Model merging has emerged as an efficient technique for expanding large language models (LLMs) by integrating specialized expert models. However, it also introduces a new threat: model merging stealing, where free-riders exploit models through unauthorized model merging. Unfortunately, existing defense mechanisms fail to provide effective protection. Specifically, we identify three critical protection properties that existing methods fail to simultaneously satisfy: (1) proactively preventing unauthorized merging; (2) ensuring compatibility with general open-source settings; (3) achieving high security with negligible performance loss. To address the above issues, we propose MergeBarrier, a plug-and-play defense that proactively prevents unauthorized merging. The core design of MergeBarrier is to disrupt the Linear Mode Connectivity (LMC) between the protected model and its homologous counterparts, thereby eliminating the low-loss path required for effective model merging. Extensive experiments show that MergeBarrier effectively prevents model merging stealing with negligible accuracy loss.

Multimodal large language models (MLLMs) have achieved significant results in various tasks, but their practical application is still severely constrained by hallucination issues, which are particularly prominent in reinforcement learning (RL) optimization processes. This paper systematically analyzes the causes of hallucinations in MLLM under RL training, identifying three key factors: (1) The model relies heavily on chained visual reasoning to guide decision-making during RL training. Thus, error and irrelevant information in visual reasoning can easily cause hallucinations, including inaccurate initial visual descriptions that anchor subsequent inferences to incorrect information, as well as redundant and broad inferential information; (2) Insufficient exploration diversity during the policy optimization phase, causing the model to output overly confident results; (3) The destructive conflict between different samples during optimization is a key factor that leads to false associations and unstable parameter updates. To address these issues, we propose a solution framework comprising three core modules. First, to improve the accuracy of visual localization, we add planning and caption stages before thinking and answer stages. To enhance initial visual descriptions ability, we allow LLMs to respond based solely on the caption and provide corresponding caption reward based on the quality of the response. Second, to enhance exploration capabilities, we classify samples based on the mean and variance of the reward distribution and select samples with high reward variance for training, thereby increasing the model's focus on diverse samples. Finally, to mitigate conflicts between training samples, we identify neural tangent kernel (NTK) similarity as the key factor. Rather than minimizing it uniformly, we regulate NTK similarity by grouping sample pairs based on a similarity threshold. An InfoNCE loss is then applied to pull dissimilar pairs closer and push overly similar ones apart, guiding interactions toward a balanced range. The experimental results demonstrate that the proposed method significantly reduces the hallucination rate and effectively improves the inference accuracy of MLLMs.

Recommender Systems (RSs) are widely applied for navigating information, and Collaborative Filtering (CF) is one of prominent recommendation techniques due to the advantages of domain independence and easy interpretation. Among the numerous CF methods, Variational Autoencoders (VAE), benefiting from modeling in a probabilitistic way, stands out in capturing user preferences through representation learning. Despite the superiority, VAE-based CF models still suffer from two challenging problems: (1) Exposure bias: models in training state are narrowly exposed to a limited, biased sample of data, leading to a skewed understanding of users' true preferences; (2) Posterior collapse: models excessively simplify the learned latent variable distributions, generating na"ive representations that are unable to encapsulate the complex data patterns and thereby resulting improper recommendations. In this paper, we propose a Debiased and Representation-enhanced Variational AutoEncoder (DR-VAE) framework for collaborative recommendations. Specifically, for exposure bias problem, DR-VAE incorporates a Debiasing Estimator, mitigating the impact of exposure bias. For poster collapse issue, DR-VAE innovatively introduces a Flow-based Representation Enhancement module, ensuring us to encapsulate complex data patterns by fitting complex and intricate posterior distributions directly. We provide experimental validations over four datasets to substantiate the efficacy of our DR-VAE framework.

