore, they need the support of large-scale historical trajectories to work properly. To improve detection precision and efficiency, in this article, we propose STR, an online abnormal taxi trajectory detection method based on spatio-temporal relations. The basic principle behind STR is that given the displacement from the source point to a testing point, if the driving time and driving distance are not within the normal ranges, the point is identified as anomalous. To learn the two normal ranges for driving time and driving distance, STR defines two spatio-temporal models which characterize the relationship between displacement and driving distance/driving time. To improve detection efficiency, STR reduces the number of models that need to be learned by making full use of the similarity of transportation modes in different time periods and neighboring areas. The effectiveness and performance of STR are evaluated on real-world taxi trajectories. The experiment results show that compared with counting-based methods, STR achieves greater precision by reducing false positives. Furthermore, STR is more efficient than its counterparts and is suitable for online detection.

The understanding of people’s inter-regional mobility behaviors, such as predicting the next activity region (AR) or uncovering the intentions for regional mobility, is of great value to public administration or business interests. While there are numerous studies on human mobility, these studies are mainly from a statistical view or study movement behaviors within a region. The work on individual-level inter-regional mobility behavior is limited. To this end, in this article, we propose a dynamic region-relation-aware graph neural network (DRRGNN) for exploring individual mobility behaviors over ARs. Specifically, we aim at developing models that can answer three questions: (1) Which regions are the ARs? (2) Which region will be the next AR, and (3) Why do people make this regional mobility? To achieve these tasks, we first propose a method to find out people’s ARs. Then, the designed model integrates a dynamic graph convolution network (DGCN) and a recurrent neural network (RNN) to depict the evolution of relations between ARs and mine the regional mobility patterns. In the learning process, the model further considers peoples’ profiles and visited point-of-interest (POIs). Finally, extensive experiments on two real-world datasets show that the proposed model can significantly improve accuracy for both the next AR prediction and mobility intention prediction.

A session-based recommender system (SBRS) captures users’ evolving behaviors and recommends the next item by profiling users in terms of items in a session. User intent and user preference are two factors affecting his (her) decisions. Specifically, the former narrows the selection scope to some item types, while the latter helps to compare items of the same type. Most SBRSs assume one arbitrary user intent dominates a session when making a recommendation. However, this oversimplifies the reality that a session may involve multiple types of items conforming to different intents. In current SBRSs, items conforming to different user intents have cross-interference in profiling users for whom only one user intent is considered. Explicitly identifying and differentiating items conforming to various user intents can address this issue and model rich contextual information of a session. To this end, we design a framework modeling user intent and preference explicitly, which empowers the two factors to play their distinctive roles. Accordingly, we propose a key-array memory network (KA-MemNN) with a hierarchical intent tree to model coarse-to-fine user intents. The two-layer weighting unit (TLWU) in KA-MemNN detects user intents and generates intent-specific user profiles. Furthermore, the hierarchical semantic component (HSC) integrates multiple sets of intent-specific user profiles along with different user intent distributions to model a multi-intent user profile. The experimental results on real-world datasets demonstrate the superiority of KA-MemNN over selected state-of-the-art methods.

An increasing number of services are being offered which leads to difficulties in choosing appropriate services during mashup development. Currently, several service recommendation techniques have been developed for mashup creation, however, they are largely limited to suggesting services which have similar functionalities. The fundamental problem with these techniques is that they do not consider the large semantic gap between mashup descriptions and service descriptions. In this article, we propose a compositional semantics-based service bundle recommendation model (CSBR) to tackle this problem. CSBR is based on a semantic service package repository, which is constructed by mining the existing mashups. Specifically, the reusable service packages, which consist of multiple collaborative services, are annotated with composite semantics rather than their original semantics. Based on the semantic service package repository, CSBR can recommend a bundle of services that cover the functional requirements of the mashup as completely as possible. Extensive experiments are conducted on a real-world dataset and the results show CSBR achieves significant performance improvements in both precision and recall metrics over the state-of-the-art methods.

Open source software (OSS) development is a highly collaborative process where individuals, groups and organizations interact to develop, operate and maintain software and related artifacts. The developers' sentiment in this process can have an impact on their working willingness and efficiency. Monitoring sentiment factors can help to improve OSS development and management. However, no method has been proposed to dynamically monitor the sentiment phenomena during the OSS development process. In this paper, an approach to detect Negative Sentiment-related Events (NSE) is proposed. It consists of two steps. The first step is to identify the burst interval of negative comments from open source projects, which corresponds to a NSE. The second step is to annotate this NSE with its event type. To support this approach, the types of NSEs in OSS projects are defined through an empirical study and classifiers are trained to annotate event types automatically. Moreover, conversation disentanglement techniques are employed to make the comments extracted more complete. Finally, the factors that have an influence on NSEs in the OSS project are studied.

Open source software development (OSSD) projects is a collaborative process among developers and volunteers with common interests. OSSD is increasingly becoming a trend and many successful OSSD projects have contributed software packages which have been widely adopted. Unfortunately, there is Pareto principle in OSSD projects, and a large number of OSSD projects have little influence, many projects a re unable to attract user interest. Therefore, it is important to understand the factors affecting OSSD project success as measured by project popularity. While technical factors such as license and compatibility with certain operating systems have a direct influence on the popularity of OSSD projects, development-related factors also have latent impacts on the popularity of OSSD projects. Therefore, we collect data on 445 projects and successfully build a structural equation model (SEM) which depicts the inherent relationships between development-related factors and OSSD project popularity. The steps to build the SEM and the implications of this model are discussed in detail in this paper.

While language-learning apps have empowered many users to learn languages inexpensively, the underlying technology limits the tasks they can offer to atomic, flashcard-like exercises. In this paper we present an algorithm that can effectively estimate memory traces from user interaction data that is generated in complex language learning tasks such as extensive reading. This technology can be applied to develop complex, intrinsically-motivating, high-value learning tasks based around long texts, television series or podcasts.

k-nearest neighbors algorithm ( k-NN) is a simple yet powerful method that can predict an unlabeled object using the k closest samples whose labels are already known. However, in some cases such as medical treatment decision making, multiple experts can provide their individual decisions and there is no single ground truth for the labels of samples. As a result, the accuracy of the predictions can be affected by the uncertainties of historical decisions. In order to learn from uncertain decisions from multiple experts, we propose a new k-NN algorithm. This algorithm firstly measures the uncertainties of labels. Then, the prediction is made based on the uncertain labels of the k closest samples based on the Dempster-Shafer theory. We also introduce two methods to compute the optimal k value. Experiments on a real-world medical treatment dataset prove that our algorithm has better performance compared with other algorithms.

In recent years, several optimal airline ticket purchasing strategies have been proposed and most of them are based on predicted price information. However, risks of ticket sold out and price uncertainties have not been modeled or considered by these strategies, which limits their effectiveness. Therefore, we design a recommendation service that is based on a new optimal airline ticket purchasing strategy PACES (Path Cost Expectation-based Strategy), which models and considers the risks and uncertainties of ticket purchasing explicitly. Extensive experiments are conducted on a real-world dataset and the results show that this strategy significantly outperforms the state-of-the-art techniques.

At present, most research on the fairness of recommender systems is conducted either from the perspective of customers or from the perspective of product (or service) providers. However, such a practice ignores the fact that when fairness is guaranteed to one side, the fairness and rights of the other side are likely to reduce. In this paper, we consider recommendation scenarios from the perspective of two sides (customers and providers). From the perspective of providers, we consider the fairness of the providers' exposure in recommender system. For customers, we consider the fairness of the reduced quality of recommendation results due to the introduction of fairness measures. We theoretically analyzed the relationship between recommendation quality, customers fairness, and provider fairness, and design a two-sided fairness-aware recommendation model (TFROM) for both customers and providers. Specifically, we design two versions of TFROM for offline and online recommendation. The effectiveness of the model is verified on three real-world data sets. The experimental results show that TFROM provides better two-sided fairness while still maintaining a higher level of personalization than the baseline algorithms.

The cloud-fog-edge hybrid system is the evolution of the traditional centralized cloud computing model. Through the combination of different levels of resources, it is able to handle service requests from terminal users with a lower latency. However, it is accompanied by greater uncertainty, unreliability, and instability due to the decentralization and regionalization of service processing, as well as the unreasonable and unfairness in resource allocation, task scheduling, and coordination, caused by the autonomy of node distribution. Therefore, this paper introduces blockchain technology to construct a trust-enabled interaction framework in a cloud-fog-edge environment, and through a double-chain structure, it improves the reliability and verifiability of task processing without a big management overhead. Furthermore, in order to fully consider the reasonability and load balance in service coordination and task scheduling, Berger’s model and the conception of service justice are introduced to perform reasonable matching of tasks and resources. We have developed a trust-based cloud-fog-edge service simulation system based on iFogsim, and through a large number of experiments, the performance of the proposed model is verified in terms of makespan, scheduling success rate, latency, and user satisfaction with some classical scheduling models.

For large-scale spatiotemporal-aware publish/subscribe systems, it is critical to design an efficient forwarding engine to achieve fast matching and maintenance of events and subscriptions. For this goal, we propose a novel data structure called MO-Tree to index both subscriptions and events in a unified way. The design philosophy behind MO-Tree is to keep the data structure concise, which manifests in three aspects: limiting the height of MO-Tree, trading space for time, and avoiding node merging and splitting. The difficulty in designing MO-Tree is how to efficiently index width-variable intervals. We present a multi-level cell-overlapping partition scheme and build a theoretical model to optimize the cell width in each level. To evaluate the performance of MO-Tree, a series of experiments is conducted on real-world trace datasets. The experiment results show MO-Tree significantly outperforms the state-of-the-art in terms of matching speed and maintenance cost.

