检索结果-内蒙古大学图书馆

Total Variation Denoising for Graph Signals Enhanced with Moreau Envelope

Circuits, systems, and Signal Processing 2025年 1-32页

作者： Jia, Zihao He, Yangfan Zhang, Zhichao School of Communication and Artificial Intelligence School of Integrated Circuits Nanjing Institute of Technology Nanjing 211167 China School of Mathematics and Statistics The Center for Applied Mathematics of Jiangsu Province The Jiangsu International Joint Laboratory on System Modeling and Data Analysis Nanjing University of Information Science and Technology Nanjing 210044 China

Graph signal denoising plays a crucial role in processing complex network data. However, traditional Total variation (TV) denoising methods often suffer from excessive smoothing and high computational cost. In this paper, we propose an Moreau-enhanced TV (MTV) denoising method for graph signals, based on the Moreau envelope. By introducing a non-convex regularization term, this method improves the conventional -norm model, effectively reducing edge information loss caused by over-smoothing and preserving the structural features of graph signals. Compared to the traditional TV approach, the MTV method strikes a better balance between noise suppression and signal feature preservation. It excels in capturing signal jumps and mitigating error accumulation, particularly for periodic cyclic and complex random graph signals. Additionally, the proposed method demonstrates strong robustness to changes in graph density, maintaining stable denoising performance even as edge probabilities increase, thus overcoming the instability commonly observed in traditional methods on complex topologies. Experimental results validate that the MTV method outperforms existing techniques across various graph topologies and signal distributions, especially in high-dimensional and complex signal scenarios, highlighting its theoretical and practical significance in graph signal processing. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Complex networks Graph Laplacian Graph signal denoising Moreau envelope Non-convex regularization Optimization algorithm Signal Recovery Total variation

来源：评论

学校读者我要写书评

暂无评论

Distributed Proximal-Correction Algorithm for The Sum of Maximal Monotone Operators

引用

IEEE Transactions on Automatic Control 2024年第7期70卷 4469-4483页

作者： Gong, Kai Zhang, Liwei The School of Mathematical Sciences Dalian University of Technology Liaoning 116024 China The National Frontiers Science Center for Industrial Intelligence and System Optimization the Key Laboratory of Data Analysis and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang110819 China

This paper focuses on a class of inclusion problems of maximal monotone operators over directed multi-agent networks, where each agent is characterized by a splittable local operator. By integrating the ideas from correction, inexact proximal methods, and push-sum protocol, we proposed a distributed proximal-correction algorithm (referred to as DPCA-ϵik) to solve this inclusion problem of operators, where ϵik is an agent predetermined accuracy for approximately computing proximal mappings. Under mild assumptions on problem setup and agents specified precision ϵik, we proved the convergence and sublinear rate o(1/k) of DPCA-ϵik in terms of the first-order optimality residual. Furthermore, under the metric regularity of local operators of agents, we established its linear convergence rate. Numerical simulations and comparisons with other distributed algorithms illustrate the effectiveness of the proposed algorithm. ©1963-2012 IEEE.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks

arXiv

引用

arXiv 2025年

作者： Cui, Shuang Li, Yi Li, Jiangmeng Tang, Xiongxin Su, Bing Xu, Fanjiang Xiong, Hui National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China China Department of Computer Science & Engineering the Hong Kong University of Science and Technology Hong Kong

Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one. Distribution shifts in defocused images generally lead to performance degradation of existing methods during out-of-distribution inferences. In this work, we gauge the intrinsic reason behind the performance degradation, which is identified as the heterogeneity of lens-specific point spread functions. Empirical evidence supports this finding, motivating us to employ a continual test-time adaptation (CTTA) paradigm for SIDD. However, traditional CTTA methods, which primarily rely on entropy minimization, cannot sufficiently explore task-dependent information for pixel-level regression tasks like SIDD. To address this issue, we propose a novel Siamese networks-based continual test-time adaptation framework, which adapts source models to continuously changing target domains only requiring unlabeled target data in an online manner. To further mitigate semantically erroneous textures introduced by source SIDD models under severe degradation, we revisit the learning paradigm through a structural causal model and propose Causal Siamese networks (CauSiam). Our method leverages large-scale pre-trained vision-language models to derive discriminative universal semantic priors and integrates these priors into Siamese networks, ensuring causal identifiability between blurry inputs and restored images. Extensive experiments demonstrate that CauSiam effectively improves the generalization performance of existing SIDD methods in continuously changing domains. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Sensitivity analysis of Cellular Automata and Heterogeneous Topology Networks: Partially-Local Cellular Automata and Homogeneous Homogeneous Random Boolean Networks

