Rule discovery is a fundamental task in data analysis, with broad applications in data cleaning, knowledge extraction, and decision making. However, existing methods often generate a large number of functionally redundant rules, with a high time cost. To address this, a recent line of work, the first to introduce diversified top-$k$rule discovery, aims to identify a set of top-ranked rules that are both relevant and diverse. Despite this advancement, it still suffers from high user interaction overhead, computational inefficiency, and the inability to handle a common scenario of selecting a diverse subset from an existing rule set. In this paper, we propose a user-friendly and efficient framework for diversified top-$k$rule discovery. As a testbed, we consider Entity Enhancing Rules (REEs), which subsume common association rules and data quality rules as special cases. Our method allows users to specify lightweight preference templates, which are used to train a correlation model that captures user preferences and generates subjective embeddings for predicates and rules. Based on these embeddings, we define an objective function to jointly measure the relevance and diversity of rules in a unified vector space; moreover, we formulate and study two key problems: (i) selecting diversified top-$k$rules from an existing redundant rule set, and (ii) discovering diversified top-$k$rules directly from raw data. We prove that both problems are intractable and propose effective algorithms; in particular, the second problem is more challenging and thus we further optimize its solution with carefully designed pruning strategies and parallel optimization. Extensive evaluation on real-world datasets demonstrates that our algorithms consistently identify top-ranked relevant and diverse rules, achieving an average 14.4 × speedup (up to 35.57 ×) over the state-of-the-art method.

With the rapid proliferation of Web services, accurately and efficiently predicting Quality of Service (QoS) has become a critical challenge in the field of service recommendation.However, existing deep learning approaches often focus on isolated feature types of either users or services and lack the capacity to comprehensively model the complex interactions between them.To address this limitation, this paper proposes a novel QoS prediction model named Multi-Feature-Aware Expert Modeling (MFAE).MFAE systematically extracts and processes five heterogeneous types of features associated with users, services, and their interactions: ID features, network topology features, geo-spatial features, similarity features, and 3-sigma-based outlier features.To effectively handle the heterogeneity among these feature types, the model constructs a network of expert groups, where each expert group consists of multiple Multi-Layer Perceptrons (MLPs) dedicated to deep representation learning for a specific feature category.The outputs from these expert groups are then fused through a weighted aggregation to generate the final QoS prediction.We evaluate MFAE on a real-world QoS dataset.Experimental results show that when the matrix density ranges from 2.5% to 10%, MFAE consistently achieves lower Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) compared to six baseline methods, demonstrating its effectiveness and robustness in sparse scenarios.

In the Internet of Things (IoT) environment, predicting the Quality of Service (QoS) is a challenging task due to the diversity of devices and service types. The dispersed nature of data collected from edge devices further complicates data sharing, thereby affecting the integrity and standardization of QoS evaluation. To address these issues, this paper proposes a QoS prediction model named HRMI, which efficiently integrates decentralized data and accommodates heterogeneous information to improve user experience. The HRMI framework comprises three main phases and one information-theoretic loss function: (1)Reputation Assessment, which leverages Utility Maximization theory and a Reputation Hybridization module to derive user and service reputations; (2)Feature Extraction, which employs deep learning techniques to construct user and service feature vectors from contextual attributes such as IDs, regions, and reputations; (3)Feature Interaction, which applies an attention mechanism to capture multi-scale feature dependencies and uncover deeper feature correlations; and (4)Mutual Information Loss, which exploits complementary information among feature vectors by maximizing the mutual information between feature representations and predicted values. Extensive experiments conducted on a widely used real-world dataset demonstrate that HRMI consistently outperforms state-of-the-art baseline methods.

Fashion vision-language pre-training models have shown efficacy for a wide range of downstream tasks. However, general vision-language pre-training models pay less attention to fine-grained domain features, while these features are important in distinguishing the specific domain tasks from general tasks. We propose a method for fine-grained fashion vision-language pre-training based on fashion Symbols and Attributes Prompt (FashionSAP) to model fine-grained multi-modalities fashion attributes and characteristics. Firstly, we propose the fashion symbols, a novel abstract fashion concept layer, to represent different fashion items and to generalize various kinds of fine- grained fashion features, making modelling fine-grained attributes more effective. Secondly, the attributes prompt method is proposed to make the model learn specific attributes of fashion items explicitly. We design proper prompt templates according to the format of fashion data. Comprehensive experiments are conducted on two public fashion benchmarks, i.e., FashionGen and FashionIQ, and FashionSAP gets SOTA performances for four popular fashion tasks. The ablation study also shows the proposed abstract fashion symbols, and the attribute prompt method enables the model to acquire fine-grained semantics in the fashion domain effectively. The obvious performance gains from FashionSAP provide a new baseline for future fashion task research.11The source code is available at https://github.com/hssip/FashionSAP

