检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Meng, Linjian Ge, Zhenxing Li, Wenbin An, Bo Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Engineering Nanyang Technological University Singapore

No-regret algorithms are popular for learning Nash equilibrium (NE) in two-player zero-sum normal-form games (NFGs) and extensive-form games (EFGs). However, most of them only have average-iterate convergence, which implies they must average strategies. Averaging strategies increases computational and memory overhead. Importantly, it may also cause additional representation errors when function approximation is used. Therefore, many recent works consider the last-iterate convergence no-regret algorithms since they do not require such averaging. Among them, the two most famous algorithms are Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weight Update (OMWU). However, OGDA has high per-iteration complexity. OMWU exhibits a lower per-iteration complexity but poorer empirical performance, and its convergence holds only when NE is unique. Recent works propose a Reward Transformation (RT) framework for MWU, which removes the uniqueness condition and achieves competitive performance with OMWU. Unfortunately, the algorithms built by this framework perform worse than OGDA under the same number of iterations, and their convergence guarantee is based on the continuous-time feedback assumption, which does not hold in most scenarios. To address these issues, we provide a closer analysis of the RT framework, which holds for both continuous and discrete-time feedback. We demonstrate that the essence of the RT framework is to transform the problem of learning NE in the original game into a series of strongly convex-concave optimization problems (SCCPs), and the sequence of the saddle points of these SCCPs converges to NE of the original game. We show that the bottleneck of the algorithms built by the RT framework is the speed of solving SCCPs. To improve the RT framework’s empirical performance, we design a novel transformation method to enable the SCCPs can be solved by Regret Matching+ (RM+), a no-regret algorithm with better empirical performance than M

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Is It Enough to Recommend Tasks to Newcomers? Understanding Mentoring on Good First Issues

arXiv

引用

arXiv 2023年

作者： Tan, Xin Chen, Yiran Wu, Haohua Zhou, Minghui Zhang, Li School of Computer Science and Engineering Beihang University State Key Laboratory of Software Development Environment Beijing China ShenYuan Honors College Beihang University Beijing China School of Computer Science Peking University Key Laboratory of High Confidence Software Technologies Ministry of Education Beijing China

Newcomers are critical for the success and continuity of open source software (OSS) projects. To attract newcomers and facilitate their onboarding, many OSS projects recommend tasks for newcomers, such as good first issues (GFIs). Previous studies have preliminarily investigated the effects of GFIs and techniques to identify suitable GFIs. However, it is still unclear whether just recommending tasks is enough and how significant mentoring is for newcomers. To better understand mentoring in OSS communities, we analyze the resolution process of 48,402 GFIs from 964 repositories through a mix-method approach. We investigate the extent, the mentorship structures, the discussed topics, and the relevance of expert involvement. We find that ∼70% of GFIs have expert participation, with each GFI usually having one expert who makes two comments. Half of GFIs will receive their first expert comment within 8.5 hours after a newcomer comment. Through analysis of the collaboration networks of newcomers and experts, we observe that community mentorship presents four types of structure: centralized mentoring, decentralized mentoring, collaborative mentoring, and distributed mentoring. As for discussed topics, we identify 14 newcomer challenges and 18 expert mentoring content. By fitting the generalized linear models, we find that expert involvement positively correlates with newcomers' successful contributions but negatively correlates with newcomers' retention. Our study manifests the status and significance of mentoring in the OSS projects, which provides rich practical implications for optimizing the mentoring process and helping newcomers contribute smoothly and successfully. © 2023, CC BY.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

A Secure Communication Mechanism of P2P RFID Code Resolution Network

引用

Chinese Journal of Electronics 2023年第4期19卷 621-626页

作者： Xueyang Liu Wen Zhao Kaimu Huang Zhiming Feng Shikun Zhang Lifu Wang National Engineering Research Center for Software Engineering Peking University Beijing China Key Laboratory of High Confidence Software Technologies (Ministry of Education) School of Electronics Engineering and Computer Science Peking University Beijing China School of Electronics Engineering and Computer Science Peking University Beijing China Information Center of China Communist Youth League Beijing Committee Beijing China

Due to the characteristics of P2P network, the correctness of P2P RFID code resolution service is not guaranteed. In this paper, a novel secure communication mechanism for the P2P RFID code resolution network is proposed based on double random numbers. In this mechanism, the nodes involved in the resolution process generate random numbers, and the random numbers are used for node authentication and message authentication. Based on Kademlia, the proposed secure communication mechanism in the P2P RFID code resolution network is implemented. In experiments, the P2P RFID code resolution network with the proposed secure communication mechanism is not only load balancing, extensible, and node failure tolerant, but also highly efficient in code resolution. At last, the future work is presented.

