The continuous emergence of new entities, relations, triples, and multimodal information drives the dynamic evolution of multimodal knowledge graph (MMKG). However, existing MMKG embedding models follow a static setting, where training from scratch for growing MMKG wastes learned knowledge, while fine-tuning on new knowledge easily leads to catastrophic forgetting, severely limiting their applicability in real-world scenarios. To address this, we propose a multimodal continual representation learning framework (MoFot) for growing MMKG. Unlike existing static multimodal embedding methods, MoFot focuses on alleviating catastrophic forgetting rather than retraining to adapt to new knowledge. Specifically, MoFot effectively mitigates catastrophic forgetting caused by parameter updates and differing forgetting rates across modalities through a multimodal collaborative modulation mechanism. The mechanism ensures consistent retention of previously learned multimodal knowledge across snapshots through multimodal weight modulation and multimodal feature modulation. MoFot outperforms existing MMKG embedding, KG continual learning, and MMKG inductive models. Experimental results demonstrate that MoFot not only avoids forgetting but also enhances old knowledge by learning new knowledge, achieving adaptation to new knowledge while mitigating forgetting of old knowledge.

A reliable autonomous driving system requires a high-precision perception module. Collaborative perception is emerging as a web-scale information-sharing paradigm for autonomous driving, enabling multiple vehicles to collectively achieve a broader perception field than any single vehicle. However, existing approaches necessitate frequent one-to-many communication, which increases network load and leads to information redundancy. This paper presents Octopus, an innovative vehicle-to-road collaboration framework that leverages the computational capabilities of roadside units. Instead of frequent one-to-many communication, vehicles interact only with roadside units, which significantly reduces communication overhead and improves real-time processing efficiency. While this design alleviates communication burdens, vehicles may still struggle to achieve comprehensive situational awareness in highly dynamic environments. To further address this limitation, our framework incorporates global fusion results as prior knowledge, enabling closed-loop fusion to refine vehicle-side perception. Extensive experiments on OPV2V and V2V4Real datasets demonstrate that Octopus excels at collaborative perception, outperforming the state-of-the-art approach up to 11.58% on [email protected], 12.74% on [email protected] and 5514× reduction in communication volume.

• A simple and effective multi-site brain disease recognition framework based on tensor decomposition and personalized federated learning is proposed to quickly integrate samples from different hospitals/sites while enabling personalized feature extraction at each site. • A designed Dynamic Prototype Aggregation (DPA) module utilizes a sliding window technique to capture the intrinsic characteristics of time-varying BOLD signals. • A dual-feature aggregation module is designed to aggregate coarse-grained shared features and fine-grained prototype representation features, respectively, to facilitate efficient knowledge sharing among sites. Brain diseases significantly impact physical and mental health, making the development of models to identify biomarkers for early diagnosis essential. However, building high-quality models typically relies on large-scale datasets, while the privacy-sensitive nature of medical data often restricts its sharing and utilization. Multi-site studies provide a potential solution by integrating data from various sources, yet existing methods frequently neglect site-specific private features, such as demographic information. Therefore, in this paper, we propose a simple yet effective framework based on Tensor Decomposition and Personalized Federated Learning (TDPFL) for multi-site brain disease recognition, while protecting these private features. On the central server, we designed a dual feature aggregation module to facilitate efficient knowledge sharing among sites. On the client side, we introduced a personalized branch to safeguard private information ( i.e. , age, gender, and education) and developed a tensor decomposition module to extract features from subjects’ brain scan data. Furthermore, we developed a dynamic prototype aggregation module to monitor evolving brain features over time. This mechanism enhances the model’s capacity to capture these dynamics, thereby improving classification and prediction accuracy. Experiments on two publicly available rs-fMRI datasets across six sites showed that TDPFL outperformed baseline methods with a 4 % improvement in average classification accuracy. Additionally, we identified site-specific brain disease-related biomarkers, offering novel insights into early diagnosis. Code is available at https://github.com/ChaojunZ/TDPFL.git