arXiv

引用

arXiv 2024年

作者： Glover, Tom Eivind Jahren, Ruben Martinuzzi, Francesco Lind, Pedro Gonçalves Nichele, Stefano Department of Computer Science OsloMet - Oslo Metropolitan University Oslo Norway Department of Computer Science and Communication Østfold University College Halden Norway Simula Research Laboratory Numerical Analysis and Scientific Computing Oslo0164 Norway Center for Scalable Data Analytics and Artificial Intelligence Leipzig University Leipzig Germany Institute for Earth System Science & Remote Sensing Leipzig University Leipzig Germany Remote Sensing Centre for Earth System Research Leipzig University Leipzig Germany

Elementary Cellular Automata (ECA) are a well-studied computational universe that is, despite its simple configurations, capable of impressive computational variety. Harvesting this computation in a useful way has historically shown itself to be difficult, but if combined with reservoir computing (RC), this becomes much more feasible. Furthermore, RC and ECA enable energy-efficient AI, making the combination a promising concept for Edge AI. In this work, we contrast ECA to substrates of Partially-Local CA (PLCA) and Homogeneous Homogeneous Random Boolean Networks (HHRBN). They are, in comparison, the topological heterogeneous counterparts of ECA. This represents a step from ECA towards more biological-plausible substrates. We analyse these substrates by testing on an RC benchmark (5-bit memory), using Temporal Derrida plots to estimate the sensitivity and assess the defect collapse rate. We find that, counterintuitively, disordered topology does not necessarily mean disordered computation. There are countering computational"forces" of topology imperfections leading to a higher collapse rate (order) and yet, if accounted for, an increased sensitivity to the initial condition. These observations together suggest a shrinking critical range. © 2024, CC BY.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

When to update your model: constrained model-based reinforcement learning 22

When to update your model: constrained model-based reinforce...

引用

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Tianying Ji Yu Luo Fuchun Sun Mingxuan Jing Fengxiang He Wenbing Huang Department of Computer Science and Technology Tsinghua University Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences JD Explore Academy *** Inc Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9781713871088

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supporting Vision-Language Model Inference with Confounder-pruning Knowledge Prompt

arXiv

引用

arXiv 2022年

作者： Li, Jiangmeng Mo, Wenyi Qiang, Wenwen Su, Bing Zheng, Changwen Xiong, Hui Wen, Ji-Rong The University of Chinese Academy of Sciences Beijing China The Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China The Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China Hong Kong

Vision-language models are pre-trained by aligning image-text pairs in a common space to deal with open-set visual concepts. To boost the transferability of the pre-trained models, recent works adopt fixed or learnable prompts, i.e., classification weights are synthesized from natural language describing task-relevant categories, to reduce the gap between tasks in the training and test phases. However, how and what prompts can improve inference performance remains unclear. In this paper, we explicitly clarify the importance of including semantic information in prompts, while existing prompting methods generate prompts without exploring the semantic information of textual labels. Manually constructing prompts with rich semantics requires domain expertise and is extremely time-consuming. To cope with this issue, we propose a semantic-aware prompt learning method, namely CPKP, which retrieves an ontological knowledge graph by treating the textual label as a query to extract task-relevant semantic information. CPKP further introduces a double-tier confounder-pruning procedure to refine the derived semantic information. The graph-tier confounders are gradually identified and phased out, inspired by the principle of Granger causality. The feature-tier confounders are demolished by following the maximum entropy principle in information theory. Empirically, the evaluations demonstrate the effectiveness of CPKP, e.g., with two shots, CPKP outperforms the manual-prompt method by 4.64% and the learnable-prompt method by 1.09% on average, and the superiority of CPKP in domain generalization compared to benchmark approaches. Our implementation is available at https://***/Mowenyii/CPKP. Copyright © 2022, The Authors. All rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