Cloud service selection is becoming more complex with the arrival of a large number of cloud providers offering various service packages on the market. These cloud service packages are generally provisioned by Spot, On-demand and Reserved Instances. Typically, a user's service requirements contain many independent sub-tasks (Bag-of-Tasks), and have budget limitations and additional constraints. To select reasonable cloud instances to run the user's sub-tasks, we propose a strategy, OSPN (Optimal Service Provisioning with Negotiation), to support the allocation of tasks to services offered by multi-cloud providers. OSPN consists of two phases: in the first phase, a one-to-many parallel Spot Instance pricing negotiation is applied; in the second phase, service provisioning strategy profiles on the three types of cloud instances are calculated. Specifically, the first phase employs an improved double auction in which the price and availability of providers' instances are taken into account; then the second phase gives the utility Nash equilibrium model and derives the optimal provisioning strategy profiles. The experimental results show that our service provisioning strategy is more cost-effective, namely, the most gains of both the user and providers in the changing scenes, and the least payments of the user than the existing relevant strategies.

With the development of cloud computing and the advent of the Web 2.0 era, composing a set of Web services as a service process is becoming a common practice to provide more functional services. However, a service process involves multiple service invocations over the network, which incurs a huge time cost and could become a bottleneck to performance. To accelerate its execution, we propose an engine-side cache-block-based service process caching strategy (CBPCS). It is based on, and derives its advantages from, three key ideas. First, the invocation of Web services embodies semantics, which enables the application of semantic-based caching. Second, cache blocks are identified from a service process, and each block is equipped with a separate cache so that the time overhead of service invocation and caching can be minimized. Third, a replacement strategy is introduced taking into account time and space factors to manage the space allocation for a process with multiple caches. The algorithms and methods used in CBPCS are introduced in detail. Moreover, how CBPCS can be applied to multiple service process models is also investigated. Finally, CBPCS is validated via comparison experiments, which shows the considerable improvements of CBPCS over other strategies.

In the mashup ecosystem, Web APIs often form cooperative communities which evolve with time. Understanding how these communities form and evolve with time is very important to help develop strategies for improving ecosystems of Web APIs. This paper empirically studies the evolution of Web API cooperative communities based on the data of Web APIs and mashups from Programmable Web. It is found that 20% of Web APIs account for half of the connections in their communities. The Web API communities identified in terms of mashups seem to be stable. Every two years, there is a 27% growth in the number of new communities, 10% dissolve, 30% tend to expand, while 5% become smaller. It is a key stage when a Web API community becomes medium sized because in this stage, there is a high probability that a Web API community reduces its size or even dissolves.

Cross-domain recommendation can alleviate data sparsity problems by leveraging data from multiple domains. Hence it is becoming an emerging research topic. Existing approaches based on latent factor models usually attempt to utilize cross-domain information in the form of inner product or Euclidean distance. This kind of form only enables the model to incorporate non-structure similarity relations between entities. However, the studies in the literature of consumer behavior have disclosed that consumers make decisions following a structural characteristic. Inspired by this, we propose a new cross-domain recommendation model, named PSRec, which learns and shares users' inherent preference structure information during their decision making in relation to their product choices in different domains. In PSRec, the latent factors of items of different domains are mapped to a common space so that the factorized user latent vectors have similar preference structures. Moreover, users' preference structure information is transferred from an auxiliary domain to a target domain as a constraint to a non-negative matrix factorization algorithm. Extensive experiments on two real-world datasets demonstrate the effectiveness and competitive performance of PSRec compared to several state-of-the-art solutions.

Although many matching algorithms have been proposed to improve the matching efficiency of the content-based publish/subscribe system, existing work seldom consider the real-time of event dissemination from the perspective of event matching. On the basis of two existing matching algorithms, in this paper, we propose a subscription-classifying and structure-layering (SCSL) optimization method for matching algorithms, aiming to improve real-time by shortening the determining time of matching subscriptions. The basic idea of SCSL is that subscriptions with high matching probabilities should be processed first in the process of event matching and their storage positions in the data structure should be adjusted in line with changing probabilities. One challenge of SCSL is the trade-off that needs to be made between the gains of improving real-time performance by identifying matching subscriptions earlier and the cost of increasing matching time due to subscription classification and adjustment. We design a concise scheme to classify subscriptions, establish a lightweight adjustment mechanism to deal with dynamics and propose an efficient greedy algorithm to compute the adjustment solution, which alleviates the impact of SCSL on matching performance. The experiment results show that the 95thpercentile of the determining time of matching subscriptions is improved by about 70%. Furthermore, we integrate SCSL into Apache Kafka to augment it as a content-based publish/subscribe system and test the effect of SCSL based on real-world stock trace data, which witnesses about 40% improvement on the average event transfer latency and confirms that SCSL can effectively improve the real-time performance of content-based publish/subscribe systems.

With the development of the internet technology, a large amount of softwares have emerged to meet users' increasing needs. At the mean time, software systems have been faced with a problem that they must adapt to the dynamic network environment. It is obvious that a variety of software development models have been proposed in the past few decades. However, the majority of these methods are gradually unadaptable to new circumstances. In this paper, we proposed a new software development model integrating collective intelligence, service and ecosystem. On the one hand, we have introduced the model in detail. On the other hand, We took a practical example to demonstrate the effectiveness of the proposed model.

In recent years, the organization of open source software development has evolved rapidly. Analyzing the behaviors of contributors helps us understand the development process of open source software and explore the general and special rules of it. Agent based model is a type of computing model that can simulate the behaviors and interactions between autonomous entities. With agent based models, we can simulate the self-organization process of open source software development by simulating contributors' behaviors. Therefore, we design an agent-based simulation system for open source software development, which are implemented with the Java Agent Development framework. In experiments, we obtain the simulation results by inputting historical behavior information of open source repositories on GitHub. Then we compare the results of various models. Finally, by adjusting input parameters for issue resolution process, we analyze the impact of these parameters, which shows this system also helps understand how to control the open source software development process.

The next-item recommendation has attracted great research interests with both static and dynamic users' preferences considered. Existing approaches typically utilize user-item binary relations, and assume a flat preference distribution over items for each user. However, this assumption neglects the hierarchical discrimination between user intentions and user preferences, causing the methods have limited capacity to depict intention-specific preference. In fact, a consumer's purchasing behavior involves a natural sequential process, i.e., he/she first has an intention to buy one type of items, followed by choosing a specific item according to his/her preference under this intention. To this end, we propose a novel key-array memory network (KA-MemNN), which takes both user intentions and preferences into account for next-item recommendation. Specifically, the user behavioral intention tendency is determined through key addressing. Further, each array outputs an intention-specific preference representation of a user. Then, the degree of user's behavioral intention tendency and intention-specific preference representation are combined to form a hierarchical representation of a user. This representation is further utilized to replace the static profile of users in traditional matrix factorization for the purposes of reasoning. The experimental results on real-world data demonstrate the advantages of our approach over state-of-the-art methods.

Recent years have witnessed an emerging trend for improving disease treatment by forming multi-disciplinary medical teams. The collaboration among specialists from multiple medical domains has been shown to be significantly helpful for designing comprehensive and reliable regimens, especially for incurable diseases. Although this kind of multi-disciplinary treatment has been increasingly adopted by healthcare providers, a new challenge has been introduced to the decision-making process—how to efficiently and effectively develop final regimens by searching for candidate treatments and considering inputs from every expert. In this article, we present a sophisticated decision support system called MdtDSS (a decision support system (DSS) for multi-disciplinary treatment (Mdt)), which is particularly developed to guide the collaborative decision-making in multi-disciplinary treatment scenarios. The system integrates a recommender system that aims to search for personalized candidates from a large-scale high-quality regimen pool and a voting system that helps collect feedback from multiple specialists without potential bias. Our decision support system optimally combines machine intelligence and human experience and helps medical practitioners make informed and accountable regimen decisions. We deployed the proposed system in a large hospital in Shanghai, China, and collected real-world data on large-scale patient cases. The evaluation shows that the proposed system achieves outstanding results in terms of high-quality multi-disciplinary treatment.

Financial fraud detection is an important topic in business intelligence, and neural networks have been effectively applied to construct detection models for this problem. Nevertheless, the timeliness of fitted models degrades over time when they are deployed in online detection systems. To maintain model performance when the labels of new transactions are not available, we propose an incremental virtual learning (IVL) method to update neural networks continually. The basic idea of IVL is to make the output distribution of neural networks smoother in the adversarial direction by unlabeled data. IVL uses local distribution smoothness (LDS) as the loss function at the unsupervised incremental learning stage. When updating a neural network by IVL, unlabeled data can be fed into the neural network periodically, so IVL can be implemented in a real online system without violating time constraints. To evaluate the effectiveness of IVL, experiments are conducted on a real dataset, demonstrating that neural networks augmented by IVL (IVL-NN) perform better than unoptimized neural networks in term of area under the curve (AUC). Furthermore, the standard deviation of the daily AUCs improves up to 19.09%, which indicates that IVL improves the stability of neural networks.

Teamwork is very important to software development. There are many studies focusing on different aspects of teamwork in open source software projects, but neglecting the fact that most teams of open source projects are temporary and dependent on the context of one specific project. Whether the collaboration of such teams can extend to different projects is highly doubted. In contrast, we are interested in long-lasting socially connected teams, whose members have steady social connections and have collaborated with each other on multiple projects. Therefore, we mine Cross-Repository Socially Connected (CRSC) teams on GitHub, the largest open-source project hosting platform. Community detection methods are used to mine CRSC teams from the developer network and more than 20,000 CRSC teams are discovered on GitHub. The productivity of such teams and how the hosting repository may influence them are studied. Their preferences for repositories are investigated. Moreover, we study the structures of these teams using complex network analysis methods. Our results indicate that CRSC teams are stable, highly productive and mature. Therefore, open-source project owners and recruiters can pay more attention to such teams.

Oceans are important for scientific research and also for global economic and military security. Usually, wireless ad hoc networks are chosen to transform real-time data collected by ocean monitoring sensors (nodes). Due to the random motion of waves or the random direction of the wind, nodes in the network might become detached from the coverage of the network. In this case, the detached nodes can either send the collected data directly to the base station at the cost of consuming more energy or wait for a period of time to rejoin the network with the price of sacrificing the real time of the collected data. In this paper, we model the optimal waiting time for detached nodes before directly sending the data in the dynamic environment of ocean monitoring. For this purpose, we need to address two problems. The first is how to calculate the rate of coverage with a different number and different broadcast radii of nodes. The second is when a node detaches from the coverage of the network, how much time will it need to wait before it rejoins the network. We first establish the motion model of nodes, which is the basis to deduce the probability distribution of a certain time when the detached node rejoins the network. Based on the probability distribution, the waiting time of the detached nodes can be optimally determined, aiming to achieve a good balance between energy consumption and data timeliness. Finally, a series of simulations is conducted to validate the effectiveness of our proposed method.

