TopER: Topological Embeddings in Graph Representation Learning
Department of Mathematics(数学系);Florida State University(佛罗里达州立大学);Department of Statistics(统计系);University of Manitoba(曼尼托巴大学);AI Institute(人工智能研究所);University of Central Florida(佛罗里达大学中央分校);Department of Mathematical Sciences(数学科学系);University of Texas at Dallas(德克萨斯大学达拉斯分校)
Astrit Tola, Funmilola Mary Taiwo, Cuneyt Gurcan Akcora, Baris Coskunuzer
Graph embeddings play a critical role in graph representation learning, allowing machine learning models to explore and interpret graph-structured data. However, existing methods often rely on opaque, high-dimensional embeddings, limiting interpretability and practical visualization.
In this work, we introduce Topological Evolution Rate (TopER), a novel, low-dimensional embedding approach grounded in topological data analysis. TopER simplifies a key topological approach, Persistent Homology, by calculating the evolution rate of graph substructures, resulting in intuitive and interpretable visualizations of graph data. This approach not only enhances the exploration of graph datasets but also delivers competitive performance in graph clustering and classification tasks. Our TopER-based models achieve or surpass state-of-the-art results across molecular, biological, and social network datasets in tasks such as classification, clustering, and visualization.
Quantum Topological Graph Neural Networks for Detecting Complex Fraud Patterns
Department of Electrical Engineering(电气工程系);Sharif University of Technology(谢里夫技术大学);Department of Electrical and Electronic Engineering(电气与电子工程系);Shahed University(沙赫德大学)
Persistence Homology of TEDtalk: Do Sentence Embeddings Have a Topological Shape?
Univerisity of Rochester(罗切斯特大学);Northeastern University(东北大学);Comcast Applied Ai Research(康卡斯特应用人工智能研究中心)
\emph{Topological data analysis}(TDA)是最近出现的一种从高维数据中提取有意义的判别特征的新技术。在本文中,我们探讨的可能性,应用TDA,以提高分类准确率的公开演讲评分。我们为TEDtalk数据的句子嵌入计算了\emph{persistence image vectors},并将此向量作为我们的机器学习模型的额外输入。我们已经发现了一个负面的结果,这种拓扑信息并没有显着提高模型的精度。在某些情况下,它会使准确性略差于原始的准确性。从我们的结果来看,我们不能得出结论,句子嵌入的拓扑形状可以帮助我们训练一个更好的模型,为公众演讲评分。
TopoEmbedX: A General Framework for Representation Learning on Topological Domains
RWTH Aachen University(亚琛工业大学);Louisiana State University(路易斯安那州立大学);The University of Manchester(曼彻斯特大学);National Technical University of Athens(雅典国立技术大学);PolyShape;University of San Francisco(旧金山大学)
Uncovering Trajectory and Topological Signatures in Multimodal Pediatric Sleep Embeddings
Department of Radiology(放射科);University of California San Francisco(加州大学旧金山分校);UNC–Chapel Hill(北卡罗来纳大学教堂山分校);UNC School of Data Science and Society(北卡罗来纳大学教堂山分校数据科学与社会学院)
Topological Data Analysis for Anomaly Detection in Host-Based Logs
The Alan Turing Institute(艾伦·图灵研究所);The British Library(大英图书馆)
拓扑数据分析(TDA)使从业人员能够分析网络安全数据的全局结构。我们使用TDA在基于主机的日志中进行异常检测,这些日志是通过开源Logging Made Easy(LME)项目收集的。我们提出了一种方法,直接从Windows日志中建立单纯复合体的过滤,使其内在结构的分析,使用拓扑工具。我们比较持久的同源性和频谱图和超图拉普拉斯算子作为特征向量对标准日志嵌入计数事件的功效,并发现计算机日志的拓扑和频谱嵌入包含用于对异常日志进行分类的判别信息,该信息是标准嵌入的补充。最后,我们讨论了我们的方法被用作异常检测的一个可解释的框架的一部分的潜力。
Dimensionality reduction and width of deep neural networks based on topological degree theory
School of Mathematics and Statistics, Huazhong University of Science and Technology(数学与统计学学院,华中科技大学);Hubei Key Laboratory of Engineering Modeling and Scientific Computing , Huazhong University of Science and Technology(工程建模与科学计算湖北省重点实验室,华中科技大学)
Ferdowsi University of Mashhad(马什哈德费尔多西大学);Center of Excellence in Soft Computing and Intelligent Information Processing, Ferdowsi University of Mashhad(马什哈德费尔多西大学软计算与智能信息处理卓越中心)
From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures
University of Tübingen(图宾根大学);Fribourg University(弗里堡大学);Boehringer Ingelheim GmbH, Biberach (Riss), Germany(勃林格殷格翰公司);The University of Texas at Austin(德克萨斯大学奥斯汀分校)