Recently, most image segmentation methods exhibit an extreme trade-off between performance and efficiency, resulting in approaches with high performance typically having low computational efficiency, while efficient methods compromise on segmentation accuracy. To address this dual challenge, this study introduces a simple yet efficient segmentation framework based on Multi-scale Prototype matching and visual Sparse Attention mechanisms (MPSA), which is a transformer-based architecture designed to optimize the balance between performance and efficiency. The proposed MPSA integrates a novel lightweight cross-attention mechanism and prototype selection and filtering strategy to accurately correlate category queries with corresponding visual objects with a multi-scale Feature Pyramid Network (FPN). Within the pixel decoder, our Axial Convolution Enhanced (ACE) module mitigates lost global context by combining depth-wise separable convolutions with deformable convolutions, thereby recovering global semantics while preserving fine-grained spatial details. Through this innovative design, MPSA demonstrates outstanding performance in both semantic and panoptic segmentation tasks across multiple datasets. Remarkably, MPSA achieves surprising 83.9% mIoU with only 114M parameters on the Cityscapes dataset while compared to some state-of-the-art architectures, highlighting its ability to deliver exceptional results with significantly reduced resource consumption. Our code is released at https://github.com/zxqing01/MPSA.

Text-based visual question answering (TextVQA) aims to answer questions by understanding scene text in images. However, many current methods overly depend on the accuracy of Optical Character Recognition (OCR) systems, while overlooking the significance of visual objects. They tend to perform poorly when the question involves the relationships between visual objects and scene text. To address the above issues, we focus on raising the status of visual objects and innovatively propose a hierarchical semantic reasoning network (CT-HSR) based on the cascade transformer architecture, achieving fine-grained cross-modal reasoning and visual semantic enhancement. Specifically, the visual representations containing rich semantic information of the question modality are obtained through the cross-modal transformer-based vision-language pre-training model firstly. Then, the uni-modal transformer for unified modality encoding module is utilized to capture visual objects that are more semantically related to OCR texts. In addition, we further alleviate the cross-modal noise interference through the feature filtering strategy. Finally, we better align the three modalities by introducing TextVQA pre-training tasks and generate prediction answers through multi-step iterative prediction during fine-tuning. Extensive experiments on the TextVQA, ST-VQA, and OCR-VQA datasets have demonstrated the effectiveness of our proposed model compared to the state-of-the-art methods. The code will be released at https://github.com/FTFWO/CT-HSR .

Multi-access edge computing (MEC) has garnered increasing attention from users due to low web service latency. Edge servers deployed near base stations have limited resources and can only serve users within their coverage areas. Therefore, efficiently allocating users to the appropriate edge servers is crucial for significantly enhancing system performance. Traditional edge user allocation (EUA) strategies often rely on precise user location, leading to significant privacy leakage risks and weakening users' trust. To tackle this challenge, this paper presents Disguiser, a novel privacy-preserving scheme designed to achieve efficient edge user allocation while safeguarding user location privacy. Disguiser employs a Laplace noise-based location obfuscation mechanism to ensure users' privacy. To resolve the user allocation problem after location obfuscation, which involves balancing real-time performance and accuracy, we design a two-stage user allocation algorithm, TEUA, consisting of the LR-EUA initial allocation algorithm and the MR-EUA reallocation algorithm. First, a novel EUA algorithm, LR-EUA, is integrated into Disguiser, innovatively combining linear relaxation with a greedy approach. Additionally, Disguiser further minimizes resource wastage in MEC systems caused by location obfuscation by employing the MR-EUA algorithm at base stations. Experimental results show that Disguiser effectively balances privacy protection with system performance, substantially outperforming existing state-of-the-art methods.

The continual emergence of new entities and relations drives the dynamic expansion of knowledge graphs (KG). In the face of such growing KG, relearning from scratch wastes acquired knowledge, while learning solely from new snapshots leads to model forgetting of old knowledge. Existing methods focus on lifelong learning in growing KG through transfer and regularize embeddings. However, extensive entity updates to adapt to new snapshots introduce conflicts between old and new knowledge, thereby resulting in the inevitable occurrence of knowledge forgetting. To address these challenges, we propose the Evolutionary Relation Path Passing (ERPP) model for lifelong knowledge graph embedding, aiming to shift from knowledge forgetting to knowledge accumulation, thereby achieving accurate long-term prediction. Specifically, we propose a snapshot conditional relation path passing strategy to generate expressive representations that better adapt to snapshots compared to the transferred embeddings in existing methods. Subsequently, we propose a relation inheritance and evolution mechanism across snapshots and continue relation path passing in next snapshots. This allows ERPP to avoid inevitable catastrophic forgetting from frequent entity embedding updates. ERPP outperforms SOTA models in 35 scenarios, with average improvements of 11.1% in long-term prediction and 12.9% in knowledge transfer. Moreover, ERPP makes a breakthrough in achieving knowledge positive accumulation, in contrast to the negative forgetting of existing models. To the best of our knowledge, ERPP is the first model to realize knowledge accumulation. Our code is available at https://anonymous.4open.science/r/ERPP-6D66.