Over the past years, intelligent control tasks, such as deep neural networks (DNNs), have demonstrated significant potential in control systems. However, deploying intelligent control policies on heterogeneous computing platforms presents open challenges. These challenges extend beyond the apparent conflict between intensive computation and timing constraints and further encompass the interactions between task executions and complicated control performance. To address these challenges, this paper introduces RICH, a general and end-to-end approach to facilitate intelligent control tasks on heterogeneous computing architectures. RICH incorporates both offline Control-Oriented Computation and Resource Mapping (CCRM) and runtime Most Remaining Accelerator Segment Number First Scheduling (MRAF). Given the control tasks, the CCRM starts with balancing the computation workloads and processor resources with the goal of optimizing overall control performance. Subse-quently, the MRAF employs segment-level real-time scheduling to ensure the timely execution of tasks. Extensive experiments on the robotic arms applications (by hardware-in-the-loop simulator) demonstrate that the RICH can work as a general and end-to-end approach. These experiments reveal significant improvements in control performance, with enhancements of 50.7% observed for intelligent control applications deployed on heterogeneous computing platforms.

Artificial intelligence is rapidly encroaching on the field of service regulation. However, existing AI-based regulation techniques are often tailored to specific application domains and thus are difficult to generalize in an automated manner. This paper presents Horae, a unified specification language for modeling (multimodal) regulation rules across a diverse set of domains. We showcase how Horae facilitates an intelligent service regulation pipeline by further exploiting a fine-tuned large language model named RuleGPT that automates the Horae modeling process, thereby yielding an end-to-end framework for fully automated intelligent service regulation. The feasibility and effectiveness of our framework are demonstrated over a benchmark of various real-world regulation domains. In particular, we show that our open-sourced, fine-tuned RuleGPT with 7B parameters suffices to outperform GPT-3.5 and perform on par with GPT-4o.

Despite the advancements in supporting artificial intelligence, accelerator-enabled computing architectures still struggle to meet strict timing constraints due to the complex interactions between CPU cores and accelerators. Although various scheduling and response-time analysis techniques have been developed, a significant gap remains between the conservative hard real-time schedulability (i.e., worst-case response times) and the average measured schedulability on real systems. This pessimism significantly limits the deployment of hard real-time tasks on accelerator-enabled computing platforms. To address this, we propose HARD, a real-time scheduling approach that integrates scheduling strategies, response time analysis, and practical scheduler designs for general accelerator-enabled computing platforms. Benefiting the subtask level segmented characteristics that are ignored by classic schedulers, the proposed HARD can significantly improve the theoretically guaranteed hard real-time schedulability. Extensive experiments on off-the-shelf Intel CPUs and NVIDIA GPUs show that HARD outperforms state-of-the-art scheduling and analysis approaches, delivering a 11.3% improvement in hard real-time schedulability and a remarkable 45.1 % reduction in pessimism.

In recent years, multiple data copies become popular in heterogeneous computing architectures. They enable parallel data transfer among diverse processing units. Tasks executed on such heterogeneous architectures often exhibit heightened re-source competitions and intricate task dependencies, posing challenges in meeting strict timing constraints. Due to the dominant roles of data copies in the heterogeneous architecture, effective scheduling and tight response time analysis could contribute to the timing performance of the entire heterogeneous computing system. In this work, we introduce MATCH, which offers realtime scheduling and end-to-end response time analysis for the multiple parallel data copies that are popular in mainstream heterogeneous architectures. We first identify the aggravated resource competition and task dependency from multiple data copies and comprehensive task execution patterns. Then, we provide a real-time scheduling strategy and cross-granularity schedulability analysis to deal with resource competition and task dependency. Extensive evaluation demonstrates that efficient scheduling and analysis on multiple parallel data copies can significantly improve the schedulability by 55.5%-144.4%. Additionally, experiments conducted on various scales of heterogeneous systems demonstrate that MATCH can significantly reduce pessimism in response time analysis by up to 22.8%-57.5%. Importantly, the proposed approach is compatible with existing scheduling approaches that do not consider multiple parallel data copies and are readily applied to off-the-shelf heterogeneous computing systems.