When to Update Your Model: Constrained Model-based Reinforcement Learning

arXiv

引用

arXiv 2022年

作者： Ji, Tianying Luo, Yu Sun, Fuchun Jing, Mingxuan He, Fengxiang Huang, Wenbing Department of Computer Science and Technology Tsinghua University China Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences China JD Explore Academy *** Inc China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO1 (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed. © 2022, CC BY-NC-SA.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language

arXiv

引用

arXiv 2022年

作者： Su, Bing Du, Dazhao Yang, Zhao Zhou, Yujie Li, Jiangmeng Rao, Anyi Sun, Hao Lu, Zhiwu Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

Although artificial intelligence (AI) has made significant progress in understanding molecules in a wide range of fields, existing models generally acquire the single cognitive ability from the single molecular modality. Since the hierarchy of molecular knowledge is profound, even humans learn from different modalities including both intuitive diagrams and professional texts to assist their understanding. Inspired by this, we propose a molecular multimodal foundation model which is pretrained from molecular graphs and their semantically related textual data (crawled from published Scientific Citation Index papers) via contrastive learning. This AI model represents a critical attempt that directly bridges molecular graphs and natural language. Importantly, through capturing the specific and complementary information of the two modalities, our proposed model can better grasp molecular expertise. Experimental results show that our model not only exhibits promising performance in cross-modal tasks such as cross-modal retrieval and molecule caption, but also enhances molecular property prediction and possesses capability to generate meaningful molecular graphs from natural language descriptions. We believe that our model would have a broad impact on AI-empowered fields across disciplines such as biology, chemistry, materials, environment, and medicine, among others. Copyright © 2022, The Authors. All rights reserved.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Complex Knowledge Base Question Answering: A Survey

arXiv

引用

arXiv 2021年

作者： Lan, Yunshi He, Gaole Jiang, Jinhao Jiang, Jing Zhao, Wayne Xin Wen, Ji-Rong School of Data Science and Engineering East China Normal University China School of Computing and Information System Singapore Management University Singapore The School of Information Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China

Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success. However, their performance on complex questions are still far from satisfaction. Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions. In this survey, we review recent advances on KBQA with the focus on solving complex questions, which usually contain multiple subjects, express compound relations, or involve numerical operations. In detail, we begin with introducing the complex KBQA task and relevant background. Then, we present two mainstream categories of methods for complex KBQA, namely semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods. Specifically, we illustrate their procedures with flow designs and discuss their difference and similarity. Next, we summarize the challenges that these two categories of methods encounter when answering complex questions, and explicate advanced solutions as well as techniques used in existing work. After that, we discuss the potential impact of pre-trained language models (PLMs) on complex KBQA. To help readers catch up with SOTA methods, we also provide a comprehensive evaluation and resource about complex KBQA task. Finally, we conclude and discuss several promising directions related to complex KBQA for future research. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Improving multi-hop knowledge base question answering by learning intermediate supervision signals

arXiv

引用

arXiv 2021年

作者： He, Gaole Lan, Yunshi Jiang, Jing Zhao, Wayne Xin Wen, Ji-Rong School of Information Renmin University of China China School of Information System Singapore Management University Singapore Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China

Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only receive the feedback from the final answer, which makes the learning unstable or ineffective. To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network. The major novelty lies in the design of the teacher network, where we utilize both forward and backward reasoning to enhance the learning of intermediate entity distributions. By considering bidirectional reasoning, the teacher network can produce more reliable intermediate supervision signals, which can alleviate the issue of spurious reasoning. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our approach on the KBQA task. The code to reproduce our analysis is available at https://***/RichardHGL/WSDM2021_NSM. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：