检索结果-内蒙古大学图书馆

17th International Conference on Computer science and Education, ICCSE 2022

作者： Li, Han Zeng, Feng Yang, Fan Department of Automation Xiamen University Xiamen China National Institute for Data Science in Health and Medicine Xiamen University Xiamen China Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision Xiamen China

ISBN: (纸本)9789819924424

With ScRNAseq, we are able to obtain genome-wide transcriptome data from single cells. However, it is very difficult to identify all cell subpopulations in single cell expression data, especially when these subpopulations are unbalanced and the number of subpopulations is unknown. In this paper, we propose a new clustering algorithm, IGFClust. We design an ensemble method to identify unbalanced subpopulations using Gini index and Fano factor. In addition, we design an iterative clustering framework to avoid the problem that only some subpopulations can be identified during the clustering process. We generated four sets of labeled simulation data and compared IGFClust with existing methods. Afterwards, we analyzed 576 glioblastoma primary tumor cells. We show that IGFClust performs accurately and robustly in identifying complex and unbalanced single-cell expression data. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models

arXiv

引用

arXiv 2024年

作者： Wang, Peng Li, Zexi Zhang, Ningyu Xu, Ziwen Yao, Yunzhi Jiang, Yong Xie, Pengjun Huang, Fei Chen, Huajun Zhejiang University China Alibaba Group China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Large language models (LLMs) need knowledge updates to meet the ever-growing world facts and correct the hallucinated responses, facilitating the methods of lifelong model editing. Where the updated knowledge resides in memories is a fundamental question for model editing. In this paper, we find that editing either long-term memory (direct model parameters) or working memory (nonparametric knowledge of neural network activations/representations by retrieval) will result in an impossible triangle—reliability, generalization, and locality can not be realized together in the lifelong editing settings. For long-term memory, directly editing the parameters will cause conflicts with irrelevant pretrained knowledge or previous edits (poor reliability and locality). For working memory, retrieval-based activations can hardly make the model understand the edits and generalize (poor generalization). Therefore, we propose WISE to bridge the gap between memories. In WISE, we design a dual parametric memory scheme, which consists of the main memory for the pretrained knowledge and a side memory for the edited knowledge. We only edit the knowledge in the side memory and train a router to decide which memory to go through when given a query. For continual editing, we devise a knowledge-sharding mechanism where different sets of edits reside in distinct subspaces of parameters and are subsequently merged into a shared memory without conflicts. Extensive experiments show that WISE can outperform previous model editing methods and overcome the impossible triangle under lifelong model editing of question answering, hallucination, and out-of-distribution settings across trending LLM architectures, e.g., GPT, LLaMA, and Mistral. Copyright © 2024, The Authors. All rights reserved.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework 38

Towards Next-Generation Logic Synthesis: A Scalable Neural C...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Zhihai Wang, Jie Yang, Qingyue Bai, Yinqi Li, Xing Chen, Lei Hao, Jianye Yuan, Mingxuan Li, Bin Zhang, Yongdong Wu, Feng MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China Noah's Ark Lab Huawei Technologies Canada College of Intelligence and Computing Tianjin University China

Logic Synthesis (LS) aims to generate an optimized logic circuit satisfying a given functionality, which generally consists of circuit translation and optimization. It is a challenging and fundamental combinatorial optimization problem in integrated circuit design. Traditional LS approaches rely on manually designed heuristics to tackle the LS task, while machine learning recently offers a promising approach towards next-generation logic synthesis by neural circuit generation and optimization. In this paper, we first revisit the application of differentiable neural architecture search (DNAS) methods to circuit generation and found from extensive experiments that existing DNAS methods struggle to exactly generate circuits, scale poorly to large circuits, and exhibit high sensitivity to hyper-parameters. Then we provide three major insights for these challenges from extensive empirical analysis: 1) DNAS tends to overfit to too many skip-connections, consequently wasting a significant portion of the network's expressive capabilities;2) DNAS suffers from the structure bias between the network architecture and the circuit inherent structure, leading to inefficient search;3) the learning difficulty of different input-output examples varies significantly, leading to severely imbalanced learning. To address these challenges in a systematic way, we propose a novel regularized triangle-shaped circuit network generation framework, which leverages our key insights for completely accurate and scalable circuit generation. Furthermore, we propose an evolutionary algorithm assisted by reinforcement learning agent restarting technique for efficient and effective neural circuit optimization. Extensive experiments on four different circuit benchmarks demonstrate that our method can precisely generate circuits with up to 1200 nodes. Moreover, our synthesized circuits significantly outperform the state-of-the-art results from several competitive winners in IWLS 2022 and 2023 competition