The matching algorithm is a critical component of the content-based publish/subscribe system, whose performance has direct effects on the QoS of the whole system. Aiming to improve and stabilize the matching performance, we propose a lightweight parallelization method called PhSIH on the basis of three existing algorithms. PhSIH fulfills Parallelization by horizontally Segmenting the Indexing Hierarchy of data structures to support multiple threads performing matching tasks in parallel on a common data structure. PhSIH can adaptively adjust the degree of parallelism according to the changing workloads in order to meet the performance requirement. The main work of PhSIH concerns dynamically adjusting the degree of parallelism and computing a task allocation solution for parallel threads. PhSIH is implemented in Apache Kafka to augment it as a content-based publish/subscribe system, which makes Kafka suitable for real-time fine-grained event dissemination scenarios, such as stock ticks. To evaluate the parallelization effect and adaptability of PhSIH, a series of experiments are conducted based on synthetic and real-world data. The experiment results demonstrate that PhSIH achieves a good parallelization effect on the three existing algorithms and possesses a desirable adaptability that stabilizes the performance of the matching algorithms.

In order to facilitate collaboration and improve service quality, progress information together with predicted information (Predictive Monitoring Information, PMI) should be published to partners or customers in a timely manner. Currently, the publishing points of PMI are assigned to certain positions empirically before the execution of a service process. However, because of the dynamic nature of service processes, a decision to publish PMI should be made based on the actual progress and predictions of the future. Therefore, an adaptive approach to select the publishing points of PMI for service processes is proposed. We design a method to quantify the benefits of notifying the delay risk at a point in the service process using long short-term memory (LSTM) neural networks. Furthermore, the deep reinforcement learning model is applied to select the publishing points for PMI dynamically. Experiments on a real-world dataset prove that our approach can select the optimal publishing points.

With the extensive applications of Web APIs, to monitor and analyze personal Web API invocation behaviors is becoming more and more important. However, due to the fact that the users' Web API invocation behaviors are highly heterogeneous, it is extremely challenging to provide a unified framework. In the paper, we introduce a predictive Web API Invocation Behavior Monitoring System (AIMS). AIMS automatically analyzes the predictability of users' invocation behaviors and for the user whose behaviors can be predicted, an adaptive strategy is applied to generate the predictions in an adaptive way. In addition, a context-aware K-nearest neighbor classifier is applied to detect the anomaly of user's invocation behaviors. Experiments on both a real-world dataset and synthetic dataset show AIMS is efficient in analyzing personal API invocation behaviors.

Dredging is the removal of sediment from the bottom of lakes, rivers, harbors, and other water bodies. It is a routine necessity in waterways around the world because the natural process of sand and silt washing downstream results in the sediment gradually filling channels and harbors. However, during the dredging operation, some dredgers do not transport the sediment to the designated area as expected but throw it near the waterway meaning sediment may return to the waterway in a short period. This paper proposes an online dredging operation anomaly detection (DOAD) method to detect this kind of irregular behavior during the dredging operation based on automatic identification system (AIS) data. First, we establish a feature system to extract behavior features from AIS data. Furthermore, we jointly utilize t-distributed stochastic neighbor embedding (t-SNE) with neural networks and a Gaussian mixture model (GMM) to train a detection model in a semi-supervised way. Through the trained model, irregular behaviors can be efficiently detected in real time during the dredging operation. The effectiveness of DOAD is evaluated according to a series of experiments. To the best of our knowledge of the published literature, this work is the first to introduce the application of AIS data to detect irregular behaviors during dredging operations.

Deep learning is popular in many areas, but users must manually specify the resource configuration when submitting deep learning training jobs, usually over-provisioning resources. This kind of unreasonable resource configuration method results in slow training and low resource utilization. Therefore, it would be more convenient and efficient if users only need to specify the quality of service (QoS) for their jobs, and then the resources will be autoconfigured to meet the QoS. To satisfy this demand, we present a QoS-oriented scheduling and autoscaling framework that schedules and autoscales deep learning training jobs in the Kubernetes cluster. This paper focuses on the most important QoS requirement for deep learning training jobs: deadline. The goal of the framework is to guarantee that as many jobs as possible can be accomplished before their specified deadlines. To reach this goal, the framework schedules deep learning jobs by implementing a heuristic scheduling policy based on resource status and job deadline, and autoscales resource configuration by exploiting a characteristic of deep learning jobs: the predictability of training time. This predictability is used to predict whether a job can be accomplished before its deadline and estimate appropriate resource configuration if necessary. We implemented the framework by modifying the default scheduler of Kubernetes and conducted experiments to evaluate its performance. The experiment results show that our scheduling policy can improve the completion rate by 26% when the cluster resources are insufficient, and our autoscaling policy can improve the completion rate to 100% when the cluster resources are sufficient. We also show that the framework improves the utilization of allocated CPUs to 100%. Our proposed framework points to a new way of submitting and managing deep learning training jobs in the cluster.

When facing fluctuating workloads, can the performance of matching algorithms in a content-based publish/subscribe system be adjusted to adapt to the workloads? In this paper, we explore the idea of endowing matching algorithms with adaptability. The prerequisite for adaptability is to enable the matching algorithm to possess the ability to dynamically and quantitatively adjust its performance. We propose PSAM, a Predicate-Skipping Adjustment Mechanism that realizes dynamic performance adjustment by smoothly switching between exact matching and approximate matching, following the strategy of trading off matching precision in favor of matching speed. The PSAM mechanism is integrated into an existing matching algorithm, resulting in a performance-adjustable matching algorithm called Ada-Rein. To collaborate with Ada-Rein, we design PADA, a Performance Adjustment Decision Algorithm that is able to make proper performance adjustment plans in the presence of fluctuating workloads. The effectiveness of Ada-Rein and PADA is evaluated through a series of experiments based on both synthetic data and real-world stock traces. Experiment results show that adjusting the performance of Ada-Rein at the price of a small false positive rate, less than 0.1%, can shorten event latency by almost 2.1 times, which well demonstrates the feasibility of our exploratory idea.

Summary Nowadays, with the development of cloud computing technology, an increasing number of enterprises or organizations have migrated applications to the cloud environment. Because of privacy concerns, a company may store sensitive data on a local server or a private cloud. As a result, the data analytics tasks have to be performed only in the local environment even when the analysis results will be shared to the outside. In this paper, we design a decentralized workflow system to speed up the execution of a Privacy‐Awareness Data Analytics application (PADA). Specifically, a workflow system with actor layer and engine layer for distributed execution of PADA proposed. The actors are responsible for performing actual data analysis tasks on the data side while the engines are deployed into different regions of the public cloud and communicate with actors to execute the whole workflow. Since engines in different regions have different communication latencies when invoking an actor, the optimization engine deployment scheme should be found to minimize the total execution time of a PADA. A path search‐based heuristic algorithm is designed to select suitable cloud regions to place the engines in the public cloud. The experimental results indicate that the proposed algorithm is effective in reducing application makespan.

With the rapid development of cloud computing, various types of cloud services are available in the marketplace. However, it remains a significant challenge for cloud users to find suitable services for two major reasons: (1) Providers are unable to offer services in complete accordance with their declared Service Level Agreements, and (2) it is difficult for customers to describe their requirements accurately. To help users select cloud services efficiently, this article presents a Trust enabled Self-Learning Agent Model for service Matching (TSLAM). TSLAM is a multi-agent-based three-layered cloud service market model, in which different categories of agents represent the corresponding cloud entities to perform market behaviors. The unique feature of brokers is that they are not only the service recommenders but also the participants of market competition. We equip brokers with a learning module enabling them to capture implicit service demands and find user preferences. Moreover, a distributed and lightweight trust model is designed to help cloud entities make service decisions. Extensive experiments prove that TSLAM is able to optimize the cloud service matching process and compared to the state-of-the-art studies, TSLAM improves user satisfaction and the transaction success rate by at least 10%.

The ever-increasing number of smartphone applications (apps) available on different app markets poses a challenge for personalized app recommendation. Conventional collaborative filtering-based recommendation methods suffer from sparse and binary user-app implicit feedback, which results in poor performance in discriminating user-app preferences. In this article, we first propose two kernel incorporated probabilistic matrix factorization models, which introduce app-categorical information to constrain the user and app latent features to be similar to their neighbors in the latent space. The two models are solved by Stochastic Gradient Descent with a user-oriented negative sampling scheme. To further improve the recommendation performance, we construct pseudo user-app ratings based on user-app usage information, and propose a novel kernelized non-negative matrix factorization by incorporating non-negative constraints on latent factors to predict user-app preferences. This model also leverages user--user and app--app similarities with regard to app-categorical information to mine the latent geometric structure in the pseudo-rating space. Adopting the Karush--Kuhn--Tucker conditions, a Multiplicative Updating Rules based optimization is proposed for model learning, and the convergence is proved by introducing an auxiliary function. The experimental results on a real user-app installation usage dataset show the comparable performance of our models with the state-of-the-art baselines in terms of two ranking-oriented evaluation metrics.

