Partially observable Markov decision processes (POMDPs) present significant challenges for reinforcement learning, as agents must learn optimal policies while maintaining belief states over unobserved environment states based on partial observations. We observe a compelling analogy: large language models (LLMs) autoregressively generate token probability distributions based on preceding context, mirroring how belief states are maintained and updated in POMDPs. This insight motivates leveraging the rich prior knowledge embedded in pre-trained LLMs for latent states estimation from observation-action histories. However, two critical challenges emerge: on the one hand, modality misalignment prevents LLMs from directly encoding visual observations and discrete actions; on the other hand, semantic misalignment exists between observation-action sequences and token sequences. To address these challenges, we introduce a novel framework ELSLLM that employs a Johnson-Lindenstrauss projection (JLP) module to transform input dimensions while preserving state similarity with theoretical guarantees, and utilizes modern Hopfield networks (MHN) to store all word embeddings from pre-trained LLMs as a knowledge repository. Through retrieval and querying mechanisms, ELSLLM achieves token-level knowledge alignment without requiring fine-tuning of the pre-trained LLMs. Extensive experiments on partially observable environments demonstrate that ELSLLM achieves state-of-the-art performance, significantly outperforming baseline methods with and without LSTM memory mechanisms. Our work opens new avenues for integrating pre-trained LLMs with reinforcement learning in partially observable settings.

Offline meta-reinforcement learning (OMRL) combines the strengths of learning from diverse datasets in offline RL with the adaptability to new tasks of meta-RL, promising safe and efficient knowledge acquisition by RL agents. However, OMRL still suffers extrapolation errors due to out-of-distribution (OOD) actions, compromised by broad task distributions and Markov Decision Process (MDP) ambiguity in meta-RL setups. Existing research indicates that the generalization of the Q network affects the extrapolation error in offline RL. This paper investigates this relationship by decomposing the Q value into feature and weight components, observing that while decomposition enhances adaptability and convergence in the case of high-quality data, it often leads to policy degeneration or collapse in complex tasks. We observe that decomposed Q values introduce a large estimation bias when the feature encounters OOD samples, a phenomenon we term "feature overgeneralization''. To address this issue, we propose FLORA, which identifies OOD samples by modeling feature distributions and estimating their uncertainties. FLORA integrates a return feedback mechanism to adaptively adjust feature components. Furthermore, to learn precise task representations, FLORA explicitly models the complex task distribution using a chain of invertible transformations. We theoretically and empirically demonstrate that FLORA achieves rapid adaptation and meta-policy improvement compared to baselines across various environments.

Branch-and-bound (B&B) is a fundamental algorithmic framework for solving Mixed-Integer Linear Programming (MILP) problems, where branching decisions critically affect solver efficiency. Recent learning-based methods apply imitation learning to select branching variables, but their deterministic predictions limit exploration and generalization. In this paper, we propose a novel framework that formulates branching variable selection as a conditional generative process, exploring deep-level decision features. Our approach leverages diffusion models to enable diverse and exploratory branching score generation, while consistency modeling distills this process into efficient one-step inference conditioned on the B&B state. This mode allows our method to achieve both high-quality and fast branching decisions, significantly improving the overall performance of branch-and-bound solvers. Extensive experiments on challenging cross-scale and cross-category benchmarks demonstrate that our framework consistently outperforms state-of-the-art imitation learning baselines, delivering substantial improvements in solution quality, computational efficiency, and inference speed.

Vehicle-to-infrastructure (V2I) communication, a subset of Vehicle-to-everything (V2X), plays a critical role in enhancing road safety and traffic efficiency. While DSRC and C-V2X technologies have standardised physical layer communication, the upper layers remain flexible and open to diverse implementations. Existing IoT application layer protocols (ALPs), built on legacy TCP and UDP transport protocols, may exhibit suboptimal performance in dynamic V2I environments. This study evaluates six ALPs, i.e., AMQP, CoAP, DDS, MQTT, WebSocket (WS), and XMPP, across twenty protocol combinations, including modern QUIC and SCTP transport protocols. Using a simulation framework that integrates Omnet++, SUMO, Veins, and OpenStreetMap data, we assess key performance metrics: latency, packet delivery ratio, throughput, inter-arrival time, and connection establishment time. Our results indicate that while most protocol combinations perform adequately under low node densities (e.g., fewer than 100 nodes), network congestion leads to performance degradation. Nevertheless, CoAP over QUIC/UDP and WS over QUIC emerge as promising candidates for disseminating awareness messages across diverse V2I communication scenarios within the context and test limits.