The growing complexity and stringent real-time demands of autonomous systems, such as self-driving cars and drones, have driven the adoption of intelligent control methods based on deep neural networks (DNNs). While these methods offer improved control performance over traditional modelbased approaches, they also pose significant computational challenges, particularly for resource-constrained platforms. FieldProgrammable Gate Arrays (FPGAs) offer an attractive solution due to their energy efficiency and customizable architecture. In this work, we propose FALCON, an innovative approach for designing real-time intelligent controllers for autonomous systems using FPGA accelerators. Our approach begins with designing DNN-based intelligent controllers with varying levels of complexity and accuracy on the FPGA platform. Then, a performance function is proposed to capture the interplay among controller complexity, computational behavior, physical system characteristics, and overall control performance. Based on this performance function, we develop an algorithm-hardware codesign framework to determine the optimal control complexity, hardware configuration, and resource allocation. Finally, a case study on the co-design of intelligent controllers and FPGAbased overlay processors, together with a hardware-in-the-loop simulator, is conducted to demonstrate the advantages of the proposed methods. Compared to benchmarking controllers on other platforms, FALCON's optimized intelligent controller using FPGA accelerators shows competitive control performance with superior real-time capability and power efficiency. FALCON's optimization reduces the worst-case response time (WCRT) by up to 46.52%, improves the control performance by$1.93 \times$compared to the default setup. For performance per power efficiency, FALCON achieves a$3.67 \times$improvement compared to the DNN intelligent controller on TX2 and a remarkable$30.78 \times$improvement compared to traditional MPC on CPU.

The Intelligent Transportation System (ITS) serves as a pivotal element within urban networks, offering decision support to users and connected automated vehicles through comprehensive information gathering, sensing, device control, and data processing. Presently, ITS predominantly relies on sensors embedded in fixed infrastructure, notably Roadside Units (RSUs). However, RSUs are confined by coverage limitations and may encounter challenges in prompt emergency responses. On-demand resources, such as drones, present a viable option to supplement these deficiencies effectively. This article introduces an approach where Software-Defined Networking and Mobile Edge Computing technologies are integrated to formulate a high-availability drone swarm control and communication infrastructure framework comprising the cloud layer, edge layer, and device layer. Drones confront limitations in flight duration attributed to battery limitations, posing a challenge in sustaining continuous monitoring of road conditions over extended periods. Effective drone scheduling stands as a promising solution to overcome these constraints. To tackle this issue, we initially utilized Graph WaveNet, a specialized graph neural network structure tailored for spatial-temporal graph modeling, for training a congestion prediction model using real-world dataset inputs. Building upon this, we further propose an algorithm for drone scheduling based on congestion prediction. Our simulation experiments using real-world data demonstrate that, compared to the baseline method, the proposed scheduling algorithm not only yielded superior scheduling gains but also mitigated drone idle rates.

Personalized incentives are crucial for boosting user engagement and increasing platform revenues. Many studies have utilized uplift modeling to estimate the conditional average treatment effects (CATEs) of incentives and then allocate them under cost constraints. However, identifying which users should receive such incentives remains challenging, posing a selection bias problem. Traditional representation-based approaches mitigate bias by balancing treated and controlled distributions but overlook local similarity information. Recognizing that similar users should exhibit similar outcomes, it is vital to preserve both intra-similarity within treatment groups and inter-similarity between covariate and representation spaces. Moreover, existing methods primarily focus on CATE accuracy, neglecting the ranking ability vital for uplift modeling. We propose the Similarity Preserved Counterfactual Incentive Effect Estimation ( S-CIEE ) method, comprising three modules: (1) an Intra-Similarity Preservation Regularizer via Fused Gromov-Wasserstein Optimal Transport, (2) an Inter-Similarity Preservation Regularizer using a similarity constraint, and (3) a Rank-Aware Learning module for uplift ranking. Comprehensive experiments on one semi-synthetic and two real-world datasets show that S-CIEE improves both CATE accuracy and uplift modeling performance.