Multimodal Knowledge Graphs (MMKG) models integrate multimodal contexts to improve link prediction performance. All existing MMKG models follow the transductive setting with a fixed predefined set, meaning that all the entities, relations, and multimodal information in the test graph are observed during training. This hinders their generalization to real-world MMKG with unseen entities and relations. Intuitively, a MMKG model trained on DBpedia cannot infer on Freebase. To address above limitations, we make the first attempt towards inductive learning for MMKG and propose a multimodal Inductive MMKG model (IndMKG) that is universal and transferable to any MMKG. Distinct from existing transductive methods, our model does not rely on specific trained embeddings; instead, IndMKG generates adaptive embeddings conditioned on any new MMKG via multimodal prototypes. Specifically, we construct class-adaptive prototypes to appropriately characterize the multimodal feature distribution of the given graph and equip IndMKG with robust adaptability to multimodal information across MMKGs. In addition, IndMKG learns non-specific structural embeddings based on meta relations. Such strategies tackle the challenge of notable multimodal feature discrepancies in cross-graph induction and allow the pre-trained IndMKG model to effectively zero-shot generalize to any MMKG. The strong performance in both inductive and transductive settings, across more than 20+ different scenarios, confirms the effectiveness and robustness of IndMKG. Our code is released at https://github.com/MMKGer/IndMKG/.

As a prevalent computing paradigm, graph computing provides an effective service strategy for the analysis of big data within the Internet of Everything (IoE), particularly for clustering graph-structured data in the IoE. Among various methods, graph contrastive clustering, which is devoted to revealing the intrinsic structure of graphs and efficiently grouping nodes into distinct clusters by contrasting positive-negative counterparts, has attracted widely attention in recent years. However, the existing methods seriously ignore the graph topology and node attributes when setting positive and negative sample pairs, which further leads to node semantic inconsistency. To this end, we design a novel tensor representation-based multiview contrastive graph representation learning framework, including adaptive data augmentation, high-confidence sample pairs construction, and a simple yet effective self-optimizing module guided by clustering objective function, to address issues of graph contrastive learning in ignoring complementary information among the topology and attributes. Specifically, by jointly modeling the graph structure and multiview node attributes, the new proposed clustering model can concurrently mine both hard positive and negative samples, and dynamically enhance the weight allocation of the hard samples during the learning process. Then leveraging the characteristics of graph-structured data, we incorporate a small subset of nodes with the highest similarity as additional positive samples to improve the discriminative power of the proposed model. Furthermore, a self-optimizing clustering module is introduced to enhance the algorithm’s performance. Experimental results on four commonly used IoE-related data sets validate that our proposed approach can achieve state-of-the-art clustering performance.

Hyperdimensional computing (HDC) is a human brain-inspired computing paradigm that processes neural activity patterns with high dimensional vectors. Existing HDC accelerators usually utilize different hardware architectures to process encoding phases and comparison phases of HDC applications separately. They are unable to adapt to dynamic workloads for various datasets, resulting in resource underutilization. In this article, we propose a resistive random access memory (ReRAM)-based HDC accelerator called ReHDC for general HDC. We abstract the computing paradigms in encoding and comparison phases, and provide uniform primitive operators to efficiently process these two phases with the same hardware architecture. In the unified processing engine, ReHDC utilizes analog crossbar arrays to accelerate accumulation operations, and digital crossbar arrays to speed up high-dimensional element-wise operations (xor). Experimental results show that ReHDC can accelerate the HDC training by$69.4\times $and$1.93\times $, and can also improve the energy efficiency by$51.5\times $and$2.2\times $, compared with NVIDIA Tesla P100 GPU and the ReRAM-based HDC accelerator DUAL, respectively. Moreover, the performance speedup and energy efficiency for HDC inference are similar to that of HDC training.