A distributed cluster provides a common computation platform to efficiently run different types of jobs, such as real-time and batch jobs that have different QoS requirements. One challenge of a distributed cluster is to find a scheduling strategy that can reduce the overtime ratio of real-time jobs as much as possible while also improving the completion time of batch jobs, aiming to promote QoS even though the resources in the cluster are stretched. To address this issue, many efficient scheduling methods have been proposed. However, most existing approaches are naive and coarse-grained in means of either killing batch jobs to preempt resources for real-time jobs or reserving some resources in advance for real-time jobs to minimize the overtime ratio of real-time jobs, which prolongs the completion time of batch jobs and reduces the resource utilization of the cluster. In this paper, we propose UpPreempt, a fine-grained preemptive scheduling strategy for container-based clusters. When scheduling real-time jobs, UpPreempt considers the deadline of jobs and the resource usage of existing batch jobs. Performing resource preemption from multiple batch jobs is the basic idea of UpPreempt. The set of batch jobs to be preempted and the amount of resources taken from each job are finely determined. In this way, UpPreempt greatly alleviates the effect of preemption on the batch jobs in terms of completion time and avoids reserving resources for real-time jobs. We implement UpPreempt in YARN to evaluate its performance. The evaluation with various workloads shows that our proposed scheduling strategy can achieve a good trade-off between the overtime ratio of real-time jobs and the completion time of batch jobs without reducing the resource utilization of the cluster.

When a passenger is going to book an airline flight, after he inputs his query conditions, he has to search from a long flight list to find the one that best matchs his preferences. Therefore, a friendly personalized flight recommender system is a necessary tool for online travel service companies. However, the majority of current approaches do not work well since in most cases, there is no enough historical order information on the route the customers may plan to take. In this paper, we propose an approach for building a Personalize Flight recommendation Service (PFS). In PFS, the attributes' information of flight orders is organized into several domains, and a tensor factorization method is used to recommend flights to users. Specifically, PFS applies a history-based weighting strategy to better model users' biases. PFS is also implemented in a distributed and parallel way to increase its execution speed when dealing with a huge amount of flight data. Extensive experiments on both a real flight order dataset and a synthetic large-scale dataset show the superiority of our model against other comparative ones.

Online periodic prediction is very common in practical problems like stock index analysis or traffic status estimation, where a prediction service is invoked at every time point. However, due to the potential communication cost, service overheads or the expenditure incurred by every prediction service invocation, it is valuable to reduce the number of invocation times without sacrificing too much precision. Therefore, we present an approach based on reinforcement learning to select the timing for prediction service invocations, which still guarantees high quality in capturing the regularity in a future time series. Extensive experiments are conducted on a real-world airfare search volume dataset of multiple routes. The experiment results prove that our algorithms show superiority over other solutions.

Personalized flight recommendation is useful when a traveler wants to find the most suitable flight ticket efficiently. It is hard to learn latent factors behind personal choices directly from users' preferred flight tickets whose features change over time, which leads to the ineffectiveness of traditional recommendation approaches. Therefore, we propose a personalized flight ticket recommendation approach based on paired choice modeling. In this approach, an optimization problem is formulated to maximize a user's choice utility over flight tickets through a paired-choice analysis of users' historical orders. The experiments conducted on a real world dataset show that our approach outperforms other state-of-the-art methods.

Due to the fast development and wide application of Web technology, online purchases have become the main method to buy airfare tickets. Because information about pricing factors is unavailable, it is difficult for customers to buy airfare tickets at the lowest cost or even at a relatively lower cost. Although several approaches have been proposed to suggest the optimal timing for purchasing airfare tickets, these methods are based on predictions of tomorrow's price information. Clearly, local optimal decisions which rely solely on tomorrow's price prediction can be misleading or incorrect, resulting in missed opportunities to buy tickets at a lower cost in the future. In this paper, a novel Optimal airfare Ticket Purchase decision-support Service (OTPS) is proposed, which makes continuous recommendations on the best purchase time before the departure date. OTPS is based on the strategy of the Dynamic ratio of numbers of Potential days with Lower Price (DPLP), which takes the fluctuation tendency of airfare prices for a period into consideration. Specifically, parameter values of the model are set in a route-specific manner and updated periodically to enhance the generalization ability and reliability of OTPS. Extensive experiments are conducted on the real-world ticket price dataset of multiple routes. The experimental results prove that OTPS shows superiority over other state-of-the-art solutions.

In the cloud computing architecture, virtual machine (VM) live migration is a fundamental research topic which has drawn extensive attention from communities of industry and academy. It is critical to transfer the VM memory pages that contain essential state information to resume the VM on another host during virtual machine (VM) live migration. There are many memory copy methods, such as pre-copy and post-copy. However, these methods have two limitations: application generality and performance imbalance. In this paper, we propose Ada-copy (adaptive copy), an adaptive memory copy strategy for VM live migration. The basic idea of Ada-copy is that the memory copy method of a VM should be determined by its workload characteristics. Specifically, based on the variation of current dirty page rate of memory, Ada-copy can adaptively select the most appropriate migration method to copy memory pages, thus addressing the two limitations of existing memory copy methods. To evaluate the effectiveness of our proposed strategy, we experiment with the Ada-copy on a variety of migration tasks with different dirty page rate and diverse memory usage workloads. Evaluation results show, compared with traditional methods, Ada-copy can significantly reduce the total migration time by 26%, the VM downtime by 42% and the amount of pages transferred by 35% in average.

In order for travelers to arrive at their destination comfortably, it is important that they plan their trip carefully. Our motivation in this paper is to free the traveler from tedious planning tasks. Several studies and applications have been proposed to help travelers plan their trip according to explicit preferences, but most ignore implicit preferences. For the first time, to the best of our knowledge, we propose a Personalized and Optimized Door-to-door TRavel Planning two-stage approach named PD-TRP, which combines different kinds of transportation services to provide high quality and cost-effective travel plan recommendations, taking into consideration individual explicit and implicit preferences in real time. In order to recommend a set of suitable plans with explicit attribute values, we propose an efficient heuristic search algorithm to generate the top-K candidate plans, and rank them according to the information entropy of implicit preferences discovered from the travelers' previous travel behaviour. We simulate information on transportation services, crawled from the Internet, on 2000 travelers and their past travel behaviour over the last three years, collected from an online travel company, and extensive experimental results show the two-stage approach PD-TRP can effectively improve the degree of satisfaction of the travelers.

Workflows have been widely used to coordinate business activities, software components and services. By making use of cloud resources, workflow systems can be deployed as common services to process a large quantity of workflow execution requests from various users. A challenge for the workflow service is that it should be elastic, i.e., to scale up or scale down to meet the requirements of processing dynamic and changing workloads efficiently while not wasting resources. To address this issue, we implemented an Elastic Workflow Service (EWS). Specifically, we propose a pattern prediction-based strategy in EWS which can dynamically deploy or undeploy components onto cloud resources according to the workload levels. The experimental results show that our configuration strategy has better performance when compared against other strategies.

With the number of smartphone applications (apps) growing explosively, it has a practical significance to provide personalized app recommendations. In this paper, we propose the GTRM, a new recommendation model which builds the top-N app list by optimizing the metric Group-oriented Mean Average Precision (GMAP). GMAP is an extension of the traditional metric Mean Average Precision (MAP) and it measures the precisions of top-N list in terms of the collective positions of related items rather than the position of individual item. Therefore, GTRM can recommend a more reasonable top-N app list by avoiding overfitting problem. The details of GMAP and GTRM are described. Extensive experiments on a real-world app dataset demonstrate the effectiveness of GTRM, and show that GTRM significantly outperforms the compared methods.

Recommender systems (RS) have become an integral part of our daily life. However, most current RS often repeatedly recommend items to users with similar profiles. We argue that recommendation should be diversified by leveraging session contexts with personalized user profiles. For this, current session-based RS (SBRS) often assume a rigidly ordered sequence over data which does not fit in many real-world cases. Moreover, personalization is often omitted in current SBRS. Accordingly, a personalized SBRS over relaxedly ordered user-session contexts is more pragmatic. In doing so, deep-structured models tend to be too complex to serve for online SBRS owing to the large number of users and items. Therefore, we design an efficient SBRS with shallow wide-in-wide-out networks, inspired by the successful experience in modern language modelings. The experiments on a real-world e-commerce dataset show the superiority of our model over the state-of-the-art methods.

Understanding air travel choice behavior of air passengers is of great significance for various purposes such as travel demand prediction and trip recommendation. Existing approaches based on surveys can only provide aggregate level air travel choice behavior of passengers and they fail to provide comprehensive information for personalized services. In this paper we focus on modeling individual level air travel choice behavior of passengers, which is valuable for recommendations and personalized services. We employ a probabilistic model to represent individual level air travel choice behavior based on a large dataset of historical booking records, leveraging several key factors, such as takeoff time, arrival time, elapsed time between reservation and takeoff, price, and seat class. However, each passenger has only a limited number of historical booking records, causing a serious data sparsity problem. To this end, we propose a mixed kernel density estimation (mix-KDE) approach for each passenger with a mixture model that combines probabilistic estimation of both regularity of the individual himself and social conformity of similar passengers. The proposed model is trained and evaluated via the expectation-maximization (EM) algorithm with a huge dataset of booking records of over 10 million air passengers from a popular online travel agency in China. Experimental results demonstrate that our mix-KDE approach outperforms the Gaussian mixture model (GMM) and the simple kernel density estimation in the presence of the sparsity issue.

With the proliferation of smartphones, participatory sensing using smartphones provides unprecedented opportunities for collecting enormous sensing data. There are two crucial requirements in participatory sensing, fair task allocation and energy efficiency, which are particularly challenging given high combinatorial complexity, trade-off between energy efficiency and fairness, and dynamic and unpredictable task arrivals. In this paper, we present a novel fair energy-efficient allocation framework whose objective is characterized by min–max aggregate sensing time. We rigorously prove that optimizing the min–max aggregate sensing time is NP hard even when the tasks are assumed as a priori. We consider two allocation models: offline allocation and online allocation. For the offline allocation model, we design an efficient approximation algorithm with the approximation ratio of 2−1m⁠, where m is the number of member smartphones in the system. For the online allocation model, we propose two algorithms: greedy algorithm and Robin-Hood algorithm, which achieve the competitive ratio of at most m and m+1⁠, respectively. The results demonstrate that the approximation algorithm reduces over 81% total sensing time, the online greedy algorithm and Robin-Hood algorithms reduce the total sensing time 73% and 37.5%, respectively. The offline approximation algorithm and online greedy algorithm achieve much better min–max fairness compared to other algorithms.

