Feature generation is an open topic of investigation in graph machine learning. In this paper, we study the use of graph homomorphism density features as a scalable alternative to homomorphism numbers which retain similar theoretical properties and ability to take into account inductive bias. For this, we propose a high-performance implementation of a simple sampling algorithm which computes additive approximations of homomorphism densities. In the context of graph machine learning, we demonstrate in experiments that simple linear models trained on sample homomorphism densities can achieve performance comparable to graph neural networks on standard graph classification datasets. Finally, we show in experiments on synthetic data that this algorithm scales to very large graphs when implemented with Bloom filters.
Sampling random graph homomorphisms and applications to network data analysis
University of California Los Angeles(加州大学洛杉矶分校);The Ohio State University(俄亥俄州立大学)
图同态是两个图之间保持邻接关系的映射。我们考虑从一个图到一个大型网络的随机图同态的采样问题。我们提出了两个互补的MCMC算法的采样随机图同态,并建立其混合时间和浓度的时间平均值的界限。基于我们的采样算法,我们提出了一个新的网络数据分析框架,该框架可以避免基于独立和邻域采样的方法中的一些缺点。MCMC轨迹的各种时间平均值为我们提供了各种可计算的观测量,包括众所周知的同态密度和平均聚类系数及其推广。此外,我们表明,这些网络观测值是稳定的,相对于一个适当的重整化网络之间的切割距离。我们提供了各种示例和模拟,通过合成网络展示我们的框架。我们还\commHL{demonstrate the performance of}我们的框架上的任务的网络聚类和子图分类的Facebook100数据集和一组经典小说的词邻接网络。
Department of Statistics University of Chicago(统计学系芝加哥大学);Department of Computing and Mathematical Sciences Department of Electrical Engineering California Institute of Technology(计算与数学科学系电气工程系加州理工学院)
On the Effect of Sampling Diversity in Scaling LLM Inference
The Pennsylvania State University(宾夕法尼亚州立大学);Carnegie Mellon University(卡内基梅隆大学);University of California, Los Angeles(加州大学洛杉矶分校);Rensselaer Polytechnic Institute(罗切斯特理工学院);The Chinese University of Hong Kong(香港中文大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);NEC Laboratories America(NEC美国实验室)
Aspects of scaling and scalability for flow-based sampling of lattice QCD
Massachusetts Institute of Technology(麻省理工学院);New York University(纽约大学);DeepMind(深度思维);Argonne National Laboratory(阿贡国家实验室);University of Wisconsin-Madison(威斯康星大学麦迪逊分校)
Classification on Large Networks: A Quantitative Bound via Motifs and Graphons
Hausdorff Center for Mathematics, University of Bonn(波恩大学豪斯多夫数学中心);Department of Computer Science, University of Bonn(波恩大学计算机科学系);Department of Mathematics, University of Texas at Austin(德克萨斯大学奥斯汀分校数学系)
Scaling-up Split-Merge MCMC with Locality Sensitive Sampling (LSS)
Rice University(莱斯大学)
分裂-合并MCMC(Monte Carlo Markov Chain)是MCMC的一种基本和流行的变体,用于解决MCMC状态由未知数量的组件组成的问题。众所周知,用于分裂-合并MCMC的最新方法不能很好地扩展。快速混合的策略需要智能和信息丰富的建议,以减少拒绝率。然而,所有已知的智能建议都涉及昂贵的操作来建议信息转换。因此,每次迭代的成本对于大规模数据集是令人望而却步的。进一步已知的是,无信息但计算有效的建议,如随机分裂-合并,导致收敛非常慢。混合时间和每次更新成本之间的权衡似乎很难解决。在本文中,我们展示了一个甜蜜点。我们利用加权MinHash的一些独特属性,这是一种流行的LSH,设计了一类新的分裂合并建议,这比随机采样的信息量更大,但同时计算效率更高。总的来说,我们得到了一个优越的收敛和每次更新成本之间的权衡。作为一个直接的结果,我们的建议是大约6倍的速度比最先进的采样方法在两个大型的真实数据集KDDCUP和PubMed与数百万个实体和数千个集群。
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
Department of Data Science & AI, Monash University(墨尔本大学数据科学与人工智能系);Faculty of Medicine Dentistry and Health Sciences, University of Melbourne(墨尔本大学医学牙科与健康科学学院);Department of Computer Science, University College London(伦敦大学学院计算机科学系)
PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling
BMW AG, Digital Campus Munich(宝马集团慕尼黑数字园区);University of Göttingen(哥廷根大学);Basque Center for Applied Mathematics(巴斯克应用数学中心);Campus Institute Data Science(数据科学校园研究所);University of the Basque Country(巴斯克大学);Intelligent Systems Group(智能系统研究组);IKERBASQUE, Basque Foundation for Science(巴斯克科学基金会);Swansea University(斯旺西大学)
Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
School of Computer and Information Engineering, Henan University(河南大学计算机与信息工程学院);Department of Statistics, LMU Munich(慕尼黑大学统计系);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心)
Parallel Test-Time Scaling for Latent Reasoning Models
Hong Kong Polytechnic University(香港理工大学);Shandong Jianzhu University(山东建筑大学);University of Science and Technology of China(中国科学技术大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
Hong Kong Baptist University(香港浸会大学);University of Texas at Austin(德克萨斯大学奥斯汀分校);Shanghai Jiao Tong University(上海交通大学);Shanghai Innovation Institute(上海创新研究院);Ant Group(蚂蚁集团)
Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
MAIS, Institute of Automation, Chinese Academy of Sciences(自动化研究所,中国科学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);University of California, Santa Barbara(加州大学圣巴巴拉分校);Beijing Wenge Technology Co., Ltd(北京文格科技有限公司)
Rensselaer Polytechnic Institute(拉特克利夫理工学院);NEC Laboratories America(NEC美洲实验室);Princeton University(普林斯顿大学);California Institute of Technology(加州理工学院);NEC Corporation(NEC公司)
From Scale to Speed: Adaptive Test-Time Scaling for Image Editing
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);AMAP, Alibaba Group(阿里巴巴集团高德地图);University of Queensland(昆士兰大学)