Over the past few years, multiview attributed graph clustering has achieved promising performance via various data augmentation strategies. However, we observe that the aggregation of node information in multilayer graph autoencoder (GAE) is prone to deviation, especially when edges or node attributes are randomly perturbed. To this end, we innovatively propose a tensor-representation-based multiview attributed graph clustering framework with smooth structure (MV_AGC) to avoid the bias caused by random view construction. Specifically, we first design a novel tensor-product-based high-order graph attention network (GAT) with structural constraints to realize efficient attribute fusion and semantic consistency encoding. By imposing attribute augmentation mechanisms and smooth constraints (SCs) on the proposed high-order graph attention autoencoder simultaneously, MV_AGC effectively eliminates the instability of reconstructed graph structures and learns a more compact node representation during training. In addition, we also theoretically analyze the stronger generality and expressiveness of the proposed tensor-product-based attention mechanism over the classical GAT and establish an intuitive connection between them. Furthermore, to address the performance degradation caused by clustering distribution updating, we further develop a simple yet effective clustering objective function-guided self-optimizing module for the final clustering performance improvement. Experimental results on the six benchmark datasets have demonstrated that our proposed method can achieve state-of-the-art clustering performance.

The emergence ofmobile edge computing(MEC) in distributed systems has sparked increased attention toward edge data management. A conflict arises from the disparity between limited edge resources and the continuously expanding data requests for data storage, making the reduction of data storage costs a critical objective. Despite the extensive studies of edge data deduplication as a data reduction technique, existing deduplication methods encounter numerous challenges in MEC environments. These challenges stem from disparities between edge servers and cloud data center edge servers, as well as uncertainties such as user mobility, leading to insufficient robustness in deduplication decision-making. Consequently, this paper presents a robust optimization-based approach for the edge data deduplication problem. By accounting for uncertainties including the number of data requirements and edge server failures, we propose two distinct solving algorithms: uEDDE-C, a two-stage algorithm based on column-and-constraint generation, and uEDDE-A, an approximation algorithm to address the high computation overhead of uEDDE-C. Our method facilitates efficient data deduplication in volatile edge network environments and maintains robustness across various uncertain scenarios. We validate the performance and robustness of uEDDE-C and uEDDE-A through theoretical analysis and experimental evaluations. The extensive experimental results demonstrate that our approach significantly reduces data storage cost and data retrieval latency while ensuring reliability in real-world MEC environments.

Edge computing, as an emerging paradigm in distributed computing, introduces a novel data access framework for latency-sensitive applications, enabling data retrieval from edge servers situated closer to users, rather than the remote cloud. This significantly reduces data retrieval latency, thereby enhancing the quality of experience. However, the resources of edge servers are highly constrained. Recent studies in erasure coding-based edge data storage have effectively sealed the gap between storage cost and data retrieval latency. Despite these advantages, the highly dynamic edge computing environments and frequent data updates introduce significant challenges in cache replacement for erasure coding-based edge storage systems. Specifically, direct data replacement, similar to traditional replica-based storage methods, may result in insufficient encoded blocks for reconstructing the original data during retrieval, which can increase data retrieval latency and even compromise data availability. In this paper, we identify and address, for the first time, the cache replacement problem in erasure coding-based edge storage systems. We propose a novel cache replacement algorithm, named ECCR, based on Lyapunov optimization, which effectively solves the cache replacement problem in dynamic edge computing environments. Theoretical analysis and extensive experiments on real-world datasets demonstrate the effectiveness and efficiency of the proposed method, which outperforms two state-of-the-art approaches and achieves an average system cost reduction of 49.78%.

Schema information is increasingly crucial to improve service discovery, recommendation, and composition, addressing link sparsity and lack of explainability inherent in methods relying solely on triples. However, existing approaches predominantly utilize schema information as a rigid filtering mechanism, equivalent to fixed conditions that lack the capability to adaptively adjust based on model learning. This paper introduces a novel learnable schema-aware knowledge embedding framework that enhances service link prediction by synergizing entity, relation, and type embeddings through a coupled matrix-tensor factorization model. To our knowledge, this is the first approach that couples entity and relation embeddings to enable adaptive learning ofSchemaEmbeddings (SchemaE). Our framework is both expressive and easy to use, with the capability to generalize to existing bilinear models. Within this framework, we further propose the schema prompt method for embedding isolated nodes, which typically suffer from sparse relations or the absence of neighbors, leading to biased representation often overlooked in existing works. Despite embedding schema information, our model remains lightweight due to the introduction of a parameter-efficient strategy via type assists. We conduct extensive experiments on four public datasets, including comparisons with existing SOTA models, parameter analysis, performance validation on extended models, and visualization. The experimental results confirm the effectiveness and efficiency of the proposed model.

