Multi-Label Classification refers to the classification task where a data sample is associated with multiple labels simultaneously, which is widely used in text classification, image classification, and other fields. Different from the traditional single-label classification, each instance in Multi-Label Classification corresponds to multiple labels, and there is a correlation between these labels, which contains a wealth of information. Therefore, the ability to effectively mine and utilize the complex correlations between labels has become a key factor in Multi-Label Classification methods. In recent years, research on label correlations has shown a significant growth trend internationally, reflecting its importance. Given that, this paper presents a survey on the label correlations in Multi-Label Classification to provide valuable references and insights for future researchers. The paper introduces multi-label datasets across various fields, elucidates and categorizes the concept of label correlations, emphasizes their utilization in Multi-Label Classification and associated subproblems, and provides a prospect for future work on label correlations.

Low-Power Wide-Area Networks (LPWANs), extensively utilized for connecting billions of IoT devices, encounter wireless interference challenges in unlicensed frequency bands. Cutting-edge research suggests employing Received Signal Strength Indication (RSSI) sequences for error detection to mitigate interference-related issues. Nevertheless, the effectiveness of this method significantly declines under low signal-to-noise ratios (SNRs). Additionally, long-range communication often results in low SNR received signals, sometimes even below the noise floor. Targeting this fundamental issue, this article proposes the LPWAN packet technique, broadly applicable across diverse scenarios through edge–cloud collaboration. On the edge side, we propose an innovative architecture that fully exploits spatial distribution and interference independence in the field. Rather than utilizing resource-intensive RSSI-based error detection, we leverage a lightweight coding scheme for error detection at the Long Range (LoRa) edge, forwarding correct frames to the cloud. On the cloud side, packet recovery is achieved utilizing group-weighted voting. We design and implement ECRLoRa with commercially available devices (SemTech’s SX1278 and SX1302 LoRa chipsets) and assess its performance in low SNR environments. Our thorough evaluation demonstrates that our approach attains a Packet Recovery Ratio of 96% with low SNR (i.e., below −10 dB), resulting in 1.8× throughput, 7.5× faster recovery time, and 4.92× average accuracy compared to state-of-the-art cloud-optimized application layer solutions.

Accurate customer LifeTime Value (LTV) predictions are crucial for customer relationship management, especially in Supply Chain Platforms (SCP), which involve effectively managing the service resources in business decision-making. Previous LTV prediction methods usually rely on ample historical customer data, which is not available in the early stages of a customer's lifecycle. It makes the modeling of the historical customer data a difficult task due to the data sparsity. Besides, the long-tail distribution of customer LTV also brings new challenges to the prediction of LTV. To tackle the above issues, we propose CDLtvS, a novel Cross Domain method for customer Lifetime value prediction in SCP. It leverages rich cross-domain information from upstream platforms to enhance LTV predictions in downstream platforms. Firstly, CDLtvS pre-trains the customer representations by an LTV modeling framework named LtvS in source and target domains separately. Specifically, LtvS incorporates the Expert Mask Network (ExMN), which not only effectively models the long-tail distribution of LTV in single-domain but also resolves cross-domain learning model bias resulting from this distribution. Then, the various-level alignment mechanism is introduced to keep the consistency of knowledge transferring from source to target domains on both sparse and non-sparse data. Comprehensive experiments on real-world data from JD, one of the world's largest supply chain platforms, demonstrate that CDLtvS achieves a normalized mean average error of 0.3378 in LTV prediction, outperforming 16.3% to the baseline. Additionally, the improvements of ≥2.3% across various data sparsity levels (0% -- 80%) provide valuable insights into cross-domain LTV modeling.

Hyperspectral remote sensing technology is swiftly evolving, prioritizing affordability, enhanced portability, seamless integration, sophisticated intelligence, and immediate processing capabilities. The leading model for classifying hyperspectral images, which relies on convolutional neural networks (CNNs), has proven to be highly effective when run on advanced computing platforms. Nonetheless, the high degree of parameterization inherent in CNN models necessitates considerable computational and storage resources, posing challenges to their deployment in processors with limited capacity like drones and satellites. This paper focuses on advancing lightweight models for hyperspectral image classification and introduces EBCNN, a novel binary convolutional neural network. EBCNN is designed to effectively regulate backpropagation gradients and minimize gradient discrepancies to optimize BNN performance. EBCNN incorporates an adaptive gradient scaling module that utilizes a multi-scale pyramid squeeze attention (PSA) mechanism during the training phase, which can adjust training gradients flexibly and efficiently. Additionally, to address suboptimal training issues, EBCNN employs a dynamic curriculum learning strategy underpinned by a confidence-aware loss function, Superloss, enabling progressive binarization and enhancing its classification effectiveness. Extensive experimental evaluations conducted on five esteemed public datasets confirm the effectiveness of EBCNN. These analyses highlight a significant enhancement in the classification accuracy of hyperspectral images, achieved without incurring additional memory or computational overheads during the inference process.

Motivated by the pursuit of greater efficiency, companies, such as Amazon and JD, are shifting toward a warehouse-distribution integration model to optimize logistics operations. In general full-link logistics scenarios, the collaboration between warehouses and sorting centers managed by different enterprises leads to data silos, posing challenges in securely sharing information and accurately predicting delivery times across the entire logistics network. Current delivery time prediction methods often overlook the heterogeneity of logistics networks and face data sharing constraints. We aim to address these issues by facilitating secure internode relationship analysis and leveraging distinct spatio-temporal characteristics to enhance efficiency. However, challenges remain in overcoming data isolation while maintaining protection and integrating diverse node characteristics for optimized modeling. To address these challenges, we propose the federated heterogeneous graph transformer (Fed-HGT) framework. This framework includes a federated training module that integrates local and central gradients by exchanging node representations and model parameters between logistics nodes and the central server. Additionally, it features a federated prediction module where local nodes compute time representations using their local data and transmit these to the central server. The central server then uses these representations to make accurate full-link delivery time predictions. Our method was evaluated on a dataset from a major e-commerce platform in China, demonstrating significant performance improvements over existing solutions.