关键词：

来源：评论

学校读者我要写书评

暂无评论

LESaET: Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER

LESaET: Low-Dimensional Embedding Method for Link Prediction...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Ding, Lichao Zhao, Jing Lu, Kai Hao, Zenghao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Knowledge graphs (KGs) provide a structured representation of the real world through entity-relation triples. However, current KGs are often incomplete, typically containing only a small fraction of all possible facts. This involves inferring missing content from existing information, a task known as link prediction. Existing methods in the field of link prediction struggle with controlling the dimensionality of embedding vectors or suffer from overly complex models. In order to tackle these challenges, we introduce a method in this paper, named Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER (LESaET). LESaET leverages both self-attention mechanisms and tensor factorization to learn expressive contextual-enhanced representations of KGs. Specifically, LESaET employs the multi-head self-attention mechanism of Transformer as an encoder to capture the mutual information between entities and relationships, and utilizes Enhanced-TuckER as a decoder, ultimately achieving expressive low-dimensional embeddings for link prediction tasks. LESaET demonstrates competitive performance compared to advanced methods on standard datasets. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret 41

Provably Efficient Exploration in Quantum Reinforcement Lear...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhong, Han Hu, Jiachen Xue, Yecheng Li, Tongyang Wang, Liwei Center for Data Science Peking University China School of Computer Science Peking University China Center on Frontiers of Computing Studies Peking University China National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China

While quantum reinforcement learning (RL) has attracted a surge of attention recently, its theoretical understanding is *** particular, it remains elusive how to design provably efficient quantum RL algorithms that can address the exploration-exploitation *** this end, we propose a novel UCRL-style algorithm that takes advantage of quantum computing for tabular Markov decision processes (MDPs) with S states, A actions, and horizon H, and establish an O(poly(S, A, H, log T)) worst-case regret for it, where T is the number of ***, we extend our results to quantum RL with linear function approximation, which is capable of handling problems with large state ***, we develop a quantum algorithm based on value target regression (VTR) for linear mixture MDPs with d-dimensional linear representation and prove that it enjoys O(poly(d, H, log T)) *** algorithms are variants of UCRL/UCRL-VTR algorithms in classical RL, which also leverage a novel combination of lazy updating mechanisms and quantum estimation *** is the key to breaking the Ω(√T)-regret barrier in classical *** the best of our knowledge, this is the first work studying the online exploration in quantum RL with provable logarithmic worst-case regret. Copyright 2024 by the author(s)

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Clustering Combination Method Using Intuitionistic Fuzzy Similarity in Software Module Clustering

Hierarchical Clustering Combination Method Using Intuitionis...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Hong Xia Bo Wang Yongkang Zhang Yanping Chen School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi 'an Key Laboratory of Big Data and Intelligent Computing Xi'an Shaanxi China

In order to solve the problem that the similarity method used in software module clustering can produce arbitrary decision, and the description matrix of dendrogram generated by base clustering in hierarchical clustering combination does not consider more characteristics of entities, a hierarchical clustering combination method based on intuitionistic fuzzy similarity (HCC-IFS) was proposed. In the process of entity similarity calculation, the intuitionistic fuzzy set theory and similarity calculation method are used to provide membership and non-membership attributes for each entity, so as to improve the merging efficiency and solve arbitrary decision problems. In the description matrix representation of base clustering, the absolute and relative features obtained from the dendrogram are used to construct the description matrix, and the generated description matrix is combined. Finally, the proposed algorithm is verified by experiments. Experimental results show that HCC-IFS can produce better clustering results and improve the recovery quality of software architecture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Search for Radio Pulsars in Supernova Remnants Using FAST with One Pulsar Discovered