To improve the performance of recommender systems in a practical manner, several hybrid approaches have been developed by considering item ratings and content information simultaneously. However, most of these hybrid approaches make recommendations based on aggregating different recommendation techniques using various strategies, rather than considering joint modeling of the item’s ratings and content, and thus fail to detect many latent factors that could potentially improve the performance of the recommender systems. For this reason, these approaches continue to suffer from data sparsity and do not work well for recommending items to individual users. A few studies try to describe a user’s preference by detecting items’ latent features from content-description texts as compensation for the sparse ratings. Unfortunately, most of these methods are still generally unable to accomplish recommendation tasks well for two reasons: (1) they learn latent factors from text descriptions or user--item ratings independently, rather than combining them together; and (2) influences of latent factors hidden in texts and ratings are not fully explored. In this study, we propose a probabilistic approach that we denote as latent random walk (LRW) based on the combination of an integrated latent topic model and random walk (RW) with the restart method, which can be used to rank items according to expected user preferences by detecting both their explicit and implicit correlative information, in order to recommend top-ranked items to potentially interested users. As presented in this article, the goal of this work is to comprehensively discover latent factors hidden in items’ ratings and content in order to alleviate the data sparsity problem and to improve the performance of recommender systems. The proposed topic model provides a generative probabilistic framework that discovers users’ implicit preferences and items’ latent features simultaneously by exploiting both ratings and item content information. On the basis of this probabilistic framework, RW can predict a user’s preference for unrated items by discovering global latent relations. In order to show the efficiency of the proposed approach, we test LRW and other state-of-the-art methods on three real-world datasets, namely, CAMRa2011, Yahoo!, and APP. The experiments indicate that our approach outperforms all comparative methods and, in addition, that it is less sensitive to the data sparsity problem, thus demonstrating the robustness of LRW for recommendation tasks.

The global, ubiquitous usage of smart handsets and diverse wireless communication tools calls for a meticulous reexamination of complex and dynamic service componentization and remote invocation. In order to satisfy ever-increasing service requirements and enrich users' experiences, efficient service composition approaches, which leverage the computing resources on nearby devices to form an on-demand composite service, should be developed. This is especially true for situations that are confronted with limited local computing capacity and device mobility. For any mobile pervasive environment, execution reliability and latency of the composite service are major concerns that impact users' satisfaction. In this paper, we propose a novel three-staged approach which takes reliability and latency into account to solve a distributed service composition efficiently. First, the graph of the functional process description is decomposed into multiple path structures through a graph-traversing algorithm. Second, messages are forwarded among the network nodes (i.e., intelligent handsets) to search for the sub-solutions for these path structures. Finally, an efficient combinatorial optimization algorithm computes the optimal service composition by the selection from these sub-solutions. This approach is validated extensively in static and mobile environments, and the results show the effectiveness and outperformance of this approach over existing approaches.

Short-head and long-tail distributed data are widely observed in the real world. The same is true of recommender systems (RSs), where a small number of popular items dominate the choices and feedback data while the rest only account for a small amount of feedback. As a result, most RS methods tend to learn user preferences from popular items since they account for most data. However, recent research in e-commerce and marketing has shown that future businesses will obtain greater profit from long-tail selling. Yet, although the number of long-tail items and users is much larger than that of short-head items and users, in reality, the amount of data associated with long-tail items and users is much less. As a result, user preferences tend to be popularity-biased. Furthermore, insufficient data makes long-tail items and users more vulnerable to shilling attack. To improve the quality of recommendations for items and users in the tail of distribution, we propose a coupled regularization approach that consists of two latent factor models: C-HMF, for enhancing credibility, and S-HMF, for emphasizing specialty on user choices. Specifically, the estimates learned from C-HMF and S-HMF recurrently serve as the empirical priors to regularize one another. Such coupled regularization leads to the comprehensive effects of final estimates, which produce more qualitative predictions for both tail users and tail items. To assess the effectiveness of our model, we conduct empirical evaluations on large real-world datasets with various metrics. The results prove that our approach significantly outperforms the compared methods.

Acquiring accurate location information of vehicles is of great importance. Global Positioning System (GPS) has been widely deployed and used to be the most convenient solution to outdoor localization. As more and more infrastructure such as elevated roads, tunnels and tall buildings is built, however, the ever-increasing complexity of urban environments makes vehicle localization especially in those urban canyons a new challenging problem. In this paper, we propose a novel scheme, called UPS, to tackle urban vehicle localization problem. Inspired by the observation from empirical study that the Received Signal Strength Indication (RSSI) values of cellular signals (e.g., GSM) perceived over a distance have ideal temporal-spatial characteristics for fingerprinting, UPS refines the location accuracy of a moving vehicle by matching its cellular-aware trajectory, which is an association between consecutive geographical positions and the corresponding wide-band GSM RSSI values, with a pre-constructed map. Moreover, UPS leverages large mobility of vehicles to construct large-scale maps. We implement a prototype system to validate the feasibility of the UPS design. We conduct extensive real-world experiments and results show that UPS can work stably in various urban settings and achieve an accuracy of 4.2 meters on average and 5.3 meters with a 90% precision.

In recent years, due to an increasing overload of information on the Internet, there are many scenarios where Recommender Systems (RSs) are employed to provide suggestions to user groups. However, most proposed approaches of group recommendations simply aggregate individual ratings or individual prediction results, rather than comprehensively investigating the hidden correlative information between members and the group, which results in inferior recommendation performance. In this paper, we propose a new approach, RWR-UTM, for group recommendations based on the combination of an integrated probabilistic topic model - a User Topic Model (UTM) and the Random Walk with Restart (RWR) method. The UTM provides a latent framework of users, groups, and items by exploiting both the users' preference profiles and the items' content information, which together can describe group interests and item features in a more complete manner. This latent framework is then combined with RWR to predict the preference degrees of groups to unrated items by detecting comprehensive latent relationships. In particular, we devised two group-based recommendation algorithms on the basis of different recommendation strategies. Finally, we conducted experiments to evaluate our approach and compare it with other state-of-the-art approaches using the real-world CAMRa2011 data-set. The results demonstrate the advantage of our approach over comparative ones.

Mashup is a developer-centric technique which allows developers to compose existing Web services together to create innovative or consolidated web applications. However, the rapid growth in the number of services and the myriad of functionally similar services make it difficult for developers to select appropriate ones to develop new applications. Therefore, it is vital to recommend a set of suitable services for mashup creation based on functionalities of services and their relationships. To this end, we propose a service package recommendation approach for mashup development, which is based on mashup textual description mining to discover semantic relationships among services. Specifically, discourse analysis of computational linguistics is utilized to uncover the structures underneath mashups' functional specifications, then the semantic relationships between services can be learned from their appearances and the constructed structures in mashup specifications. Accordingly, we are able to recommend a package of services that can be used together with high compatibility for a new mashup to be developed. We evaluate our approach on a real-world dataset. Experimental results show that our approach achieves higher accuracy and outperforms other comparative ones.

Composing a set of Web services as a service process is becoming a common practice, but it involves multiple service invocations over the network, which incurs a huge time cost. To accelerate its execution, we propose an engine-side block-based service process caching strategy (BPCS). It is based on, and derives its advantages from, three key ideas. First, the invocation of Web service embodies semantics which enables the application of semantic-based caching. Second, cachable blocks are identified from a service process and each block is equiped with a separate cache so that the time overhead of service invocation and caching can be minimized. Third, a replacement strategy is introduced taking into account time and space factors to manage the space allocation for a process with multiple caches. The algorithms and methods used in BPCS are introduced in detail. Finally, BPCS is validated with a detailed performance study on real service processes and Web services via comparison experiments, which shows considerable improvements of BPCS over other strategies.

Workflows have been used to represent a variety of applications that involve coordinating a set of business services or scientific services, which are generally geographically distributed. With the development of cloud computing, a workflow engine can be deployed as a cloud service, responsible for executing customers' workflow instances. In a cloud workflow service, workflow engine components can be placed into different cloud regions. Thus, one challenging problem that arises is how to select the appropriate cloud regions to place the workflow engine components in order to efficiently execute a service workflow instance. Because this is a typical nondeterministic polynomial-time hard (NP-hard) problem, we propose a heuristic algorithm to select the regions where to place workflow engine components in an optimal and efficient way, with the objective of reducing the execution time of the service workflow instance. The experimental results prove that our proposed algorithm has higher performance than other approaches in terms of the solution quality and the running speed.

In the real-world environment, users have sufficient experience in their focused domains but lack experience in other domains. Recommender systems are very helpful for recommending potentially desirable items to users in unfamiliar domains, and cross-domain collaborative filtering is therefore an important emerging research topic. However, it is inevitable that the cold-start issue will be encountered in unfamiliar domains due to the lack of feedback data. The Bayesian approach shows that priors play an important role when there are insufficient data, which implies that recommendation performance can be significantly improved in cold-start domains if informative priors can be provided. Based on this idea, we propose a Weighted Irregular Tensor Factorization (WITF) model to leverage multi-domain feedback data across all users to learn the cross-domain priors w.r.t. both users and items. The features learned from WITF serve as the informative priors on the latent factors of users and items in terms of weighted matrix factorization models. Moreover, WITF is a unified framework for dealing with both explicit feedback and implicit feedback. To prove the effectiveness of our approach, we studied three typical real-world cases in which a collection of empirical evaluations were conducted on real-world datasets to compare the performance of our model and other state-of-the-art approaches. The results show the superiority of our model over comparison models.

Modern airlines use sophisticated pricing models to maximize their revenue, which results in highly volatile airfares. Without sufficient information, it is usually difficult for ordinary customers to estimate future price changes. Over the last few years, several studies have tried to solve the problem of optimal purchase timing for flight tickets, in which the prediction task is described as a binary classification concerning to buy or wait at a given point. However, forecasting the real-time price changes has never received much attention from the research community. In this paper, we address the problem of airfare forecast and present a systematic approach that covers the most important aspects of building a forecast service, including data modelling, forecast algorithm and long-term prediction strategies. A novel matrix-like data schema is first introduced to organize price series and extract temporal features. For the prediction task, we specifically investigate Learn++.NSE, an incremental ensemble classifier designed for learning in nonstationary environments. We propose a modification of the original algorithm to make a regressor that is capable of learning incrementally from streaming price series, with an extra ability of multi-step ahead forecasting. We further evaluate the forecast model on real-world price data collected from diverse routes and discuss its performance with respect to short-term and long-term prediction.

