检索结果-内蒙古大学图书馆

Boosting Short Text Classification with Multi-Source Information Exploration and Dual-Level Contrastive Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Yonghao Li, Mengyu Pang, Wei Giunchiglia, Fausto Huang, Lan Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University China Mathematical and Computer Sciences Heriot-Watt University United Kingdom University of Trento Italy

Short text classification, as a research subtopic in natural language processing, is more challenging due to its semantic sparsity and insufficient labeled samples in practical scenarios. We propose a novel model named MI-DELIGHT for short text classification in this work. Specifically, it first performs multi-source information (i.e., statistical information, linguistic information, and factual information) exploration to alleviate the sparsity issues. Then, the graph learning approach is adopted to learn the representation of short texts, which are presented in graph forms. Moreover, we introduce a dual-level (i.e., instance-level and cluster-level) contrastive learning auxiliary task to effectively capture different-grained contrastive information within massive unlabeled data. Meanwhile, previous models merely perform the main task and auxiliary tasks in parallel, without considering the relationship among tasks. Therefore, we introduce a hierarchical architecture to explicitly model the correlations between tasks. We conduct extensive experiments across various benchmark datasets, demonstrating that MI-DELIGHT significantly surpasses previous competitive models. It even outperforms popular large language models on several datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

Toward Capturing Genetic Epistasis From Multivariate Genome-Wide Association Studies Using Mixed-Precision Kernel Ridge Regression

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ltaief, Hatem Alomairy, Rabab Cao, Qinglei Ren, Jie Slim, Lotfi Kurth, Thorsten Dorschner, Benedikt Bougouffa, Salim Abdelkhalak, Rached Keyes, David E. Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Saudi Arabia Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology United States Department of Computer Science Saint Louis University United States NVIDIA United States

We exploit the widening margin in tensor-core performance between [FP64/FP32/FP16/INT8,FP64/FP32/FP16/FP8/INT8] on NVIDIA [Ampere,Hopper] GPUs to boost the performance of output accuracy-preserving mixed-precision computation of Genome-Wide Association Studies (GWAS) of 305K patients from the UK BioBank, the largest-ever GWAS cohort studied for genetic epistasis using a multivariate approach. Tile-centric adaptive-precision linear algebraic techniques motivated by reducing data motion gain enhanced significance with low-precision GPU arithmetic. At the core of Kernel Ridge Regression (KRR) techniques for GWAS lie compute-bound cubic-complexity matrix operations that inhibit scaling to aspirational dimensions of the population, genotypes, and phenotypes. We accelerate KRR matrix generation by redesigning the computation for Euclidean distances to engage INT8 tensor cores while exploiting symmetry. We accelerate solution of the regularized KRR systems by deploying a new four-precision Cholesky-based solver, which, at 1.805 mixed-precision ExaOp/s on a nearly full Alps system, outperforms the state-of-the-art CPU-only REGENIE GWAS software by five orders of magnitude. Copyright © 2024, The Authors. All rights reserved.

关键词： Tensors

Annotating TSSs in Multiple Cell Types Based on DNA Sequence and RNA-seq Data via DeeReCT-TSS

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2022年第5期20卷 959-973页

作者： Juexiao Zhou Bin Zhang Haoyang Li Longxi Zhou Zhongxiao Li Yongkang Long Wenkai Han Mengran Wang Huanhuan Cui Jingjing Li Wei Chen Xin Gao Computer Science Program ComputerElectrical and Mathematical Sciences and Engineering DivisionKing Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia Computational Bioscience Research Center King Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia Department of Biology School of Life SciencesSouthern University of Science and TechnologyShenzhen 518055China Shenzhen Key Laboratory of Gene Regulation and Systems Biology School of Life SciencesSouthern University of Science and TechnologyShenzhen 518055China Academy for Advanced Interdisciplinary Studies Southern University of Science and TechnologyShenzhen 518055China

