检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Baisong Wang, Xingwang Xu, Haixiao School of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China

Large language models(LLMs) excellent performance across a variety of tasks, but they come with significant computational and storage costs. Quantizing these models is an effective way to alleviate this issue. However, existing methods struggle to strike a balance between model accuracy and hardware efficiency. This is where we introduce AWEQ, a post-training method that requires no additional training overhead. AWEQ excels in both ultra-low-bit quantization and 8-bit weight and activation (W8A8) quantization. There is an observation that weight quantization is less challenging than activation quantization. AWEQ transfers the difficulty of activation quantization to weights using channel equalization, achieving a balance between the quantization difficulties of both, and thereby maximizing performance. We have further refined the equalization method to mitigate quantization bias error, ensuring the robustness of the model. Extensive experiments on popular models such as LLaMA and OPT demonstrate that AWEQ outperforms all existing post-training quantization methods for large models. 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

Reusable Generator Data-Free knowledge Distillation with Hard Loss Simulation for Image Classification

SSRN

引用

SSRN 2024年

作者： Sun, Yafeng Wang, Xingwang Huang, Junhong Chen, Shilin Hou, Minghui College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

In many image classification scenarios where knowledge distillation (KD) is applied, multiple users need to train various student models that conform to the device's computational limitations at different times. However, due to security concerns, existing data-free KD (DFKD) methods discard the trained generator after completing a task, preventing its reuse in training subsequent students and resulting in wasted resources. Furthermore, the unlabeled nature of fake images eliminates the hard loss that plays a crucial role in data-driven KD. This paper introduces the reusable generator DFKD with hard loss simulation (RG-HLS) to address these challenges. RG-HLS employs a generator consisting of two generative networks and a decoder. The decoder and one of the generative networks can be reused in subsequent tasks. The adversarial example attack is also introduced to mimic the behavior of the teacher model in predicting real images, ensuring that DFKD exhibits a hard loss similar to that of data-driven KD. Extensive experiments across CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets validate the proposed method's superior performance. The reusable generator accelerates convergence without compromising security, and integrating the hard loss further boosts accuracy. Code is available at https://***/sunyafeng-jlu/RG-HLS. © 2024, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing

arXiv

引用

arXiv 2024年

作者： Sun, Ziyu Su, Haoyang Sun, Hanqi Wang, En Liu, Wenbin The College of Computer Science and Technology Jilin University Changchun130012 China The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

Mobile Crowd Sensing (MCS) is a promising paradigm that leverages mobile users and their smart portable devices to perform various real-world tasks. However, due to budget constraints and the inaccessibility of certain areas, Sparse MCS has emerged as a more practical alternative, collecting data from a limited number of target subareas and utilizing inference algorithms to complete the full sensing map. While existing approaches typically assume a time-discrete setting with data remaining constant within each sensing cycle, this simplification can introduce significant errors, especially when dealing with long cycles, as real-world sensing data often changes continuously. In this paper, we go from fine-grained completion, i.e., the subdivision of sensing cycles into minimal time units, towards a more accurate, time-continuous completion. We first introduce Deep Matrix Factorization (DMF) as a neural network-enabled framework and enhance it with a Recurrent Neural Network (RNN-DMF) to capture temporal correlations in these finer time slices. To further deal with the continuous data, we propose TIME-DMF, which captures temporal information across unequal intervals, enabling time-continuous completion. Additionally, we present the Query-Generate (Q-G) strategy within TIME-DMF to model the infinite states of continuous data. Extensive experiments across five types of sensing tasks demonstrate the effectiveness of our models and the advantages of time-continuous completion. Copyright © 2024, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Learning Interpretable Network Dynamics via Universal Neural symbolic Regression

arXiv

引用

arXiv 2024年

作者： Hu, Jiao Cui, Jiaxu Yang, Bo College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