Nowadays most metro advertising systems schedule advertising slots on digital advertising screens to achieve the maximum exposure to passengers by exploring passenger demand models. However, our empirical results show that these passenger demand models experience uncertainty at fine temporal granularity (e.g., per min). As a result, for fine-grained advertisements (shorter than one minute), a scheduling based on these demand models cannot achieve the maximum advertisement exposure. To address this issue, we propose an online advertising approach, called EveryoneCounts, based on an uncertain passenger demand model. It combines coarse-grained statistical demand modeling and fine-grained Bayesian demand modeling by leveraging realtime card-swiping records along with both passenger mobility patterns and travel periods within metro systems. Based on this uncertain demand model, it schedules advertising time online based on robust receding horizon control to maximize the advertisement exposure. We evaluate the proposed approach based on an one-month sample from our 530 GB real-world metro fare dataset with 16 million cards. The results show that our approach provides a 61.5% lower traffic prediction error and 20% improvement on advertising efficiency on average.

The composition of multiple services that are deployed on smart devices generally incurs significant communication overheads, especially when an optimized composition is pursued. A parallel approach for service composition is proposed for obtaining the optimal solution with minimum executing time efficiently. In this approach, the request for a composite service is represented by a function graph which is decomposed into multiple path-structured sub graphs firstly. Then messages are sent among the service nodes to search for the corresponding sub-solutions. Finally, a Branch-and-Bound strategy is applied to generate the optimal solution over these sub-solutions. The experiments show our optimization strategies can reduce the time and communication cost considerably under different experimental settings.

Recommending routes for a group of competing taxi drivers is almost untouched in most route recommender systems. For this kind of problem, recommendation fairness and driving efficiency are two fundamental aspects. In the paper, we propose SCRAM, a sharing considered route assignment mechanism for fair taxi route recommendations. SCRAM aims to provide recommendation fairness for a group of competing taxi drivers, without sacrificing driving efficiency. By designing a concise route assignment mechanism, SCRAM achieves better recommendation fairness for competing taxis. By considering the sharing of road sections to avoid unnecessary competition, SCRAM is more efficient in terms of driving cost per customer (DCC). We test SCRAM based on a large number of historical taxi trajectories and validate the recommendation fairness and driving efficiency of SCRAM with extensive evaluations. Experimental results show that SCRAM achieves better recommendation fairness and higher driving efficiency than three compared approaches.

Traditional topic models illustrate how documents can be modeled as mixtures of topic probability distributions, which provides a simple method for discovering author’s research interests from a collection of documents. However, existing topic models such as the simplest author model [ 1 ] and the author-topic model (ATM) [ 2 ] mainly detect popular research topics and largely neglect unpopular ones. In these models, general topical words are grouped into the shared word distribution of each topic, but the words contained in each author-specific distribution that best describe the authors’ research interests are not included. Thus, a novel author-topic model for discovering unpopular research interests (URI-ATM) is proposed, which incorporates a new control variable k that takes on different values when the words belong to different types of research topics. In the model, each topic is associated with two classes of word distributions: one is the popular class among all authors, and the other is the author-specific class from which the document comes. After the URI-ATM is explained, a variety of qualitative and quantitative evaluations are performed. The results demonstrate the advantage of our approach over comparative ones.

Content-based publish/subscribe systems have been employed to deal with complex distributed information flows in many applications. It is well recognized that event matching is a fundamental component of such large-scale systems. Event matching searches a space which is composed of all subscriptions. As the scale and complexity of a system grows, the efficiency of event matching becomes more critical to system performance. However, most existing methods suffer significant performance degradation when the system has large numbers of both subscriptions and their component constraints. In this paper, we present Hash Tree (H-Tree), a highly efficient index structure for event matching. H-Tree is a hash table in nature that is a combination of hash lists and hash chaining. A hash list is built up on an indexed attribute by realizing novel overlapping divisions of the attribute's value domain, providing more efficient space consumption. Multiple hash lists are then combined into a hash tree. The basic idea behind H-Tree is that matching efficiencies are improved when the search space is substantially reduced by pruning most of the subscriptions that are not matched. We have implemented H-Tree and conducted extensive experiments in different settings. Experimental results demonstrate that H-Tree has better performance than its counterparts by a large margin. In particular, the matching speed is faster by three orders of magnitude than its counterparts when the numbers of both subscriptions and their component constraints are huge.

Nowadays, most recommender systems (RSs) mainly aim to suggest appropriate items for individuals. Due to the social nature of human beings, group activities have become an integral part of our daily life, thus motivating the study on group RS (GRS). However, most existing methods used by GRS make recommendations through aggregating individual ratings or individual predictive results rather than considering the collective features that govern user choices made within a group. As a result, such methods are heavily sensitive to data, hence they often fail to learn group preferences when the data are slightly inconsistent with predefined aggregation assumptions. To this end, we devise a novel GRS approach which accommodates both individual choices and group decisions in a joint model. More specifically, we propose a deep-architecture model built with collective deep belief networks and dual-wing restricted Boltzmann machines. With such a deep model, we can use high-level features, which are induced from lower-level features, to represent group preference so as to relieve the vulnerability of data. Finally, the experiments conducted on a real-world dataset prove the superiority of our deep model over other state-of-the-art methods.

Entity resolution identifies entities from different data sources that refer to the same real-world entity and it is an important prerequisite for integrating data from multiple sources. Entity resolution mainly relies on similarity measures on data records. Unfortunately, the data quality of data sources is not so good in practice. Especially web data sources often only provide incomplete information, which leads to the difficulties of direct applying similarity measures to identify the same entities. In order to address this problem, the concept of confidence is introduced to measure the trustworthy of the similarity calculation. An adaptive rule-based approach is used to calculate the similarity between records and its confidence is also derived. Then the similarity and confidence are propagated on the entity relational graph until fix point is reached. Finally, any pair of two records can be determined as matched or unmatched based on a threshold. We performed a series of experiments on real data sets and experiment results show that our approach has a better performance comparing with others.

Stimulating participation from smartphone users is of paramount importance to mobile crowd sourcing systems and applications. A few incentive mechanisms have been proposed, but most of them have made the impractical assumption that smartphones remain static in the system and sensing tasks are known in advance. The existing mechanisms fail when being applied to the realistic scenario where smartphones dynamically arrive to the system and sensing tasks are submitted at random. It is particularly challenging to design an incentive mechanism for such a mobile crowd sourcing system, given dynamic smartphones, uncertain arrivals of tasks, strategic behaviors, and private information of smartphones. We propose two truthful auction mechanisms for two different cases of mobile crowd sourcing with dynamic smartphones. For the offline case, we design an optimal truthful mechanism with an optimal task allocation algorithm of polynomial-time computation complexity of O (n+γ)3, where n is the number of smartphones and γ is the number of sensing tasks. For the online case, we design a near-optimal truthful mechanism with an online task allocation algorithm that achieves a constant competitive ratio of 1:2. Rigorous theoretical analysis and extensive simulations have been performed, and the results demonstrate the proposed auction mechanisms achieve truthfulness, individual rationality, computational efficiency, and low overpayment.

Choice modeling (CM) aims to describe and predict choices according to attributes of subjects and options. If we presume each choice making as the formation of link between subjects and options, immediately CM can be bridged to link analysis and prediction (LAP) problem. However, such a mapping is often not trivial and straightforward. In LAP problems, the only available observations are links among objects but their attributes are often inaccessible. Therefore, we extend CM into a latent feature space to avoid the need of explicit attributes. Moreover, LAP is usually based on binary linkage assumption that models observed links as positive instances and unobserved links as negative instances. Instead, we use a weaker assumption that treats unobserved links as pseudo negative instances. Furthermore, most subjects or options may be quite heterogeneous due to the long-tail distribution, which is failed to capture by conventional LAP approaches. To address above challenges, we propose a Bayesian heteroskedastic choice model to represent the non-identically distributed linkages in the LAP problems. Finally, the empirical evaluation on real-world datasets proves the superiority of our approach.

Event matching is the process of checking high volumes of events against large numbers of subscriptions and is a fundamental issue for the overall performance of a large-scale distributed publish/subscribe system. Most existing algorithms are based on counting satisfied component constraints in each subscription. As the scale of a system grows, these algorithms inevitably suffer from performance degradation. We present REIN (REctangle INtersection), a fast event matching approach for large-scale content-based publish/subscribe systems. The idea behind REIN is to quickly filter out unlikely matched subscriptions. In REIN, the event matching problem is first transformed into the rectangle intersection problem. Then, an efficient index structure is designed to address the problem by using bit operations. Experimental results show that REIN has a better matching performance than its counterparts. In particular, the event matching speed is faster by an order of magnitude when the selectivity of subscriptions is high and the number of subscriptions is large.

With the proliferation of smartphones, participatory sensing using smartphones provides unprecedented opportunities for collecting enormous sensing data. There are two crucial requirements in participatory sensing, fair task allocation and energy efficiency, which are particularly challenging given high combinatorial complexity, tradeoff between energy efficiency and fairness, and dynamic and unpredictable task arrivals. In this paper, we present a novel fair energy-efficient allocation framework whose objective is characterized by min-max aggregate sensing time. We rigorously prove that optimizing the min-max aggregate sensing time is NP hard even when the tasks are assumed as a priori. We consider two allocation models: offline allocation and online allocation. For the offline allocation model, we design an efficient approximation algorithm with the approximation ratio of 2 - 1/m, where m is the number of member smartphones in the system. For the online allocation model, we propose a greedy online algorithm which achieves a competitive ratio of at most m. The results demonstrate that the approximation algorithm reduces over 81% total sensing time, the greedy online algorithm reduces more than 73% total sensing time, and both algorithms achieve over 3x better min-max fairness.