Web service-oriented transactions have become an integral part of the Internet economy, with the mainstream transaction patterns relying primarily on cloud service markets. However, traditional service transaction methods have deficiencies in terms of both trust and scalability. Distrust between service provider (SP) and consumer (SC), particularly around online payments and data security, impedes the further growth of service transactions. Although blockchain-based transaction mechanisms have made notable progress in addressing trust issues, they still face performance bottlenecks. To tackle these challenges, this paper introduces TrustPay, a service transaction framework that leverages a dual-layer blockchain structure consisting of a parent chain and multiple subchains. The framework partitions the subchain network based on business, with each subchain dedicated to storing service invocation records generated within a specific business unit. The smart contract deployed on the parent chain will settle the invocation records in all subchain networks as transaction records and facilitate automatic transfers among blockchain accounts. This design leverages blockchain's inherent reliability while improving its scalability in large-scale scenarios. Additionally, a novel consensus protocol, REFEREE, is introduced and applied to the subchain network, ensuring efficient recording of invocation data and trusted verification among participants, further enhancing both trust and performance. Comparative experiments and analysis show that TrustPay's dual-layer blockchain structure and REFEREE protocol are not only reliable but also outperform baseline methods in terms of efficiency.

Artificial intelligence is rapidly encroaching on the field of service regulation. This work-in-progress article presents the design principles behind Horae, a unified specification language to model multimodal regulation rules across a diverse set of domains. We show how Horae facilitates an intelligent service regulation pipeline by further exploiting a fine-tuned large language model named RuleGPT that automates the Horae modeling process, thereby yielding an end-to-end framework for fully automated intelligent service regulation.

Recent years have witnessed remarkable advances in graph representation learning using Graph Neural Networks (GNNs). To fully exploit the unlabeled graphs, researchers pre-train GNNs on large-scale graph databases and then fine-tune these pre-trained G raph M odels (GMs) for better performance in downstream tasks. Because different GMs are developed with diverse pre-training tasks or datasets, they can be complementary to each other for a more complete knowledge base. Naturally, a compelling question is emerging: How can we exploit the diverse knowledge captured by different GMs simultaneously in downstream tasks? In this paper, we make one of the first attempts to exploit multiple GMs to advance the performance in the downstream tasks. More specifically, for homogeneous GMs that share the same model architecture but are obtained with different pre-training tasks or datasets, we align each layer of these GMs and then aggregate them adaptively on a per-sample basis with a tailored Recurrent Aggregation Policy Network (RAPNet). For heterogeneous GMs with different model architectures, we design an alignment module to align the output of diverse GMs and a meta-learner to decide the importance of each GM conditioned on each sample automatically before aggregating the GMs. Extensive experiments in various downstream tasks from 3 domains reveal our dominance over each single GM. Additionally, our methods (UniGM) can achieve better performance with moderate computational overhead compared to alternative approaches including ensemble and model fusion. Also, we verify that our methods are not limited to graph data but could be flexibly applied to multiple modalities. The codes are available at https://github.com/monica309673/UniGM.

Modern control systems, including robotics, drones, and autonomous vehicles, are increasingly incorporating intelligent controllers such as deep neural networks (DNNs) supported by heterogeneous processors. However, unlike conventional control algorithms on homogeneous platforms, the design and runtime execution of intelligent control tasks on heterogeneous computing platforms pose more rigorous demands and substantial challenges. These challenges encompass not only inherent conflicts between algorithm complexity and accuracy but also the couplings and trade-offs among run-time execution latency, end-to-end system performance, and reliability with timing constraints. To address these challenges, this paper introduces an end-to-end capability and scheduling co-design approach to efficiently design intelligent control tasks on heterogeneous computing architectures. We first introduce a novel and general control capability function, which bridges the control performance with the complexity of the intelligent controller, computation latency, and the properties of the physical plants. Subsequently, we formulate a comprehensive optimization problem to properly design algorithm capability and assign limited heterogeneous computational resources from offline heterogeneous resource allocation to run-time execution. Finally, we present a case study on the intelligent control of autonomous quadcopters (with the hardware-in-the-loop simulator built on Microsoft AirSim), and the extensive experiments demonstrate the superiority of the capability and scheduling co-design in terms of overall system performance compared with state-of-the-art design approaches.