Medication recommendation (MR) has undergone rapid advancement in recent years, driven by its significant practical implications in healthcare. However, such high-risk scenarios still experience two critical yet overlooked challenges: the prevalent overconfidence in raw confidence for individual medications and the lack of a robust solution for confidence quantification in medication combinations. This paper represents the first in-depth study addressing this gap. We introduce two innovative methodologies tailored to the unique challenges of MR scenarios: 1) A discernible binning-based calibration method with theoretical guarantees for the confidence of individual medication. It guarantees distinct accuracy levels between adjacent bins and maintains consistent statistical reliability across calibration and test data, enabling calibrated confidence to reflect the correctness of medication recommendations distinctively. 2) A sample-based quantification method for the set confidence of medication combination, which is applicable for various existing performance metrics in MR. Utilizing representative deep MR models as backbones and conducting extensive experiments on the widely recognized MIMIC datasets, we empirically prove the effectiveness and robustness of our proposed methods. Our approaches not only improve the reliability of MR but also pave the way for more informed decision-making in clinical settings.

Signed graph clustering is a critical technique for discovering community structures in graphs that exhibit both positive and negative relationships. We have identified two significant challenges in this domain: i) existing signed spectral methods are highly vulnerable to noise, which is prevalent in real-world scenarios; ii) the guiding principle "an enemy of my enemy is my friend", rooted in Social Balance Theory, often narrows or disrupts cluster boundaries in mainstream signed graph neural networks. Addressing these challenges, we propose the Deep Signed Graph Clustering framework (DSGC), which leverages Weak Balance Theory to enhance preprocessing and encoding for robust representation learning. First, DSGC introduces Violation Sign-Refine to denoise the signed network by correcting noisy edges with high-order neighbor information. Subsequently, Density-based Augmentation enhances semantic structures by adding positive edges within clusters and negative edges across clusters, following Weak Balance principles. The framework then utilizes Weak Balance principles to develop clustering-oriented signed neural networks to broaden cluster boundaries by emphasizing distinctions between negatively linked nodes. Finally, DSGC optimizes clustering assignments by minimizing a regularized clustering loss. Comprehensive experiments on synthetic and real-world datasets demonstrate DSGC consistently outperforms all baselines, establishing a new benchmark in signed graph clustering.

The widespread adoption of Graph Neural Networks (GNNs) has led to an increasing focus on their reliability. To address the issue of underconfidence in GNNs, various calibration methods have been developed to gain notable reductions in calibration error. However, we observe that existing approaches generally fail to enhance consistently, and in some cases even deteriorate, GNNs' ability to discriminate between correct and incorrect predictions. In this study, we advocate the significance of discriminative ability and the inclusion of relevant evaluation metrics. Our rationale is twofold: 1) Overlooking discriminative ability can inadvertently compromise the overall quality of the model; 2) Leveraging discriminative ability can significantly inform and improve calibration outcomes. Therefore, we thoroughly explore the reasons why existing calibration methods have ineffectiveness and even degradation regarding the discriminative ability of GNNs. Building upon these insights, we conduct GNN calibration experiments across multiple datasets using a straightforward example model, denoted as DC(GNN). Its excellent performance confirms the potential of integrating discriminative ability as a key consideration in the calibration of GNNs, thereby establishing a pathway toward more effective and reliable network calibration.