Compilation optimization bugs are prevalent and can significantly affect the correctness of software products, posing serious challenges to software development. Identifying and localizing these bugs are critical tasks for compiler developers. However, the intricate nature and extensive scale of modern compilers make it difficult to pinpointing the root causes of such bugs. Previous research has introduced innovative techniques that generatewitness test programs–tests that pass–by mutating bug-triggering test cases, highlighting the importance of this problem and demonstrating the effectiveness of such approaches. Nevertheless, existing techniques based on witness test programs generation suffer from inherent limitations. Specifically, they do not guarantee the successful creation of witness test programs via mutation and are often time-consuming, typically requiring extensive iterations to produce a valid witness test program. In this study, we present Odfl, a simple yet effective approach for automatically isolating compiler optimization faults by introducing the concept ofdifferentiated compilation configurations. The core insight behind Odfl is that modifying compilation settings such as disabling fine-grained compilation flags in GCC or reducing the number of fine-grained compilation passes in LLVM, can suppress the manifestation of compiler bugs triggered by the same test program. Through adjusting these settings, Odfl creates differentiated compilation configuration that produce multiple compiler executions with distinct pass/-fail outcomes. We utilize these differentiated configurations to collect both passing and failing compiler coverage, and then applySpectrum-Based Fault Localization (SBFL)techniques to rank compiler source files based on their suspiciousness. Our evaluation of 60 GCC and 50 LLVM compiler bugs demonstrates that Odfl substantially outperforms state-of-the-art compiler fault localization techniques in terms of both effectiveness and efficiency. Notably, Odfl achieves over 90% improvement in accurately ranking the top-1 faulty source files compared to three existing techniques–DiWi, RecBi, and LLM4CBI–and reduces fault localization time by more than 99% on average.

Link prediction aims to infer missing valid triplets to complete knowledge graphs, with recent inclusion of multimodal information to enrich entity representations. Existing methods project multimodal information into a unified embedding space or learn modality-specific features separately for later integration. However, performance was limited in such studies due to neglecting the modalities compatibility and conflict semantic carried by entities in valid and invalid triplets. In this paper, we aim at modeling inter-entity modality interactions and thus propose a novel Modality Circular fusion approach (MoCi), which interweaves multimodal contextual of entities. Firstly, unlike most methods in this task that directly fuse modalities, we design a triplets-prompt modality contrastive pre-training to align modality semantics beforehand. Moreover, we propose a modality circular fusion model using a simple yet efficient multilinear transformation strategy. This allows explicit inter-entity modality interactions, distinguishing it from methods confined to fuse within individual entities. To the best of our knowledge, MoCi presents one of the pioneering frameworks that tailored to grasp inter-entity modality semantics for better link prediction. Extensive experiments on seven datasets demonstrate our model yields SOTA performance, confirming the efficacy of MoCi in modeling inter-entity modality interactions. Our code is released at https://github.com/MoCiGitHub/MoCi.

Global news events graphs (GNEG) are designed for the noisy and ungrammatical world’s news media, aiming at capturing the true insight and providing explanations by incorporating potential dimensions and network structures of global news. This article focuses on the temporal representation learning of GNEG to eliminate misunderstanding or ambiguity caused by missing information. Although some temporal models have been developed, the crossover interactions among entity, relation, and time have not been explicitly discussed. The multidirectional effects between entities, relations, and timestamps matter in predicting the establishment of quadruples. This motivates the proposal of learning temporal interaction embeddings (TIE) to benefit GNEG link prediction performance. Specifically, we propose the following. 1) We propose a crossover convolution layer to learn the two-by-two and common interaction features of entity, relation, and time in GNEG to capture their potential effect patterns in the context of different quadruples. 2) For the learned interaction information, we adopt tensor neural network (TNN) to maintain the multiple order structure and further extract effective features to improve prediction. 3) A tensor temporal consistency constraint (TCC) is proposed to enhance the learning of time-weakly sensitive information and induce the embeddings to have a certain compatibility over time. Finally, we carried out extensive experiments on three benchmark datasets, the results proved that the performance of the proposed TIE model is competitive with the state-of-the-art methods.