关键词： Privacy Codes Query processing Education Medical services Load management Security

来源：评论

学校读者我要写书评

暂无评论

A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness

arXiv

引用

arXiv 2023年

作者： Peng, Ze Qi, Lei Shi, Yinghuan Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

A recent empirical observation (Li et al., 2022b) of activation sparsity in MLP blocks offers an opportunity to drastically reduce computation costs for free. Although having attributed it to training dynamics, existing theoretical explanations of activation sparsity are restricted to shallow networks, small training steps and special training, despite its emergence in deep models standardly trained for a large number of steps. To fill these gaps, we propose the notion of gradient sparsity as one source of activation sparsity and a theoretical explanation based on it that sees sparsity as a necessary step to adversarial robustness w.r.t. hidden features and parameters, which is approximately the flatness of minima for well-learned models. The theory applies to standardly trained LayerNorm-ed MLPs, and further to Transformers or other architectures trained with weight noises. Eliminating other sources of flatness except for sparsity, we discover the phenomenon that the ratio between the largest and smallest non-zero singular values of weight matrices is small. When discussing the emergence of this spectral concentration, we use random matrix theory (RMT) as a powerful tool to analyze stochastic gradient noises. Experiments for validation are conducted to verify our gradient-sparsity-based explanation. We propose two plug-and-play modules for both training and finetuning for sparsity. Experiments on ImageNet-1K and C4 demonstrate their 50% sparsity improvements, indicating further potential cost reduction in both training and inference. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

ALFLAT: Chinese NER Using ALBERT, Flat-Lattice Transformer, Word Segmentation and Entity Dictionary 2nd

ALFLAT: Chinese NER Using ALBERT, Flat-Lattice Transformer, ...

引用

2nd EAI International Conference on Applied Cryptography in computer and Communications, AC3 2022

作者： Lv, Haifeng Ding, Yong School of Data Science and Software Engineering Wuzhou University Wuzhou China Guangxi Key Laboratory of Cryptography and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China

ISBN: (纸本)9783031170805

Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information. However, one hand, since the lattice structure is dynamic and complex, although some existing lattice-based models are effectively utilize the parallel computation of GPUs, they do not fully utilize word segmentation boundary tags that as features are helpful for NER task. On the other hand, the character-word vector needs to be trained, and the user-defined entity dictionary cannot be effectively used. In this paper, we propose ALFLAT: based on a flat-lattice Transformer to incorporate ALBERT pre-trained model, word segmentation information and user-defined entity dictionary for Chinese NER. ALFLAT converts the lattice structure into a flat structure consisting of spans, integrate word segmentation embedding with the output of flat-lattice Transformer model, then modifies the emission scores according to the user-defined entity dictionary, finally utilize Viterbi decoding of the CRF layer to obtain the correct entity results. Each span corresponds to a character or latent word and its position in the original lattice. With the power of ALBERT pre-trained model, Transformer and position encoding, ALFLAT can fully leverage the lattice, word segmentation and user-defined entity dictionary information. Experiments on MSRA dataset show ALFLAT outperforms other lexicon-based models in performance and efficiency. © 2022, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images 39

Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstr...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Yihui Lv, Chengxin Yang, Hongyu Huang, Di State Key Laboratory of Complex and Critical Software Environment Beijing China School of Computer Science and Engineering Beihang University China School of Artificial Intelligence Beihang University China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (纸本)157735897X

3D reconstruction from unconstrained image collections presents substantial challenges due to varying appearances and transient occlusions. In this paper, we introduce Micro-macro Wavelet-based Gaussian Splatting (MW-GS), a novel approach designed to enhance 3D reconstruction by disentangling scene representations into global, refined, and intrinsic components. The proposed method features two key innovations: Micro-macro Projection, which allows Gaussian points to capture details from feature maps across multiple scales with enhanced diversity;and Wavelet-based Sampling, which leverages frequency domain information to refine feature representations and significantly improve the modeling of scene appearances. Additionally, we incorporate a Hierarchical Residual Fusion Network to seamlessly integrate these features. Extensive experiments demonstrate that MW-GS delivers state-of-the-art rendering performance, surpassing existing methods. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

A Channel Mix Method for Fine-Grained Cross-Modal Retrieval

A Channel Mix Method for Fine-Grained Cross-Modal Retrieval

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Shen, Yang Sun, Xuhao Wei, Xiu-Shen Hu, Hanxu Chen, Zhipeng School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Xidian University State Key Laboratory of Integrated Services Networks Xi'an China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China University of Edinburgh Edinburgh United Kingdom Beijing China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

In this paper, we propose a simple but effective method for dealing with the challenging fine-grained cross-modal retrieval task where it aims to enable flexible retrieval among subor-dinate categories across different modalities. Specifically, in order to enhance information interaction in different modalities for fine-grained objects, a channel mix method is developed and performed upon the channels of deep activations across dif-ferent modalities. After that, a 1 x 1 convolution is employed to aggregate the mixed channels into a unified feature vector. Moreover, equipped with a novel fine-grained cross-modal cen-ter loss, our method can further improve the intra-class separa-bility as well as inter-class compactness for multi-modalities. Experiments are conducted on the fine-grained cross-modal benchmark dataset and show our superiority over competing methods. Meanwhile, ablation studies also demonstrate the effectiveness of our proposals. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Energy-saving Processors Two-phases Frequency Reduction Algorithm on Heterogeneous Embedded Systems

Energy-saving Processors Two-phases Frequency Reduction Algo...