Meta-Reinforcement Learning (Meta-RL) aims to reveal shared characteristics in dynamics and reward functions across diverse training tasks. This objective is achieved by meta-learning a policy that is conditioned on task representations with encoded trajectory data or context, thus allowing rapid adaptation to new tasks from a known task distribution. However, since the trajectory data generated by the policy may be biased, the task inference module tends to form spurious correlations between trajectory data and specific tasks, thereby leading to poor adaptation to new tasks. To address this issue, we propose the Meta-RL with task unCertAinty feedback through decoupled context-aware Reward and Dynamics components (MetaCARD). MetaCARD distinctly decouples the dynamics and rewards when inferring tasks and integrates task uncertainty feedback from policy evaluation into the task inference module. This design effectively reduces uncertainty in tasks with changes in dynamics or/and reward functions, thereby enabling accurate task identification and adaptation. The experiment results on both Meta-World and classical MuJoCo benchmarks show that MetaCARD significantly outperforms prevailing Meta-RL baselines, demonstrating its remarkable adaptation ability in sophisticated environments that involve changes in both reward functions and dynamics.

Molecular structures and Drug-Drug Interactions (DDI) are recognized as important knowledge to guide medication recommendation (MR) tasks, and medical concept embedding has been applied to boost their performance. Though promising performance has been achieved by leveraging Graph Neural Network (GNN) models to encode the molecular structures of medications or/and DDI, we observe that existing models are still defective: 1) to differentiate medications with similar molecules but different functionality; or/and 2) to properly capture the unintended reactions between drugs in the embedding space. To alleviate this limitation, we propose Carmen, a cautiously designed graph embedding-based MR framework. Carmen consists of four components, including patient representation learning, context information extraction, a context-aware GNN, and DDI encoding. Carmen incorporates the visit history into the representation learning of molecular graphs to distinguish molecules with similar topology but dissimilar activity. Its DDI encoding module is specially devised for the non-transitive interaction DDI graphs. The experiments on real-world datasets demonstrate that Carmen achieves remarkable performance improvement over state-of-the-art models and can improve the safety of recommended drugs with a proper DDI graph encoding.

Multivariate time series (MTS) analysis and forecasting are crucial in many real-world applications, such as smart traffic management and weather forecasting. However, most existing work either focuses on short sequence forecasting or makes predictions predominantly with time domain features, which is not effective at removing noises with irregular frequencies in MTS. Therefore, we propose WaveForM, an end-to-end graph enhanced Wavelet learning framework for long sequence FORecasting of MTS. WaveForM first utilizes Discrete Wavelet Transform (DWT) to represent MTS in the wavelet domain, which captures both frequency and time domain features with a sound theoretical basis. To enable the effective learning in the wavelet domain, we further propose a graph constructor, which learns a global graph to represent the relationships between MTS variables, and graph-enhanced prediction modules, which utilize dilated convolution and graph convolution to capture the correlations between time series and predict the wavelet coefficients at different levels. Extensive experiments on five real-world forecasting datasets show that our model can achieve considerable performance improvement over different prediction lengths against the most competitive baseline of each dataset.

The interpretability of policies remains an important challenge in Deep Reinforcement Learning (DRL). This paper explores interpretable DRL via representing policy by Differentiable Inductive Logic Programming (DILP) and provides a theoretical and empirical study of DILP-based policy learning from an optimization perspective. We first identified a fundamental fact that DILP-based policy learning should be solved as a constrained policy optimization problem. We then proposed to use Mirror Descent for policy optimization (MDPO) to deal with the constraints of DILP-based policies. We derived the closed-form regret bound of MDPO with function approximation, which is helpful to the design of DRL frameworks. Moreover, we studied the convexity of DILP-based policy to further verify the benefits gained from MDPO. Empirically, we experimented MDPO, its on-policy variant, and 3 mainstream policy learning methods, and the results verified our theoretical analysis.

The alignment of multiple multi-relational networks, such as knowledge graphs, is vital for many AI applications. In comparison with existing GCNs which cannot fully utilize relational information of multiple types, we propose a relation-aware graph convolutional network (ERGCN), which is equipped with both entity convolution and relation convolution to learn the entity embeddings and relation embeddings simultaneously. The role discrimination and translation property of knowledge graphs are adopted in the entity convolutional process to incorporate the relation information. To facilitate the relation convolution, we construct quadruples to model the connection between a pair of relations thus to determine their neighborhood, which also enables the relation convolution to be conducted in an efficient way. Thereafter, AERGCN, the alignment framework based on ERGCN, is developed for multi-relational network alignment tasks. Anchors are used to supervise the objective function, which aims at minimizing the distances between anchors and to generate new cross-network triplets to build a bridge between different knowledge graphs at the level of triplet to improve the performance of alignment. Experiments on real-world datasets show that the proposed solutions outperform the competitive baselines in terms of link prediction, entity alignment, and relation alignment.

