Existing hierarchical text classification (HTC) methods typically use prompt tuning or contrastive learning to inject the label hierarchy into a model as prior knowledge to implicitly learn label embeddings for classification.However, such implicit learning fails to accurately reflect label geometry (i.e., feature spatial distribution of label embeddings), as it does not model hierarchy-aware geometric relations among labels.To address this issue, we propose a novel two-stage label geometry structuring and aligning framework, termed LGSA, which transforms the label hierarchy from an implicit prior into an explicit embedding.First, we propose a hierarchical geometric structuring (HGS) module that leverages a general orthogonal frame (GOF) to reconstruct an explicit label geometry conforming to the label hierarchy.The label geometry is then treated as a label prototype to guide model training.To facilitate the guidance, we thereby propose a hierarchical geometric aligning (HGA) module as a regularization term to align label geometry learned by the model with the explicit label prototype.Experiments on three realworld HTC datasets confirm that LGSA consistently outperforms existing state-of-the-art methods.

Accurately capturing the spatial correlations of traffic network significantly benefits short-term traffic forecasting. Some existing works represent spatial correlations in a simple one-dimensional space, but they cannot represent the real spatial correlations among sensors comprehensively. The other existing works represent the spatial correlations through grid-based method, but the local correlation of constructed spatial map is too superficial to extract deep spatial features effectively. Therefore, a novel deep learning model is proposed, which aims to represent the spatial correlations more effectively through a new correlation matrix structure. In the proposed model, the correlations among sensors are calculated from multiple perspectives to construct the speed, volume, and occupancy correlation matrices respectively. Then, considering that highly correlated sensors are close in the spatial dimension, an enhanced heuristic optimization algorithm is proposed to evolve these three correlation matrices into optimal ones by reorganizing the highly correlated sensors into each others neighborhood. Finally, the three optimal correlation matrices are combined to form a three-dimensional multivariate correlation matrix characterized by locally high correlation, which is beneficial to exploit the deep spatial features of traffic network. The experiments show that the proposed model has better accuracy and stability than other commonly used baseline models.

As a promising method for organizing remanufacturing production activities, remanufacturing scheduling has attracted increasing attention in recent years. However, extant studies have primarily focused on solving remanufacturing scheduling problems in a deterministic environment, while neglecting the impact of uncertainties on remanufacturing. Therefore, a new scenario-based robust remanufacturing scheduling problem was investigated in this study, and a robust optimization model for this problem was established. In the proposed model, a discrete scenario set is used to describe the uncertain arrival time and uncertain processing time of end-of-life products, and the variable start-up batch size constraint is considered to improve the practicality and flexibility of the model. To solve this model, an improved biogeography-based optimization algorithm with a new three-dimensional unequal-length representation scheme is proposed, in which, new migration and mutation operators, a local search strategy, and a new batch promotion mechanism are designed to improve the algorithmic performance. The results of the experiments demonstrate the feasibility of the proposed model and the superiority of the presented algorithm in solving the proposed model.

The combination of service-oriented architecture (SOA) and peer-to-peer (P2P) architecture plays a promising role in distributed manufacturing environments in that the peer service can be used to facilitate the integration and discovery of distributed manufacturing resources and achieve communication and collaboration across distributed virtual enterprises. However, the large size, dynamic nature, and heterogeneous expression of distributed manufacturing resources bring forth a serious challenge in scalability and efficiency. This paper presents a self-organized P2P framework that supports scalable and efficient manufacturing service (MS) discovery for cross-enterprise collaboration by forming and maintaining autonomous enterprise peer groups (PG). Each enterprise exhibits as a peer that provides some sharable MSs that are represented comprehensively and formally with a generalized ontology. Each enterprise PG dynamically clusters a set of enterprise peers offering semantically similar MSs, and elects the most reputed peer through multicriteria trust evaluation as its core (i.e., super peer, SP). Then, a MS request can be first routed to the suitable SP and further to its leaf peer in a systematic way, thus supporting efficient service discovery. A prototype system is implemented on JXTA for real application and validated through an experimental case study.