引用

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Weihong Huang Kuan Jiang Jing Huang Li Lisi Yufeng Xiao Zihao Deng School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China

Energy saving has become a key issue for heterogeneous embedded systems. Previous energy-saving methods attempt to minimize the energy consumption of applications in heterogeneous embedded systems subject to deadline constraints by reducing the processor frequency. However, good scheduling strategy can also minimize energy consumption to some extent. This paper proposes a novel energy-saving scheduling algorithm, called the Energy-saving Processors Two-phases Frequency Reduction (EPTFR) Algorithm. In the first stage, within the deadline constraints, the maximum working frequency of each processor is reasonably and synchronously reduced; in the second phase, when running sub-applications on the processor, under the constraints of the earliest start time and latest end time of sub-applications, the actual operating frequency of the processor is reasonably reduced. Finally, the effectiveness of the EPTFR algorithm is verified through numerical experiments, and the results show that the proposed EPTFR algorithm can achieve a significant energy-saving effect.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of enhancer-promoter interaction based on ResNeXt

Prediction of enhancer-promoter interaction based on ResNeXt

引用

2022 International Conference on Advanced Algorithms and Neural Networks, AANN 2022

作者： Gong, KeCun Zhou, MengLin Rui, AiSha The Key Laboratory for Computer Systems of State Ethnic Affairs Commission Southwest Minzu University Sichuan Chengdu610041 China School of Computer Science and Engineering Southwest Minzu University Sichuan Chengdu610041 China School of Software Engineering Chengdu University of Information Technology Sichuan Chengdu610225 China

ISBN: (纸本)9781510655751

Aiming at the low accuracy of traditional algorithms in predicting Enhancer-Promoter Interactions (EPIs) in the human genome, an EPIs prediction network based on ResNeXt and attention mechanism was proposed. In the data processing stage, the gene sequence data of a small number of positive samples in the data set is expanded to be consistent with the number of negative samples;then an EPIRNX model is constructed for feature selection and extraction for a given gene sequence, and long-distance features are mined for use in This cell line prediction;the transfer learning model EPIRNX-Transfer was also trained for cross cell line prediction. Using AUROC and AUPRC as evaluation indicators, EPIRNX can better predict EPIs in this cell line than traditional models, and EPIRNX-Transfer can better predict EPIs across cell lines. © 2022 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Stochastic approximation approaches to group distributionally robust optimization 23

Stochastic approximation approaches to group distributionall...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Lijun Zhang Peng Zhao Zhen-Hua Zhuang Tianbao Yang Zhi-Hua Zhou National Key Laboratory for Novel Software Technology Nanjing University Nanjing China and Peng Cheng Laboratory Shenzhen China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Engineering Texas A & M University College Station

This paper investigates group distributionally robust optimization (GDRO), with the purpose to learn a model that performs well over m different distributions. First, we formulate GDRO as a stochastic convex-concave saddle-point problem, and demonstrate that stochastic mirror descent (SMD), using m samples in each iteration, achieves an O(m(log m)/ε2) sample complexity for finding an ε-optimal solution, which matches the Ω(m/ε2) lower bound up to a logarithmic factor. Then, we make use of techniques from online learning to reduce the number of samples required in each round from m to 1, keeping the same sample complexity. Specifically, we cast GDRO as a two-players game where one player simply performs SMD and the other executes an online algorithm for non-oblivious multi-armed bandits. Next, we consider a more practical scenario where the number of samples that can be drawn from each distribution is different, and propose a novel formulation of weighted GDRO, which allows us to derive distribution-dependent convergence rates. Denote by ni the sample budget for the i-th distribution, and assume n1 ≥ n2 ≥ ··· ≥ nm. In the first approach, we incorporate non-uniform sampling into SMD such that the sample budget is satisfied in expectation, and prove that the excess risk of the i-th distribution decreases at an $O(\sqrt{n_1 \log m}/n_i)$ rate. In the second approach, we use mini-batches to meet the budget exactly and also reduce the variance in stochastic gradients, and then leverage stochastic mirror-prox algorithm, which can exploit small variances, to optimize a carefully designed weighted GDRO problem. Under appropriate conditions, it attains an O((log m) / √ni) convergence rate, which almost matches the optimal O(√1/ni) rate of only learning from the i-th distribution with ni samples.

关键词：

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：