This work explores how to learn robust and generalizable state representation from image-based observations with deep reinforcement learning methods. Addressing the computational complexity, stringent assumptions and representation collapse challenges in existing work of bisimulation metric, we devise Simple State Representation (SimSR) operator. SimSR enables us to design a stochastic approximation method that can practically learn the mapping functions (encoders) from observations to latent representation space. In addition to the theoretical analysis and comparison with the existing work, we experimented and compared our work with recent state-of-the-art solutions in visual MuJoCo tasks. The results shows that our model generally achieves better performance and has better robustness and good generalization.

Next Point-of-interest (POI) recommendation is a key task in improving location-related customer experiences and business operations, but yet remains challenging due to the substantial diversity of human activities and the sparsity of the check-in records available. To address these challenges, we proposed to explore the category hierarchy knowledge graph of POIs via an attention mechanism to learn the robust representations of POIs even when there is insufficient data. We also proposed a spatial-temporal decay LSTM and a Discrete Fourier Series-based periodic attention to better facilitate the capturing of the personalized behavior pattern. Extensive experiments on two commonly adopted real-world location-based social networks (LBSNs) datasets proved that the inclusion of the aforementioned modules helps to boost the performance of next and next new POI recommendation tasks significantly. Specifically, our model in general outperforms other state-of-the-art methods by a large margin.

Network embedding is capable of providing low-dimensional feature representations for various machine learning applications. Current work focuses on: 1) designing the embedding as an unsupervised learning task to explicitly preserve the structural connectivity in the network or 2) generating the embedding as a by-product during the supervised learning of a specific discriminative task in a deep neural network. In this paper, we aim to take advantage of these two lines of research in the view of multi-output learning. That is, we propose a generative adversarial network embedding (GANE) model to adapt the generative adversarial framework to achieve the network embedding learning during the specific machine learning tasks. GANE has a generator to generate link edges, and a discriminator to distinguish the generated link edges from real connections (edges) in the network. Wasserstein-1 distance is adopted to train the generator to gain better stability. GANE is further extended by utilizing the pairwise connectivity of vertices to preserve the structural information in the original network. Experiments with real-world network data sets demonstrate that our models constantly outperform state-of-the-art solutions with significant improvements for the tasks of link prediction, clustering, and network alignment.

Alignment of multiple multi-relational networks, such as knowledge graphs, is vital for AI applications. Different from the conventional alignment models, we apply the graph convolutional network (GCN) to achieve more robust network embedding for the alignment task. In comparison with existing GCNs which cannot fully utilize multi-relation information, we propose a vectorized relational graph convolutional network (VR-GCN) to learn the embeddings of both graph entities and relations simultaneously for multi-relational networks. The role discrimination and translation property of knowledge graphs are adopted in the convolutional process. Thereafter, AVR-GCN, the alignment framework based on VR-GCN, is developed for multi-relational network alignment tasks. Anchors are used to supervise the objective function which aims at minimizing the distances between anchors, and to generate new cross-network triplets to build a bridge between different knowledge graphs at the level of triplet to improve the performance of alignment. Experiments on real-world datasets show that the proposed solutions outperform the state-of-the-art methods in terms of network embedding, entity alignment, and relation alignment.

Next and next new point-of-interest (POI) recommendation are essential instruments in promoting customer experiences and business operations related to locations. However, due to the sparsity of the check-in records, they still remain insufficiently studied. In this article, we propose to utilize personalized latent behavior patterns learned from contextual features, e.g., time of day, day of week, and location category, to improve the effectiveness of the recommendations. Two variations of models are developed, including GPDM, which learns a fixed pattern distribution for all users; and PPDM, which learns personalized pattern distribution for each user. In both models, a soft-max function is applied to integrate the personalized Markov chain with the latent patterns, and a sequential Bayesian Personalized Ranking (S-BPR) is applied as the optimization criterion. Then, Expectation Maximization (EM) is in charge of finding optimized model parameters. Extensive experiments on three large-scale commonly adopted real-world LBSN data sets prove that the inclusion of location category and latent patterns helps to boost the performance of POI recommendations. Specifically, our models in general significantly outperform other state-of-the-art methods for both next and next new POI recommendation tasks. Moreover, our models are capable of making accurate recommendations regardless of the short/long duration or distance.

