The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was proposed as a new KGE model, Rotate3D, by leveraging its non-commutative property. Inspired by CompoundE and Rotate3D, we leverage 3D compound geometric transformations, including translation, rotation, scaling, reflection, and shear and propose a family of KGE models, named CompoundE3D, in this work. CompoundE3D allows multiple design variants to match rich underlying characteristics of a KG. Since each variant has its own advantages on a subset of relations, an ensemble of multiple variants can yield superior performance. The effectiveness and flexibility of CompoundE3D are experimentally verified on four popular link prediction datasets.
Propositionalization and Embeddings: Two Sides of the Same Coin
Jožef Stefan Institute(约瑟夫·斯特凡研究所);University of Nova Gorica(新戈里察大学);International Postgraduate School Jožef Stefan(约瑟夫·斯特凡国际研究生院);University of Ljubljana(卢布尔雅那大学)
InfiniteWalk: Deep Network Embeddings as Laplacian Embeddings with a Nonlinearity
University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)
用于学习词嵌入的skip-gram模型(Mikolov et al. 2013)已经广泛流行,DeepWalk(Perozzi et al. 2014)以及其他方法已经将该模型扩展到从网络中学习节点表示。Qiu et al.(2018)最近的工作为DeepWalk目标提供了一个封闭形式的表达式,避免了对小数据集进行采样的需要,并提高了准确性。在这些方法中,“窗口大小”T是一个关键的超参数,在该窗口大小内,单词或节点被认为是共现的。我们研究的目标在极限T走向无穷大,这使我们能够简化Qiu等人的表达。我们证明,这个限制目标对应于分解一个简单的变换的伪逆图拉普拉斯,链接DeepWalk广泛的频谱图嵌入的工作。此外,我们表明,通过对这个伪逆应用一个简单的非线性逐项变换,我们恢复了有限T目标和嵌入的良好近似,这些目标和嵌入与DeepWalk和多标签分类中的其他skip-gram方法具有竞争力。令人惊讶的是,我们发现,即使是简单的二进制阈值的拉普拉斯伪逆往往是有竞争力的,这表明最近的方法的核心进步是一个非线性的经典谱嵌入方法的顶部。
Hierarchical and Permutation-Invariant Feature Transformation Learning via Policy-Guided Embedding Search
University of Kansas(堪萨斯大学);Southwest University of Finance and Economics(西南财经大学);University of Wisconsin–Madison(威斯康星大学麦迪逊分校);University of Auckland(奥克兰大学);Arizona State University(亚利桑那州立大学);Northeast Normal University(东北师范大学)
Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation
State Key Lab of CAD&CG(CAD与CG国家重点实验室);School of Computing(计算机学院);National University of Singapore(新加坡国立大学);School of Intelligence Science and Engineering(智能科学与工程学院);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))
Department of Applied Tumor Biology, Institute of Pathology, Heidelberg University Hospital(海德堡大学医院病理学研究所应用肿瘤生物学系);National Center for Hereditary Tumor Syndromes, University Hospital Bonn(波恩大学医院遗传性肿瘤综合征国家中心);Department of Internal Medicine I, University Hospital Bonn(波恩大学医院第一内科);Leibniz Institut für Wissensmedien(莱布尼茨知识媒体研究所)
A Pre-trained Reaction Embedding Descriptor Capturing Bond Transformation Patterns
Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China(复旦大学人工智能创新与孵化院);Shanghai Academy of Artificial Intelligence for Science, Shanghai, China(上海人工智能科学研究院);Zhongshan Hospital, Shanghai, China(中山医院)