As neural networks are trained to be deeper and larger, the scalability of neural network analyzers is urgently required. The main technical insight of our method is modularly analyzing neural networks by segmenting a network into blocks and conduct the analysis for each block. In particular, we propose the network block summarization technique to capture the behaviors within a network block using a block summary and leverage the summary to speed up the analysis process. We instantiate our method in the context of a CPU-version of the state-of-the-art analyzer DeepPoly and name our system as Bounded-Block Poly (BBPoly). We evaluate BBPoly extensively on various experiment settings. The experimental result indicates that our method yields comparable precision as DeepPoly but runs faster and requires less computational resources. For example, BBPoly can analyze really large neural networks like SkipNet or ResNet which contain up to one million neurons in less than around 1 hour per input image, while DeepPoly needs to spend even 40 hours to analyze one image.
Indiana University Network Science Institute(印第安纳大学网络科学研究所);King Abdulaziz University(阿卜杜勒阿齐兹国王大学);Luddy School of Informatics, Computing and Engineering, Indiana University(印第安纳大学拉迪信息学、计算与工程学院)
Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling
Graduate School of Arts and Sciences, Columbia University, New York, USA(哥伦比亚大学艺术与科学研究生院);Department of Computer Science, University of Warwick, Coventry, UK(沃里克大学计算机科学系)
Modular Delta Merging with Orthogonal Constraints: A Scalable Framework for Continual and Reversible Model Composition
Rensselaer Polytechnic Institute(伦斯勒理工学院);National University of Sciences and Technology (NUST)(国立科技大学);Virginia Tech(弗吉尼亚理工大学);University of New Mexico(新墨西哥大学)
Deep unfolding of MCMC kernels: scalable, modular & explainable GANs for high-dimensional posterior sampling
Maxwell Institute for Mathematical Sciences(麦克斯韦数学科学研究所);School of Mathematical and Computer Sciences, Heriot-Watt University(赫瑞-瓦特大学数学与计算机科学学院);School of Mathematics, University of Edinburgh(爱丁堡大学数学学院)
Modular connectivity in neural networks emerges from Poisson noise-motivated regularisation, and promotes robustness and compositional generalisation
McGovern Institute for Brain Research, Massachusetts Institute of Technology, MA 02139, U.S.A.(麦戈文脑科学研究所,麻省理工学院);K. Lisa Yang Integrative Computational Neuroscience Center in the Yang-Tan Collective(李嘉诚整合计算神经科学中心);Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, MA 02139, U.S.A.(脑科学与认知科学系,麻省理工学院);Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, MA 02139, U.S.A.(电气工程与计算机科学系,麻省理工学院)
Enhancing NLP Robustness and Generalization through LLM-Generated Contrast Sets: A Scalable Framework for Systematic Evaluation and Adversarial Training
College of Natural Sciences, The University of Texas at Austin(德克萨斯大学奥斯汀分校自然科学学院)
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
McGill University(麦吉尔大学);Mila(Mila实验室);Microsoft(微软公司);Université de Montréal(蒙特利尔大学);ServiceNow(ServiceNow公司);Georgia Institute of Technology(佐治亚理工学院)