引用

Chinese Physics Letters 2024年第2期41卷 133-136页

作者：张振闫文明袁建平王娜白俊涛温志刚李保达解进涛赵德王榆斌翟楠楠 Xinjiang Astronomical Observatory Chinese Academy of SciencesUrumqi 830011China University of Chinese Academy of Sciences Beijing 100049China Key Laboratory of Radio Astronomy and Technology(Chinese Academy of Sciences) Beijing 100101China Xinjiang Key Laboratory of Radio Astrophysics Urumqi 830011China College of Physics GuiZhou UniversityGuizhou 550025China Research Center for Intelligent Computing Platforms Zhejiang LaboratoryHangzhou 311100China School of Physical Science and Technology Xinjiang UniversityUrumqi 830046China School of Physics and Electronic Engineering Sichuan University of Science&EngineeringZigong 643000China

We report the results of a search for radio pulsars in five supernova remnants(SNRs)with the FAST *** observations were made using the 19-beam receiver in“snapshot”*** integration time for each pointing was 10 *** discovered a new pulsar,PSR J1845–0306,which has a spin period of 983.6 ms and a dispersion measure of 444.6±2.0 cm^(−3)·pc,in observations of SNR G29.6+*** judge the association between the pulsar and the SNR,further verification is *** also re-detected some known pulsars in the data from SNRs G29.6+0.1 and G29.7–*** pulsars were detected in the observations of the other three SNRs.

关键词： observations Pulsar pulsar

来源：评论

学校读者我要写书评

暂无评论

BENCHMARKING AGENTIC WORKFLOW GENERATION

arXiv

引用

arXiv 2024年

作者： Qiao, Shuofei Fang, Runnan Qiu, Zhisong Wang, Xiaobin Zhang, Ningyu Jiang, Yong Xie, Pengjun Huang, Fei Chen, Huajun Zhejiang University China Alibaba Group China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Large Language Models (LLMs), with their exceptional ability to handle a wide range of tasks, have driven significant advancements in tackling reasoning and planning tasks, wherein decomposing complex problems into executable workflows is a crucial step in this process. Existing workflow evaluation frameworks either focus solely on holistic performance or suffer from limitations such as restricted scenario coverage, simplistic workflow structures, and lax evaluation standards. To this end, we introduce WORFBENCH, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures. Additionally, we present WORFEVAL, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms to accurately quantify the LLM agent’s workflow generation capabilities. Through comprehensive evaluations across different types of LLMs, we discover distinct gaps between the sequence planning capabilities and graph planning capabilities of LLM agents, with even GPT-4 exhibiting a gap of around 15%. We also train two open-source models and evaluate their generalization abilities on held-out tasks. Furthermore, we observe that the generated workflows can enhance downstream tasks, enabling them to achieve superior performance with less time during inference1 Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Object Detection Algorithm Based on Second-Order Pooling Network and Gaussian Mixture Attention 5

Object Detection Algorithm Based on Second-Order Pooling Net...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Ma, Sugang Li, Ningbo Yang, Xiaobao School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Shaanxi Xi'an China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an University of Posts and Telecommunications Shaanxi Xi'an China

ISBN: (纸本)9781450396899

To improve the feature representation ability of the YOLOX algorithm and obtain better detection performance, an object detection algorithm based on second-order pooling network and gaussian mixture attention is proposed. Firstly, the second-order pooling network is added after the PAFPN, and the higher-order statistical information is obtained by calculating the covariance matrix between different channels, to enhance the non-linear modeling capability. Secondly, the mixture attention based on the gaussian function is added after the SPP to model global contexts in the spatial and channel dimensions respectively, which improves the network performance with almost no extra parameters. The experimental results show that the detection accuracy of the proposed algorithm on the PASCAL VOC dataset reaches 82.6 %, which is 1.6 % higher than the YOLOX algorithm. © 2022 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Augmentation-Aware Self-Supervision for data-Efficient GAN Training 37

Augmentation-Aware Self-Supervision for Data-Efficient GAN T...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Hou, Liang Cao, Qi Yuan, Yige Zhao, Songtao Ma, Chongyang Pan, Siyuan Wan, Pengfei Wang, Zhongyuan Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Kuaishou Technology China

ISBN: (纸本)9781713899921

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic - harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Generative adversarial networks

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：