Shortest path query over a dynamic road network is a prominent problem for the optimization of real-time traffic systems. Existing solutions rely either on a centralized index system with tremendous pre-computation overhead, or on a distributed graph processing system such as Pregel that requires much synchronization effort. However, the performance of these systems degenerates with frequent route path updates caused by continuous traffic condition change. In this paper, we build CANDS, a distributed stream processing platform for continuous optimal shortest path queries. It provides an asynchronous solution to answering a large quantity of shortest path queries. It is able to efficiently detect affected paths and adjust their paths in the face of traffic updates. Moreover, the affected paths can be quickly updated to the optimal solutions throughout the whole navigation process. Experimental results demonstrate that the performance for answering shortest path queries by CANDS is two orders of magnitude better than that of GPS, an open-source implementation of Pregel. In addition, CANDS provides fast response to traffic updates to guarantee the optimality of answering shortest path queries.

SUMMARY Resource performance prediction is becoming more and more important in cloud environment, and CPU load prediction is helpful for system maintenance and application schedule. However, the best predictor often varies from one resource to another. At the same time, CPU load in cloud environment has a wide range of dynamics so that the best predictor for any particular CPU load time series may change over time. Ensemble method, which can use multiple models to obtain better performances, is investigated to support CPU load prediction in this paper. The novel ensemble model proposed consists of two layers. The predictor optimization layer can continuously incorporate new predictor instances and remove those ones with a poor performance. The ensemble layer is responsible for producing the final prediction based on the results of multiple predictor instances. In addition, the ensemble layer can also provide feedbacks to the predictor optimization layer, which helps it to adopt appropriate optimization strategies. Extensive experiments have been performed on CPU load traces collected from an in‐production private cloud environment, and it shows this ensemble model has a better performance than any individual model. Copyright © 2013 John Wiley & Sons, Ltd.

Forming coalitions for a group of tasks efficiently in a distributed setting is a practical problem and a hot research topic in agent research. Most of current solutions for this problem are based on the assumption that there is no relationship between these tasks. However, logical interdependent relationships may exist between tasks so that transfer costs will be incurred when interdependent tasks are assigned to different agents. In order to solve this problem, a coalition formation strategy is proposed. In this strategy, it is allowed that agents disclose some personal cost information to compete for tasks in a controlled way. Experimental results show that, under the labor-based profit distribution framework, the information disclosure strategy is faster in forming coalitions and increases coalition net profit compared to the traditional information non-disclosure strategy.

Mashup is a user-centric approach to create value-added new services by utilizing and recombining existing service components. However, as services become increasingly more spontaneous and prevalent on the Internet, finding suitable services from which to develop a mashup based on users' explicit and implicit requirements remains a daunting task. Several approaches already exist for recommending specific services for users but they are limited to proposing only services with similar functionality. In order to recommend a set of suitable services for a general mashup based on users' functional specifications, a novel social-aware service recommendation approach, where multi-dimensional social relationships among potential users, topics, mashups, and services are described by a coupled matrix model, is proposed in this paper. Accordingly, a factorization algorithm is designed to predict unobserved relationships, and as a result, a comprehensive service recommendation model can be readily constructed. Experimental results for a realistic mashup data set indicate that the proposed approach outperforms other state-of-the-art methods.

Collaborative filtering (CF) is a major technique in recommender systems to help users find their potentially desired items. Since the data sparsity problem is quite commonly encountered in real-world scenarios, Cross-Domain Collaborative Filtering (CDCF) hence is becoming an emerging research topic in recent years. However, due to the lack of sufficient dense explicit feedbacks and even no feedback available in users' uninvolved domains, current CDCF approaches may not perform satisfactorily in user preference prediction. In this paper, we propose a generalized Cross Domain Triadic Factorization (CDTF) model over the triadic relation user-item-domain, which can better capture the interactions between domain-specific user factors and item factors. In particular, we devise two CDTF algorithms to leverage user explicit and implicit feedbacks respectively, along with a genetic algorithm based weight parameters tuning algorithm to trade off influence among domains optimally. Finally, we conduct experiments to evaluate our models and compare with other state-of-the-art models by using two real world datasets. The results show the superiority of our models against other comparative models.

ABSTRACT Designing and implementing an interoperable and flexible service process collaboration strategy is one of key issues for business to business integrations. To better support service process collaboration, an event view model is proposed, which is composed of a set of event types and their dependency relationships. It provides a general and flexible way to define a public view of a service process model and serves as the basis for defining service process collaboration protocols. In the paper, the basic concepts and a system framework for event‐based service process collaboration are first introduced. The definitions of event and the dependency relationships among event types are then presented. Especially, how to identify dependency relationships among composite event types is studied in detail. After discussing the definition of event view and its specifying approach, a procedure for transforming a BPEL process model into an event model and deriving dependencies among events is given. Finally, a case study is presented, and some implementation issues for defining and publishing an event view are discussed. Copyright © 2013 John Wiley & Sons, Ltd.

Because web services and agent technology can help each other, to integrate them together is becoming a trend. Most of current research works focus on developing an integration framework to provide gateways that can connect the agent and web service worlds. In the paper, the service intermediary agent is proposed as a value-added professional service provider, which can manage a group of inherently related Web services. It organizes Web services as a set of plans and reacts to the requests by selecting and executing the appropriate plans. In order to process the incoming requests intelligently, the semantic goal structure is employed to facilitate plan organizing and plan selecting. The structure of the service intermediary agent and its working process are given. The semantic goal structure together with the deliberation process is given. The case study and experiments are also provided.

Agent technology has gained increasing popularity in service oriented architecture (SOA) because of its features of autonomy, initiative, interactivity, persistency and adaptability. There are already a plenty of implementations which integrate SOA with multi-agent systems (MAS). The ability of learning is a significant feature of MAS. This paper proposes a learning model of the service-oriented MAS for the service composition problem. It adopts the principle of reinforcement learning and is based on the Markov game and Q-learning. The reward of the learning procedure is determined by the QoS parameters such as responding time and cost. The mechanism of multi-agent leaning for service composition is introduced. The results of experiments and case study show that our multi-agent learning approach can reach convergence efficiently and it can also accelerate the service composition process based on the knowledge continuously learned from past composition experiences.

In this study, we propose a module-level Evolvable Hardware (EHW) approach to design synchronous sequential circuits and minimize the circuit complexity (the number of logic gates and wires used). Firstly, we use Genetic Algorithm (GA) to implement state simplification and obtain near-optimal state assignment. Then, in the pre-evolution stage, EHW evolves a set of high performing circuits and uses data mining method to find frequently evolved blocks from these circuits. The frequently evolved block would be re-used as function or terminal for evolving better circuits in the re-evolution stage. EHW has a faster convergence so that the circuit with small complexity could be evolved. Auto starting ability of circuits would also be test by the fitness function of EHW. Finally, sequence detectors, modulon counters, and ISCAS'89 circuit are used as the proof for our evolutionary design approach. Simulation results are given, and our evolutionary algorithm is shown to be better than other methods in terms of convergence time, success rate, and maximum fitness across generations.

Computer simulation has already become an indispensible means for complex system developments, and the multi-agent oriented modeling and simulation is one of the most influential methods. In order to support multi-agent oriented simulation, a distributed platform is designed and developed to support the whole process that includes modeling, deployment and simulation. This platform can support uses to define the multi-agent models in a visual way and submit it as a sharable simulation model, which can be instantiated as simulation cases by other users. This platform also supports multiple simulation cases run concurrently. The execution engine can allocate agents to different machines and maintain the balances of loads across these machines. In this paper, the system structures together with the mechanisms behind the platform are introduced.

Sometimes, explicit relationships between entities do not provide sufficient information or can be unavailable in the real world. Unseen latent relationships may be more informative than explicit relationships. Thereby, we provide a method for constructing latent informative links between entities, using their common features, where entities are regarded as vertices on a graph. First, we employ a hierarchical nonparametric model to infer shared latent features for entities. Then, we define a filter function based on information theory to extract significant features and control the density of links. Finally, a couple of stochastic interaction processes are introduced to simulate dynamics on the net-works so that link strength can be retrieved from statistics in a natural way. In experiments, we evaluate the usage of filter function. The results of two examples based on mixture networks show how our method is capable of providing latent informative relationships in comparison to explicit relationships

In cloud computing environment, it is common for a multi-component application to be deployed into the IT infrastructure on demand. Although the Application Component Placement Problem or ACP has been studied both in the academy and industry for some years, so far these approaches all rely on a centralized node to collect the information about the network topology and hosts of the targeting environment so that it can make the optimized decision. In cloud environment, computing resources are shared by many applications and the IT infrastructure is dynamically changing, which makes collecting the dynamic information of the environment a more difficult task. In addition, when two or more clouds are involved in the deployment, there may exist privacy concern between different clouds so that a centralized approach cannot be applied. In this paper, we propose a distributed approach to solve the ACP problem. In our approach, we transform the ACP into a Distributed Constraint Optimization Problem or DCOP and solving the ACP becomes solving the DCOP. The detail of the algorithm and experiments are given.

In the past few decades, large-scale distributed computing systems such as grids have been widely used to serve a growing number of applications in a time-shared manner. In such environment, resources should be strictly assigned to achieve high performance. Hence, resource monitoring and usage prediction are required for the scheduling. Among these resources, CPU load has a significant effect on the performance. So prediction of CPU load plays an important role in the scheduling. In recent years, some research has been carried out in the field of CPU load prediction. Many prediction models were developed, such as Network Weather Service, the most popular performance prediction system. However, most of them adopt one-step-ahead or short-term prediction strategies, which cannot meet the requirement of the applications with much longer execution time. In this paper, we present a new long-term prediction model applying Fourier transform to exploit the periods of the CPU waves and using tendency-based methods to predict the variation.