As an important part of cyber–physical–social intelligence, artificial intelligence (AI)-driven smart healthcare is committed to promoting the application of human–machine hybrid augmented intelligence in the medical field, including AI-assisted medical image analysis and lesion recognition. Among them, deep learning models represented by fully convolutional networks (FCNs) have achieved excellent performance in medical image segmentation. However, limited by the complex structure of segmentation networks and the inherently redundant characteristics of convolutional operation, the scale of these models is extremely large. To further promote the application of machine intelligence in the field of medical image analysis, we propose an attention U-Net based on Bi-ConvLSTM (AUBC-Net) for accurate segmentation of medical images in this article. Different from classical U-Net, the proposed model deals with the potential association between decoding features and encoding features by bidirectional convolution LSTM. Furthermore, for the inherent redundancy characteristics of FCNs, we propose a lightweight feature generation strategy and optimize the calculation process of Bi-ConvLSTM based on tensor multilinear algebra, which can greatly reduce the number of network parameters. In addition, we have conducted the image segmentation experiments on two benchmark medical datasets, and the experimental results demonstrate that the proposed model can not only achieve better performance than existing methods, but also effectively compress network parameters while ensuring performance, which greatly facilitates AI-driven smart medical applications.

With the deepening of industry 4.0 paradigm in logistics systems, artificial intelligent has been widely used to improve the quality of logistics services. Considering that data collected in comprehensive logistics service system usually integrate multistage complex information such as traffic flow records and spatiotemporal trajectory, it is inevitable that the data are incomplete and partially missing due to equipment failures, communication interruptions, etc. As an effective spatiotemporal completion tool in logistics systems, low-rank tensor completion has aroused extensive research interest thanks to its excellent performance on data recovery. Although existing tensor completion methods effectively capture the complex associations/dependencies of multidimensional inputs, they fail to exploit the potential characteristics of spatiotemporal data, such as the periodicity. In this article, we propose a jointly low-rank tensor completion method for logistics data completion, which constructs multiple periodic subtensors by setting an appropriate time window, then performs jointly low-rank completion and imputation. In addition, we also provide an optimization algorithm based on Alternating Direction Method of Multiplier framework for the proposed problem. Experimental results on four logistics-related datasets have further demonstrated the promising performance of the proposed method compared with other state-of-the-art competitors. We believe that the proposed approach not only effectively maintains the advantages of classical completion methods, but also fully excavates the multidimensional correlation and hidden patterns behind records, and further provides a novel and effective strategy for data completion and imputation in logistics systems.

Combining data-driven approaches and physical laws for industrial trajectory prediction can improve the performance of industrial applications such as path planning of robots and route selection of vehicles in transportation systems. In the era of industrial Big Data, the application of industrial trajectory prediction based on the physical Markov process and tensor model has attracted much attention. To synchronously improve the prediction accuracy and computational efficiency, this article proposes a tensor-train (TT)-based multiuser multivariate multiorder (3M) physical Markov prediction approach for multimodal industrial trajectory pattern mining. First, we propose a TT-based unified product calculation rule with its scalable computation approach based on decomposed TT cores to speed up the execution efficiency. Then, a TT-based 3M (TT-3M) Markov transition approach is presented. Furthermore, we put forward a TT-based power method to calculate the stationary joint eigentensor (SJE) and an SJE-based multimodal prediction algorithm to mine concealed trajectory patterns. Experimental results based on real GPS trajectory dataset show that compared with the original tensor-based 3M approach, the TT-3M approach can improve the computational efficiency up to three times and reduce the storage space proportion to a minimum of 1‰ while ensuring basically consistent prediction accuracy.

Augmented Intelligence of Things empowered by knowledge graph drives cognitive intelligence for smart enterprise management systems (EMS). Knowledge fusion technology can effectively integrate knowledge from different sources, thereby improving the accuracy and richness of the knowledge graph, which is of great significance to the sustainable development of smart EMS. Traditional machine learning methods on graphs face challenges in the fusion of complex and multirelational enterprise knowledge graphs due to inherent defects in relation semantic and local structure information capturing. In order to break through these limitations and improve EMS knowledge graphs, we propose tensor-based graph attention networks for multirelational graph representation learning (MR-GAT), and apply it to the critical tasks in knowledge fusion: Entity and relation alignment. Specifically, we innovatively adopt tensor operations to adequately model the interactions between entities and relations in EMS knowledge graph to learn more accurate representations. Additionally, we propose a relation attention mechanism, which focuses on assigning weights in the process of aggregating local semantic information for relation learning in an EMS knowledge graph. Furthermore, we develop a joint entity and relation alignment framework by utilizing the proposed multirelational graph attention networks to improve the accuracy of knowledge fusion. Experimental evaluations on three datasets present that the proposed approach outperforms the baseline models by about 1.4% on average in terms of the mean reciprocal rank metric, which demonstrates the superior ability of the proposed MR-GAT in representation learning for knowledge fusion in smart EMS.