Discovering governing equations of complex network dynamics is a fundamental challenge in contemporary science with rich data, which can uncover the mysterious patterns and mechanisms of the formation and evolution of complex phenomena in various fields and assist in decision-making. In this work, we develop a universal computational tool that can automatically, efficiently, and accurately learn the symbolic changing patterns of complex system states by combining the excellent fitting ability from deep learning and the equation inference ability from pre-trained symbolic regression. We conduct intensive experimental verifications on more than ten representative scenarios from physics, biochemistry, ecology, epidemiology, etc. Results demonstrate the outstanding effectiveness and efficiency of our tool by comparing with the state-of-the-art symbolic regression techniques for network dynamics. The application to real-world systems including global epidemic transmission and pedestrian movements has verified its practical applicability. We believe that our tool can serve as a universal solution to dispel the fog of hidden mechanisms of changes in complex phenomena, advance toward interpretability, and inspire more scientific discoveries. Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

AHMSA-Net: Adaptive Hierarchical Multi-Scale Attention Network for Micro-Expression Recognition

arXiv

引用

arXiv 2025年

作者： Zhang, Lijun Zhang, Yifan Tang, Weicheng Sun, Xinzhi Wang, Xiaomeng Li, Zhanshan College of Computer Science and Technology Jilin University Changchun Jilin130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun Jilin130012 China

Micro-expression recognition (MER) presents a significant challenge due to the transient and subtle nature of the motion changes involved. In recent years, deep learning methods based on attention mechanisms have made some breakthroughs in MER. However, these methods still suffer from the limitations of insufficient feature capture and poor dynamic adaptation when coping with the instantaneous subtle movement changes of micro-expressions. Therefore, in this paper, we design an Adaptive Hierarchical Multi-Scale Attention Network (AHMSA-Net) for MER. Specifically, we first utilize the onset and apex frames of the micro-expression sequence to extract threedimensional (3D) optical flow maps, including horizontal optical flow, vertical optical flow, and optical flow strain. Subsequently, the optical flow feature maps are inputted into AHMSA-Net, which consists of two parts: an adaptive hierarchical framework and a multi-scale attention mechanism. Based on the adaptive downsampling hierarchical attention framework, AHMSA-Net captures the subtle changes of micro-expressions from different granularities (fine and coarse) by dynamically adjusting the size of the optical flow feature map at each layer. Based on the multi-scale attention mechanism, AHMSA-Net learns micro-expression action information by fusing features from different scales (channel and spatial). These two modules work together to comprehensively improve the accuracy of MER. Additionally, rigorous experiments demonstrate that the proposed method achieves competitive results on major micro-expression databases, with AHMSA-Net achieving recognition accuracy of up to 78.21% on composite databases (SMIC, SAMM, CASMEII) and 77.08% on the CASME3 database. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Verifying Diagnosability of Discrete Event System with Logical Formula

引用

Chinese Journal of Electronics 2020年第2期29卷 304-311页

作者： GENG Xuena OUYANG Dantong HAN Cheng College of Computer Science and Technology Changchun University of Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering for Ministry of Education Jilin University

Diagnosability is an important property in the field of fault diagnosis. In this paper, a novel approach based on logical formula is proposed to verify diagnosability of Discrete event systems(DESs). CNFFSM is defined to represent a new model for DES. Each transition in DES can be described as a clause. According to CNF-FSM, we construct a CNF-diagnoser. Based on the resolution principle and CNF-diagnoser, an algorithm is presented to test whether the failure events can be detected or not in a finite number of observable *** algorithm can be applied in both off-line diagnosis and on-line diagnosis. Experimental results show that our algorithm can solve the diagnosability problem efficiently.

关键词： Fault diagnosis Diagnosability Discrete event system Finite state machine Conjunctive normal form

来源：评论

学校读者我要写书评

暂无评论

Computing PUR of Zero-Dimensional Ideals of Breadth at Most One

引用

Journal of Systems Science & Complexity 2021年第6期34卷 2396-2409页

作者： PAN Jian SHANG Baoxin LI Zhe ZHANG Shugong School of Mathematics Key Laboratory of Symbolic Computation and Knowledge Engineering(Ministry of Education)Jilin UniversityChangchun 130012China College of Science Northeast Electric Power UniversityJilin 132012China School of Science Changchun University of Science and TechnologyChangchun 130022China

In this paper,for a zero-dimensional polynomial ideal I,the authors prove that k[x_(1),x_(2),…,x_(n)]/I is cyclic if and only if the breadth of I is 0 or ***,the authors present a new algorithm to compute polynomial ... 详细信息