Industrial Internet of Things (IIoT)-based control is growing rapidly, such as smart factories and industrial automation. Sensing and transmitting physical state measurements is the first step and the prerequisite for IIoT-based control. However, sensor interference (e.g., electromagnetic interference on sensing, temperature, and humidity variations in the field) and network interference (e.g., metal obstacles and background noises) may destroy the control performance by interfering with sensing and communication processes. Most of the present upstream “fixed sensors-networking-state estimation” approaches cannot effectively deal with sensor and network interferences due to the fixed measurements/estimation and network resource limitations. To optimize the performance of IIoT-based control, we propose a smart sensing and communication co-design (SSCC) framework to select more potential sensors and establish the corresponding network scheduling. SSCC consists of a smart estimator (SE) and a sensing communication mode switching (SCMS) agent. The SE detects sensor interference and obtains resilient state estimation based on collaborative sensing. SCMS agent dynamically switches sensor selections and network configurations (routing and transmission number) in an integrated manner based on the network and plant states by solving a performance optimization problem. We propose a lightweight SCMS approach by searching a predefined mode table. We perform simulations integrating TOSSIM and MATLAB/Simulink, and semi-physical experiments on a real wireless sensor-actuator network composed of TelosB nodes. The results show that the SSCC framework can effectively improve the control performance and enhance network energy efficiency under various types of interference by dynamically selecting sensors and allocating network resources.

Innovation and prosperity of the Modern Service Industry bring convenience and efficiency to our society. However, the service governance capability lags behind the development of the industry, causing problems such as service violations and poor service quality. Existing works towards service regulation for service design time such as business process compliance checking are restricted to certain types of rules. When services or policies undergo evolution, rapid iteration becomes challenging. Motivated by this, we propose a service regulation analysis framework for service design time. It includes three phases: the service regulation modeling phase, which realizes modeling of regulation requirements; the service violation recognition phase, proposing an automatic detection algorithm based on process semantics; and the violation trace-back phase, which supports rapid localization of violations. Based on previous work, we construct the Enhanced-LPD4VR, a dataset with a broader range of processes and more nuanced annotations. Furthermore, we introduce an Internet healthcare service case study that illustrates the effectiveness of our framework through comparative experiments.

Contrastive Learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive samples) and pushes the embeddings of other samples (negatives) apart. As revealed in recent studies, CL can benefit from hard negatives (negatives that are most similar to the anchor). However, we observe limited benefits when we adopt existing hard negative mining techniques of other domains in Graph Contrastive Learning (GCL). We perform both experimental and theoretical analysis on this phenomenon and find it can be attributed to the message passing of Graph Neural Networks (GNNs). Unlike CL in other domains, most hard negatives are potentially false negatives (negatives that share the same class with the anchor) if they are selected merely according to the similarities between anchor and themselves, which will undesirably push away the samples of the same class. To remedy this deficiency, we propose an effective method, dubbed \textbf{ProGCL}, to estimate the probability of a negative being true one, which constitutes a more suitable measure for negatives’ hardness together with similarity. Additionally, we devise two schemes (i.e., \textbf{ProGCL-weight} and \textbf{ProGCL-mix}) to boost the performance of GCL. Extensive experiments demonstrate that ProGCL brings notable and consistent improvements over base GCL methods and yields multiple state-of-the-art results on several unsupervised benchmarks or even exceeds the performance of supervised ones. Also, ProGCL is readily pluggable into various negatives-based GCL methods for performance improvement. We release the code at \textcolor{magenta}\url{https://github.com/junxia97/ProGCL}.