The capability of an intelligent services system is based on a set of services processes, which are often organized into and managed by a process library. In order to react to a outside requirement, the system takes one of the approaches of using a predefined process directly, composing existing process models or generating a new process model based on a search algorithm on demand. Therefore, to decide which process models should be stored and how to update process models within the library is very important to improve the efficiency and lower the space cost of the system. A suffix tree-based optimization approach is proposed, which is based on a tree-structured representation. The algorithm, its complexity analysis and experiments are presented.

Cloud computing provides an efficient way to expose computing capabilities as sophisticated services that can be accessed remotely. It eliminates the need for organizations to maintain extensive infrastructures. Parallel and distributed simulation over cloud will bring us not only the increased productivity and efficiency but also the lower barrier for usage. This paper introduces a private cloud system based on BOINC which supports parallel and distributed simulation. The design idea and implementation method of each component for our system is discussed in detail.

Agent-based service composition has provided a promising computing paradigm for the automatic web service composition. In this paper, a formal service agent model is proposed, which integrates the web service and software agent technologies into one cohesive entity. Based on the service agent model, a distributed planning algorithm for web service composition called DPAWSC is presented. DPAWSC formalizes web service composition into a graph search problem according to the dependence relations among service agents. The key to DPAWSC is that the alternative solution with smaller length has higher priority to be searched than one with larger length. DPAWSC is based on the distributed decision making of the autonomous service agents and addresses the distributed nature of web service composition. We evaluate the algorithm by simulation experiments and the results demonstrate that DPAWSC is effective for its ability to produce the high quality solution at a low cost of communications.

In order to better support service collaboration for complex tasks, an event view model is proposed to facilitate the activation and integration of individual service processes. An event view is composed of a set of event types and their dependency relationships, it provides a public view of a service process model and serves as the basis for defining process collaboration protocols. After discussing the definition of event view and the service process collaboration framework based on event view, its construction approach and a procedure for transforming a service process model into an event model are proposed. Finally, a case study is presented and some implement issues are discussed.

Service discovery is one of the most vital components involved in almost all service applications. A lot of researches have paid attention to improving the matching accuracy for the given user requirement. Without a clarified requirement specification to describe the goals user really wants to achieve, any matching algorithm is useless. Goal-oriented requirement engineering is a formal requirement analysis methodology which recursively decompose a complex requirement into a set of finer grained goals. Such a hierarchical granulation structure partitions a requirement into a family of fine grain-sized granules. In order to handle uncertainties, rough set theory is employed in granular computing. For any given imprecise user requirement, a set of ordered stratified rough set approximations can be induced over all possible partitions. These approximations are used to iteratively refine imprecise requirement and recommend goals most probably desired. A matching algorithm based on six types of granule approximation is also given to describe different matching strategies for satisfying user requirement. Through the theoretical analysis and case study, it shows that rough set theory combining with granular computing is powerful to handle imprecise requirements and also provide better service quality.

An agent-based Web service workflow model is presented in this paper to facilitate the autonomic Web service composition, which contains three layers. The top is the user layer which represents the service requirements as goal workflow, the bottom service layer denotes the distributed Web services, and the middle is the agent layer. Each service agent in the agent layer abstracts the features of a group of actual operations with similar functions as operation template and models the process of using operation templates to achieve a certain goal as plan. The proposed model has great flexibility and extensibility and provides the guidance for the development of Web service integration tools.

Grid computing technology makes it possibly to use scientific workflow to be shared and reused among different users. However, a scientific workflow model usually needs to be tailored during reuse because of different problem contexts met by different users. These change logs provide additional information to help users customize scientific workflow. In this paper, we present a change sequence mining approach to automatically induce customized workflow based on different scientific experiment contexts. A docking case for drug design is described to validate the approach.

With the popularity of Web services, a set of Web services with similar functions but different qualities can be found. Since services are often be composed through a service process model, the way to compose them affects the whole quality of the process model itself. In this paper, a quality optimization method for the service process model is proposed, which takes the structure of service process into account. Based on the proposed quality model, a genetic algorithm is proposed to optimize the service process model.

Abstract Multi‐granularity of time and time zone difference are two aspects of a time management model (TMM) for distributed workflow management system (DWfS). There are some recent literatures concerning each of them. However, current researches on DWfS have not put them together but have built up an integrated model. As business and scientific collaboration processes across continents become more and more frequent, it is increasingly important to build an integrated model to take them as a whole to make the time transformation and temporal verification in collaboration processes easy and efficient. Aiming at solving this problem, an integrated TMM, DWfS‐TMM, is proposed in this paper. The DWfS‐TMM model consists of a set of general time ontology and a set of general rules for unified transformation between different time zones and different time granularity units. The representation of build‐time and run‐time temporal constraints in workflow processes and the temporal consistency checking method in this model is investigated. Finally, a real case study is investigated and it is shown from this case study that the presented model is useful and practicable. Copyright © 2009 John Wiley & Sons, Ltd.

Service process usually needs to be changed during reuse because of the change of context. These change mapping relations provide additional information to help users customize service processes. In this paper, we present a mining approach to mining process change sequences based on different context and finding the best sequence to tailor the base process.

Information theory has shown that feedback can greatly improve the error probability performance of communication channels. In practical communication systems with random message arrivals and queuing, however, this error improvement may come at the expense of longer delay and additional burstiness caused by the retransmissions. In this paper, we assess the benefits using feedback from an integrated information-theoretic and queuing-theoretic perspective. In particular, we characterize policies which achieve the optimal tradeoff between transmission power and packet queuing delay for communication over fading channels with feedback. It is shown that the use of feedback yields substantial improvements in the power-delay tradeoff over systems without feedback.

We consider the multiple-access communication problem in a distributed setting for both the additive white Gaussian noise channel and the discrete memoryless channel. We propose a scheme called Distributed Rate Splitting to achieve the optimal rates allowed by information theory in a distributed manner. In this scheme, each real user creates a number of virtual users via a power/rate splitting mechanism in the M-user Gaussian channel or via a random switching mechanism in the M-user discrete memoryless channel. At the receiver, all virtual users are successively decoded. Compared with other multiple-access techniques, Distributed Rate Splitting (DRS) can be implemented with lower complexity and less coordination. Furthermore, in a symmetric setting, we show that the rate tuple achieved by this scheme converges to the maximum equal rate point allowed by the information-theoretic bound as the number of virtual users per real user tends to infinity. When the capacity regions are asymmetric, we show that a point on the dominant face can be achieved asymptotically. Finally, when there is an unequal number of virtual users per real user, we show that differential user rate requirements can be accommodated in a distributed fashion

ShanghaiGrid is the first metropolitan grid in China. The project aims to develop an environment to share distributed resources in Shanghai conveniently based on grid technology. Yet, resources are finite for ever, especially for some expensive and specific resources. Users must reserve these resources in advance before use them. Present solutions need users confirm the absolute start time of reservation before the reservation which is impossible in practice at most time. But they can often estimate the relative time to start reservation after a specific event, e.g. beginning or finishing a task. As a part of ShanghaiGrid, we develop an ECA rule-based workflow management system (EWMS) which can serve for arranging the relative start time of advance resource reservation as users' demand. We introduce the design architecture of EWMS in the paper, and give a modeling demo to show how to realize advance resource reservation through our system

With the improvement of the traffic complexity extent, the solution of traffic problems becomes more and more difficult in the reality, so traffic simulation is an effective method for analyzing the traffic states and problems. As the simulation area becomes larger and more complicate, which requires large computing and storage resources, it can't be resolved by the traditional computing technology. Due to grid technology's advantages on such aspects, a new simulation architecture named GHA, which implements the HLA 's component as grid service and combined with the agent technology is presented in this paper. Thus the simulation architecture can offer high-capable computing resources to solve the complex traffic issues with great expansibility and flexibility; moreover, it also makes solid foundation to the authenticity of traffic simulation by adopting agent model the character of traffic entity. At last, a traffic simulation platform is implemented based on GHA and the performance tests are given

Abstract The goal of the ShanghaiGrid is to provide information services to the people. It aims to construct a metropolitan‐area information service infrastructure and establish an open standard for widespread upper‐layer applications from both communities and the government. The Information Service Grid Toolkit and a typical application called the Traffic Information Grid are discussed in detail. Copyright © 2005 John Wiley & Sons, Ltd.

Yan-Nong Huang et al. (1998) define a SQL-like language to specify organizational policies (or constraints) in workflow systems. Three types of policies are studied including qualification, requirements and substitution policies. However, they can't handle complex role resolution, such as separation of roles and binding of roles, and several exception situations, such as role delegation and role unavailable. Furthermore, from the perspective of project-oriented workflow, a project and its subprojects can be under the charge of teams (or virtual teams). The teams should satisfy the role resolution of the projects managed by the team. To support the above requirements, based on the team-enabled organization model, (1) we extend the policy language defined by Yan-Nong Huang et al. to support role resolution in project-oriented workflow, (2) provide its modeling and enforcement mechanism, and (3) propose rules to guarantee the correctness and optimization of the policy repository.

From the view of distributed application, it has the two important points to build ontology: sharing domain knowledge, reuse of domain knowledge. There are some problems in the present distributed applications based on ontology: It may use different terms for a same concept in different systems and it does not facilitate the information interchange between heterogeneous systems. Also, it lacks of a rigorous formal logic description for verification. Considering the application in the Internet, in this paper, we present a uniform expression format based on XML/RDF to describe the ontology, and extend PSL by creating new PSL Extensions to define the ontology of location, organization, resources, activity, process and product. These provide the mobile agent application system formal description language that supports the verification of the system and the translation with other application systems.

Using e-commerce over the Internet is very cheap and convenient, which enlarges the view of enterprises and lets the enterprises have more chances to select their partners. To achieve these goals, we need the support of information systems, in which workflow management system is of significance. The inherent characteristics of a workflow system make it suitable to implement the cross organization management. Nowadays, however, systems which support cross organization management are not common. When developing a supply chain management system for a big motorcycle corporation in China, we have to construct an inter-enterprises workflow Architecture over Internet for the system by ourselves. The main part of the Architecture is a workflow supported inner supply chain and an integrated interface, through which the whole supply chain system cross several independent enterprises is constructed and the information exchange is fulfilled. This paper introduces how the system is designed and implemented in detail.