关键词： Cyclic basis Grobner basis polynomial univariate representation separating element

来源：评论

学校读者我要写书评

暂无评论

Nucleus Detection Based on Adversarial Domain Adaptation with Cross-Domain Consistency

Nucleus Detection Based on Adversarial Domain Adaptation wit...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Shuyu Guo Lan Huang Lang Li Tian Bai College of Computer Science and Technology (of Jilin University) Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education (of Jilin University) Changchun China

Automatic cell/nucleus detection is a prerequisite for various quantitative analyses on microscopy image. However, previous deep learning methods require enough annotated microscopy images for better performance, which is a great challenge for microscopy image due to limited annotation and high cost. This paper proposes an end-to-end adversarial learning model with unsupervised domain adaptation for cell/nucleus detection. Different staining microscopy images transformation and cell/nucleus detection are merged into one end-to-end model to achieve mutual restriction of accuracy. Furthermore, a cross-domain consistency loss is introduced, which can refine the results of image transformation and localize cells synchronously. The experiments conclude that proposed method achieves the best F1 scores compared with other methods on cell/nucleus detection of different staining microscopy images. Moreover, ablation study also approves the effectiveness of cross-domain consistency loss.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Local Search for Pseudo Boolean Optimization by Fragile Scoring Function and Deep Optimization 29

Improving Local Search for Pseudo Boolean Optimization by Fr...

引用

29th International Conference on Principles and Practice of Constraint Programming, CP 2023

作者： Zhou, Wenbo Zhao, Yujiao Wang, Yiyuan Cai, Shaowei Wang, Shimao Wang, Xinyu Yin, Minghao School of Information Science and Technology Northeast Normal University Changchun China Key Laboratory of Applied Statistics of MOE Northeast Normal University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE Jilin University Changchun China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783959773003

Pseudo-Boolean optimization (PBO) is usually used to model combinatorial optimization problems, especially for some real-world applications. Despite its significant importance in both theory and applications, there are few works on using local search to solve PBO. This paper develops a novel local search framework for PBO, which has three main ideas. First, we design a two-level selection strategy to evaluate all candidate variables. Second, we propose a novel deep optimization strategy to disturb some search spaces. Third, a sampling flipping method is applied to help the algorithm jump out of local optimum. Experimental results show that the proposed algorithms outperform three state-of-the-art PBO algorithms on most instances. © Wenbo Zhou, Yujiao Zhao, Yiyuan Wang, Shaowei Cai, Shimao Wang, Xinyu Wang, and Minghao Yin.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transport 25

Enhancing Unsupervised Graph Few-shot Learning via Set Funct...

引用

Proceedings of the 31st ACM SIGKDD Conference on knowledge Discovery and Data Mining V.1

作者： Yonghao Liu Fausto Giunchiglia Ximing Li Lan Huang Xiaoyue Feng Renchu Guan Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China Department of Information Engineering and Computer Science University of Trento Trento Italy

ISBN: (纸本)9798400712456

Graph few-shot learning has garnered significant attention for its ability to rapidly adapt to downstream tasks with limited labeled data, sparking considerable interest among researchers. Recent advancements in graph few-shot learning models have exhibited superior performance across diverse applications. Despite their successes, several limitations still exist. First, existing models in the meta-training phase predominantly focus on instance-level features within tasks, neglecting crucial set-level features essential for distinguishing between different categories. Second, these models often utilize query sets directly on classifiers trained with support sets containing only a few labeled examples, overlooking potential distribution shifts between these sets and leading to suboptimal performance. Finally, previous models typically require necessitate abundant labeled data from base classes to extract transferable knowledge, which is typically infeasible in real-world scenarios. To address these issues, we propose a novel model named STAR, which leverages Set funcTions and optimAl tRansport for enhancing unsupervised graph few-shot learning. Specifically, STAR utilizes expressive set functions to obtain set-level features in an unsupervised manner and employs optimal transport principles to align the distributions of support and query sets, thereby mitigating distribution shift effects. Theoretical analysis demonstrates that STAR can capture more task-relevant information and enhance generalization capabilities. Empirically, extensive experiments across multiple datasets validate the effectiveness of STAR. Our code can be found https://***/KEAML-JLU/STAR here.

关键词： few-shot learning

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：