Graph contrastive learning (GCL) has emerged as a dominant technique for graph representation learning which maximizes the mutual information between paired graph augmentations that share the same semantics. Unfortunately, it is difficult to preserve semantics well during augmentations in view of the diverse nature of graph data. Currently, data augmentations in GCL broadly fall into three unsatisfactory ways. First, the augmentations can be manually picked per dataset by trial-and-errors. Second, the augmentations can be selected via cumbersome search. Third, the augmentations can be obtained with expensive domain knowledge as guidance. All of these limit the efficiency and more general applicability of existing GCL methods. To circumvent these crucial issues, we propose a Simple framework for GRAph Contrastive lEarning, SimGRACE for brevity, which does not require data augmentations. Specifically, we take original graph as input and GNN model with its perturbed version as two encoders to obtain two correlated views for contrast. SimGRACE is inspired by the observation that graph data can preserve their semantics well during encoder perturbations while not requiring manual trial-and-errors, cumbersome search or expensive domain knowledge for augmentations selection. Also, we explain why SimGRACE can succeed. Furthermore, we devise adversarial training scheme, dubbed AT-SimGRACE, to enhance the robustness of graph contrastive learning and theoretically explain the reasons. Albeit simple, we show that SimGRACE can yield competitive or better performance compared with state-of-the-art methods in terms of generalizability, transferability and robustness, while enjoying unprecedented degree of flexibility and efficiency. The code is available at: https://github.com/junxia97/SimGRACE.

For modern service industry (MSI), service pattern is a service provision approach to support the realisation of business model that involves participants from various domains and organizations. A comprehensive description and quantitative assessment of service patterns is of great significance for optimizing the organizational cooperation process in MSI and improving the competitiveness of enterprises. However, most relevant studies on service patterns stay at the level of business processes and qualitative analysis, lacking a comprehensive description of data, resources, and value exchanges among participants. Studies related to pattern assessment focus more on QoS (Quality of Service) rather than consideration of the utility of multi-participant collaboration. Hence, two issues need to be tackled for future development of MSI: a) How to systematically describe and distinguish service patterns with the same business processes. b) How to assess and compare service patterns quantitively and comprehensively. In this article, we propose a service pattern assessment framework which consists of two parts. As part one, we complement the service pattern description language (SPDL) with extended elements and observable attributes to empower it with quantitative analysis, namely Quantitative SPDL (SPDL-Q). In part two, a set of service pattern assessment metrics are designed to assess not only the quality of the services but also the cooperation efficiency of the participants and the orchestration effect of the service patterns elements. The proposed framework was then further validated by a case study, of which four E-commerce service patterns were studied to reveal their evolvement processes. Correlation experiments were also performed to identify the pattern features that have the greatest impact on each metric, so to provide guidance and suggestions for pattern design. Finally, the innovation and significance of the work are outlined and discussed.

For modern service industry (MSI), service pattern is a service provision approach to support the realisation of business model that involves participants from various domains and organizations. A comprehensive description and quantitative assessment of service patterns is of great significance for optimizing the organizational cooperation process in MSI and improving the competitiveness of enterprises. However, most relevant studies on service patterns stay at the level of business processes and qualitative analysis, lacking a comprehensive description of data, resources, and value exchanges among participants. Studies related to pattern assessment focus more on QoS (Quality of Service) rather than consideration of the utility of multi-participant collaboration. Hence, two issues need to be tackled for future development of MSI: a) How to systematically describe and distinguish service patterns with the same business processes. b) How to assess and compare service patterns quantitively and comprehensively.

The convergence of the Internet and traditional industries gives the birth to the crossover services, which break through the boundaries of domains, enterprises, and businesses. The design of the service pattern is one of the key points to the success of crossover services. Existing works are mainly aimed at resource and process convergence, unable to guide the design of whole crossover service. To address this issue, we propose a rule-based service pattern convergence framework for crossover service, which consists of participant convergence, resource convergence and service process convergence. In addition to summarizing the general rules of convergence, we introduce semantic similarity to promote deep pattern convergence. Finally, a case study is presented to prove the operability of this framework.