Cross-modal hashing (CMH) has been widely used in multimedia retrieval applications for its low storage cost and fast indexing speed. Thanks to the success of deep learning, cross-modal hashing has made significant progress with high-quality deep features. However, the modal gap is still a crucial bottleneck for existing cross-modal hashing methods: the commonly used convolutional neural network and bag-of-words encoders are customized for single modal prior, limiting the models to learn semantics representation in a cross-modal space. To overcome modality heterogeneity, we propose a shared transformer encoder (UniHash) to unify the cross-modal hashing into the same semantic space. A contrastive label correlation learning (CLC) loss using the category labels as modality bridge is designed together to improve the representation quality. Moreover, we take advantage of the multi-hot label space and propose a negative label generation (NegLG) strategy to get richer and uniformly distributed negative labels for contrast. Extensive experiments on three benchmarks verify the advantage of our proposed method. Besides, the proposed UniHash outperforms state-of-the-art cross-modal hashing methods significantly, establishing a new important baseline for the cross-modal hashing research. Codes are released github.com/idealwhite/Unihash.

Driven by the tremendous application demands, the Internet of Things (IoT) systems are expected to fulfill computation-intensive and latency-sensitive sensing and computational tasks, which pose a significant challenge for the IoT devices with limited computational ability and battery capacity. To address this problem, edge computing is a promising architecture where the IoT devices can offload their tasks to the edge servers. Current works on task offloading often overlook the unique task topologies and schedules from the IoT devices, leading to degraded performance and underutilization of the edge resources. In this article, we investigate the problem of fine-grained task offloading in edge computing for low-power IoT systems. By explicitly considering: 1) the topology/schedules of the IoT tasks; 2) the heterogeneous resources on edge servers; and 3) the wireless interference in the multiaccess edge networks, we propose a lightweight yet efficient offloading scheme for multiuser edge systems, which offloads the most appropriate IoT tasks/subtasks to edge servers such that the expected execution time is minimized. To support the multiuser offloading, we also propose a distributed consensus algorithm for low-power IoT devices. We conduct extensive simulation experiments and the results show that the proposed offloading algorithms can effectively reduce the end-to-end task execution time and improve the resource utilization of the edge servers.

The last decade has witnessed the rapid development of Internet of Things (IoT). The IoT applications are becoming more and more computation-intensive and latency-sensitive, which pose severe challenges for the resource-constrained IoT devices. To empower the computational ability of the IoT systems, edge computing emerges as a promising approach which allows the resource-constrained devices to offload their tasks to edge servers. A major challenge, which has been overlooked by most existing works on task offloading, is the dependencies among tasks and subtasks, which can have a significant impact on the offloading decisions. Besides, the existing works often consider offloading tasks to specific edge servers, which may underutilize the edge resources in the ultra-dense edge networks. In this paper, we investigate the problem of dependency-aware task offloading in ultra-dense edge networks. Specifically, we explicitly analyze the task dependency as directed acyclic graphs (DAGs) and establish full parallelism between edge servers and IoT devices. We further formulate task offloading as a joint optimization problem for minimizing both task latency and energy consumption. We prove the problem is NP-hard and propose a heuristic algorithm, which guarantees the dependency among subtasks and improves the task efficiency. Simulation experiments demonstrate that the proposed work can effectively reduce the task latency in ultra-dense edge networks.

With the various emerging innovative applications, the Internet-of-Things (IoT) systems are expected to fulfill more computation-intensive and latency-sensitive sensing and computational tasks, which pose huge challenges for the IoT devices with limited computational ability and battery capacity. To address this problem, edge computing is a promising architecture where the IoT devices can offload their tasks to the edge servers. Current works on task offloading often overlook the unique task topologies and schedules from the IoT devices, leading to degraded performance and underutilization of the edge resources. In this paper, we investigate the problem of fine-grained task offloading in edge computing for low-power IoT systems. By explicitly considering 1) the topology/schedules of the IoT tasks, 2) the heterogeneous resources on edge servers and 3) the wireless interference in the multi-access edge networks, we propose a lightweight yet efficient offloading scheme for multi-user Edge systems, which offloads the most appropriate IoT tasks/subtasks to edge servers such that the expected execution time is minimized. Both centralized and distributed algorithms are devised in both sparse and dense network scenarios. We conduct extensive simulation experiments and the results show that the proposed offloading algorithms can effectively reduce the end-to-end task execution time and improve the resource utilization of the edge servers.