Most existing solutions for the alignment of multi-relational networks, such as multi-lingual knowledge bases, are ``translation''-based which facilitate the network embedding via the trans-family, such as TransE. However, they cannot address triangular or other structural properties effectively. Thus, we propose a non-translational approach, which aims to utilize a probabilistic model to offer more robust solutions to the alignment task, by exploring the structural properties as well as leveraging on anchors to project each network onto the same vector space during the process of learning the representation of individual networks. The extensive experiments on four multi-lingual knowledge graphs demonstrate the effectiveness and robustness of the proposed method over a set of state-of-the-art alignment methods.

With a profusion of network applications, traffic classification plays a crucial role in network management and policy-based security control. The widely used encryption transmission protocols, such as the secure socket layer/transport layer security (SSL/TLS) protocols, lead to the failure of traditional payload-based classification methods. Existing methods for encrypted traffic classification cannot achieve high discrimination accuracy for applications with similar fingerprints. In this paper, we propose an attribute-aware encrypted traffic classification method based on the second-order Markov Chains. We start by exploring approaches that can further improve the performance of existing methods in terms of discrimination accuracy, and make promising observations that the application attribute bigram, which consists of the certificate packet length and the first application data size in SSL/TLS sessions, contributes to application discrimination. To increase the diversity of application fingerprints, we develop a new method by incorporating the attribute bigrams into the second-order homogeneous Markov chains. Extensive evaluation results show that the proposed method can improve the classification accuracy by 29% on the average compared with the state-of-the-art Markov-based method.

Software Defined Networks (SDNs) decouple control plane from data plane and enable fine-grained traffic management by a logically centralized controller. Reducing the flow latency is of great importance in traffic management, which benefits both service providers and end users. Routing design and flow scheduling are typical ways to improve the flow transmission efficiency. However, existing studies usually consider them separately, due to the complexity of joint consideration. In this paper, we combine the routing and scheduling together and propose a latency-aware routing scheme with bandwidth assignment, which can efficiently reduce the flow latency with a moderate complexity. In the routing design, we utilize the global flow information to reduce both the latency of the newly arrived flow and its interference with existing flows in the network. Given flow forwarding paths determined by routing, the flow scheduling dynamically reallocates the bandwidth to all flows so as to further reduce the total flow latency. Experimental results show that our scheme outperforms the scheme currently available in OpenFlow, with an improvement of up to 60% on flow efficiency and a higher percentage of flows that meet their deadlines.

With the prosperity of network applications, traffic classification serves as a crucial role in network management and malicious attack detection. The widely used encryption transmission protocols, such as the Secure Socket Layer/Transport Layer Security (SSL/TLS) protocols, leads to the failure of traditional payload-based classification methods. Existing methods for encrypted traffic classification suffer from low accuracy. In this paper, we propose a certificate-aware encrypted traffic classification method based on the Second-Order Markov Chain. We start by exploring reasons why existing methods not perform well, and make a novel observation that certificate packet length in SSL/TLS sessions contributes to application discrimination. To increase the diversity of application fingerprints, we develop a new model by incorporating the certificate packet length clustering into the Second-Order homogeneous Markov chains. Extensive evaluation results show that the proposed method lead to a 30% improvement on average compared with the state-of-the-art method, in terms of classification accuracy.

Communication privacy and latency perceived by users have become great concerns for delay-sensitive Internet services. Existing anonymous communication systems either provide high anonymity at an expense of prolonged latency (e.g., mix-net), or offer better real-time performance by sacrificing the ability against traffic analysis attacks (e.g., Onion Routing). The emerging Software-Defined Networking (SDN) introduces additional challenges to communication anonymity, due to the existence of a centralized controller that has a global view of the entire network traffic. In this paper, we propose a new anonymous communication scheme for delay-sensitive services under SDN scenarios, which can simultaneously protect communication privacy and reduce the end-to-end latency. A self-adaptive method based on the mix-net framework is designed to dynamically modify the waiting threshold of mix nodes, which helps to reduce the communication latency. In order to preserve the degree of anonymity, the self-adaptive method is incorporated with a random walking strategy for packets forwarding. Both theoretical analysis and experimental results prove that our scheme provides a moderate degree of anonymity and effectively reduces the latency derived from mix-net by up to 50%.