Code optimization is an essential feature for compilers and almost all software products are released by compiler optimizations. Consequently, bugs in code optimization will inevitably cast significant impact on the correctness of software systems. Locating optimization bugs in compilers is challenging as compilers typically support a large amount of optimization configurations. Although prior studies have proposed to locate compiler bugs via generating witness test programs, they are still time-consuming and not effective enough. To address such limitations, we propose an automatic bug localization approach, ODFL, for locating compiler optimization bugs via differentiating finer-grained options in this study. Specifically, we first disable the fine-grained options that are enabled by default under the bug-triggering optimization levels independently to obtain bug-free and bug-related fine-grained options. We then configure several effective passing and failing optimization sequences based on such fine-grained options to obtain multiple failing and passing compiler coverage. Finally, such generated coverage information can be utilized via Spectrum-Based Fault Localization formulae to rank the suspicious compiler files. We run ODFL on 60 buggy GCC compilers from an existing benchmark. The experimental results show that ODFL significantly outperforms the state-of-the-art compiler bug isolation approach RecBi in terms of all the evaluated metrics, demonstrating the effectiveness of ODFL. In addition, ODFL is much more efficient than RecBi as it can save more than 88% of the time for locating bugs on average.

Knowledge graph builds the bridge from massive data generated by the interaction and communication between various objects to intelligent applications and services in Internet of Things. The graph representation learning technology represented by graph neural networks plays an essential role in the understanding and reasoning of the knowledge graph with complicated internal structure. Although they are capable of assigning different attention weights to neighbors, the graph attention network (GAT) and its variants are inherently flawed and inadequate in modeling high-order knowledge graphs with high heterogeneity. Therefore, we propose a novel multirelational GAT framework in this article for knowledge reasoning over heterogeneous graphs by employing tensor and tensor operations. Specifically, we formulate the general high-order heterogeneous knowledge graph first. Then, the tensor GAT (TGAT), composed of three components: 1) heterogeneous information propagation; 2) multimodal semantic-aware attention; and 3) knowledge aggregation, is developed to simulate rich interactions between mixed triples, entities, and relationships when aggregating local information. What is more, we utilize the Tucker model to compress the parameters of TGAT and further reduce the storage and calculation consumption of the intermediate calculation process on the premise of maintaining the expressive power. We conduct extensive experiments to solve the link prediction task on four real-world heterogeneous graphs, and the results demonstrate that the TGAT model proposed in this article remarkably outperforms state-of-the-art competitors and improves the hits@1 accuracy by up to 7.6%.

Human-oriented and machine-generated data in cyber-physical-social systems are often complicated graph-structured. Graph-powered learning methods are conducive to discovering valuable knowledge from large-scale graph data and improving decision-making processes. However, due to the neglect of diverse relations among things, most existing knowledge reasoning studies are inherently flawed and inefficient in processing the heterogeneous graphs with high-order connectivity. Tensor, as a powerful and effective tool to model high-level semantic interactions between various things, can provide high-order Internet of things graph with new perspectives and possibilities. Therefore, this article innovatively proposes a collaborative artificial intelligence of things data analysis and application framework based on Boolean tensors, which supports the expression and fusion of heterogeneous graph and ultimately promotes the AI processing. In this context, we focus on developing an incremental Boolean tensor factorization (IBTF) approach for efficient knowledge reasoning to meet the requirements of real-time and high-level quality demands for intelligent services. To the best of our knowledge, we are the first to do this work. More concretely, we present factors update and binary features merge algorithms for the integrated graph tensors to avoid numerous repeated calculations of historical data. Experimental results on general synthetic datasets demonstrate that the IBTF approach proposed in this article guarantees nearly equal approximate accuracy while reducing execution time by dozens and even more of times. Furthermore, experimental evaluations and interpretability analysis on real-world datasets verify the practicality of the proposed framework and approach.