Towards Classification of Web ontologies using the Horizontal and Vertical Segmentation

可复用材料本体的多层次架构——以OntoCrafter陶瓷本体(OCO)作为参考实现

A Multi-Level Architecture for Reusable Materials Ontologies -- The OntoCrafter Ceramics Ontology (OCO) as Reference Implementation

针对材料科学本体在水平、垂直和机制三个维度上的碎片化问题，提出一种多层次模块化架构，通过抽象层次和消费受众两个独立分类轴，并在材料特定层内采用七层机制解释骨架，以OntoCrafter陶瓷本体(OCO v0.94)作为参考实现。

语言模型中的演绎推理：横向与纵向推理

Deductive Logic in Language Models: Horizontal vs Vertical Reasoning

研究小型Transformer语言模型在演绎任务中的推理机制，区分横向推理（自回归生成中间步骤）和纵向推理（跨层隐式推理），发现思维链监督有助于学习基于规则的推理，并通过机械可解释性揭示其实现方式。

How global observation works in Federated Learning: Integrating vertical training into Horizontal Federated Learning

Federated learning (FL) has recently emerged as a transformative paradigm that jointly train a model with distributed data sets in IoT while avoiding the need for central data collection. Due to the limited observation range, such data sets can only reflect local information, which limits the quality of trained models. In practice, the global information and local observations would require a joint consideration for learning to make a reasonable policy. However, in horizontal FL, the central agency only acts as a model aggregator without utilizing its global observation to further improve the …

从水平分层到垂直整合：一种由AI驱动的软件开发范式比较研究

From Horizontal Layering to Vertical Integration: A Comparative Study of the AI-Driven Software Development Paradigm

本文研究了AI驱动的软件开发范式转变，发现垂直整合可大幅降低资源消耗，并提出人机协作效能作为组织优化的新目标。

垂直符号回归

Vertical Symbolic Regression

提出垂直符号回归（VSR），通过逐步添加变量在缩减假设空间中搜索，以指数级缩小搜索空间，加速复杂符号表达式的学习，并在实验中优于基线方法。

FedEmb：一种使用网络和特征嵌入聚合的垂直与混合联邦学习算法

FedEmb: A Vertical and Hybrid Federated Learning Algorithm using Network And Feature Embedding Aggregation

本文提出通用算法FedEmb，用于解决基于DNN的垂直与混合联邦学习问题，相比现有方法提升了推理准确率与隐私保护并降低通信带宽，实验证明其准确率提升0.3%至4.2%且时间复杂度降低88.9%。