Reducing the flow latency is of great importance in traffic management, which benefits both service providers and end users. Routing design and flow scheduling are typical ways to improve the flow transmission efficiency. However, existing studies usually consider them separately, due to the complexity of joint consideration. Here, we propose a latency-aware routing scheme with bandwidth assignment in the Software Defined Networks, which can efficiently reduce the flow latency with a moderate complexity, to combine the routing and scheduling together.

Messages spreading inside vehicular ad hoc networks (VANETs) generally need to achieve the property of verifiability and content integrity, while preserving user privacy. Otherwise, VANETs will either fall into chaos, or prevent users from embracing it. To achieve this goal, we propose a protocol, which contains a priori and posteriori countermeasures, to guarantee these features. The a priori process firstly verifies that each message is sent by a vehicle only once. Then it collects and checks whether the count of the message exceeds the threshold value to improve the trustworthiness of the message. The posteriori process verifies the integrity of the message, ensuring it is unchanged during transmission between the vehicle and the road side unit. The privacy is preserved by applying group signature. In case of disruptive events, the proposed solution can trace back to the source vehicle which generates the message.

Delay Tolerant Networks (DTNs) are intermittently connected networks, such as mobile social networks formed by human-carried mobile devices. Routing in such mobile social DTNs is very challenging as it must handle network partitioning, long delays, and dynamic topology. Recently, social-based approaches, which attempt to exploit social behaviors of DTN nodes to make better routing decision, have drawn tremendous interests in DTN routing design. In this paper, we propose a novel social-based routing approach for mobile social DTNs, where a new metric social energy is introduced to quantify the ability of a node to forward packets to others, inspired by general laws in particle physics. Social energy is generated via node encounters and shared by the communities of encountering nodes. Similar to the radiation of energy in physics, the social energy of any node decays over time. Our proposed Social Energy Based Routing (SEBAR) protocol considers social energy of encountering nodes and is in favor of the Dode with a higher social energy in its or the destination's social community. Our simulations with real-life wireless traces demonstrate the efficiency and effectiveness of SEBAR method by comparing It with several existing DTN routing schemes.

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

ABSTRACT Current secure communication schemes do not take together traffic security and data security (content integrity and non‐repudiation) of the secret message into consideration, making the content prone to blind tampering and compromised party cheating attacks. In this paper, we present a scheme that hides secret audio in cover audio on the basis of robust digital signature to preserve not only hidden communication but also content integrity and non‐repudiation of the secret audio. Furthermore, instead of traditional binary authentication that only outputs yes or no, the authentication of our scheme is flexibly measurable, and the measurement value is in correspondence with the sense of human hearing precisely. Experimental results show that the proposed scheme provides highly robust authentication against content‐preserving degradations with 99.03% of test audios having the strongest authenticity (1.00) and high level of distinct authentication between content‐destructive degradations with 95.01% of test audios having relatively weak authenticity (less than 0.15). As the authentication is flexibly measureable, there is no false alarm in the semantic aspect. Copyright © 2013 John Wiley & Sons, Ltd.

Abstract Robustness and reliability with respect to the successful completion of a schedule are crucial requirements for scheduling in scientific workflow management systems because service providers are becoming autonomous. We introduce a model to incorporate trust, which indicates the probability that a service agent will comply with its commitments to improve the predictability and stability of the schedule. To deal with exceptions during the execution of a schedule, we adapt and evolve the schedule at runtime by interleaving the processes of evaluating, scheduling, executing and monitoring in the life cycle of the workflow management. Experiments show that schedules maximizing participants' trust are more likely to survive and succeed in open and dynamic environments. The results also prove that the proposed approach of workflow evaluation can find the most robust execution flow efficiently, thus avoiding the need of scheduling every possible execution path in the workflow definition. Copyright © 2009 John Wiley & Sons, Ltd.