The accurate annotation of transcription start sites(TSSs)and their usage are critical for the mechanistic understanding of gene regulation in different biological *** fulfill this,specific high-throughput experimental technologies have been developed to capture TSSs in a genome-wide manner,and various computational tools have also been developed for in silico prediction of TSSs solely based on genomic *** of these computational tools cast the problem as a binary classification task on a balanced dataset,thus resulting in drastic false positive predictions when applied on the genome ***,we present Dee Re CT-TSS,a deep learningbased method that is capable of identifying TSSs across the whole genome based on both DNA sequence and conventional RNA sequencing *** show that by effectively incorporating these two sources of information,Dee Re CT-TSS significantly outperforms other solely sequence-based methods on the precise annotation of TSSs used in different cell ***,we develop a meta-learning-based extension for simultaneous TSS annotations on 10 cell types,which enables the identification of cell type-specific ***,we demonstrate the high precision of DeeReCT-TSS on two independent datasets by correlating our predicted TSSs with experimentally defined TSS chromatin *** source code for Dee Re CT-TSS is available at https://github.-com/Joshua Chou2018/Dee Re CT-TSS_release and https://***/biocode/tools/BT007316.

关键词： Transcription start site Machine learning Deep learning Meta-learning RNA sequencing

An Inexact Variable Metric Proximal Gradient-subgradient Algorithm for a Class of Fractional Optimization Problems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Lei Kong, Xiangrui Zhang, Min Hu, Yaohua School of Computer Science and Engineering Guangdong Province Key Laboratory of Computational Science Sun Yat-sen University China School of Computer Science and Engineering Sun Yat-sen University China School of Mathematics and Information Science Guangzhou University Guangzhou510006 China School of Mathematical Sciences Shenzhen University Shenzhen518060 China

In this paper, we study a class of fractional optimization problems, in which the numerator of the objective is the sum of a convex function and a differentiable function with a Lipschitz continuous gradient, while the denominator is a nonsmooth convex function. This model has broad applicability and encompasses several important optimization problems in the literature. To address these problems, we propose an inexact variable metric proximal gradient-subgradient algorithm (iVPGSA), which, to our knowledge, is the first inexact proximal algorithm specifically designed for solving such type of fractional problems. By incorporating a variable metric proximal term and allowing for inexact solutions to the subproblem under a flexible error criterion, the proposed algorithm is highly adaptable to a broader range of problems while achieving favorable computational efficiency. Under mild assumptions, we establish that any accumulation point of the sequence generated by the iVPGSA is a critical point of the target problem. Moreover, we develop an improved Kurdyka-Lojasiewicz (KL)-based analysis framework to prove the global convergence of the entire sequence and characterize its convergence rate, without requiring a strict sufficient descent property. Our results offer detailed insights into how the KL exponent and inexactness influence the convergence rate. The proposed analysis framework also has the potential to serve as a theoretical tool for studying the convergence rates of a wide range of inexact algorithms beyond the iVPGSA. Finally, some numerical experiments on the 1/2 Lasso problem and the constrained 1/2 sparse optimization problem are conducted to show the superior performance of the iVPGSA in comparison to existing algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

Perovskite Nanocrystal Based Plastic Optical Fiber Amplifier via Two-Photon Excitation

学校读者我要写书评

暂无评论

Perovskite Nanocrystal Based Plastic Optical Fiber Amplifier...

IEEE Photonics Conference (IPC)

作者： Yue Wang Chun Hong Kang Partha Maity Tien Khee Ng Omar F. Mohammed Boon S. Ooi Photonics Laboratory Electrical and Computer Engineering Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia Advanced Membranes and Porous Materials Center Division of Physical Science and Engineering King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

A plastic optical fiber amplifier coated with CsPbBr3 nanocrystals and pumped by an 800-nm Ti:Sapphire laser exhibited two-photon-excited amplified spontaneous emission with a 7.4-mJ/cm 2 threshold and >10-dB opti... 详细信息

ISBN: (数字)9798350361957

ISBN: (纸本)9798350361964

关键词： Optical fiber amplifiers Plastic optical fiber Nanocrystals Stimulated emission Optical pumping Ultrafast optics Optical amplifiers Gain Pump lasers Fiber lasers

An implementation, evaluation and validation of a dynamic fire and conflagration risk indicator for wooden homes

学校读者我要写书评

暂无评论

Procedia computer science 2024年 238卷 49-56页

作者： R.D. Strand L.M. Kristensen Department of Safety Chemistry and Biomedical laboratory sciences Western Norway University of Applied Sciences Haugesund Norway Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway

The pervasive presence of IoT sensing devices combined with advances in cloud-based services has made historical- and forecast weather data services widely available for use in smart software systems. The contribution of this paper is the design, performance evaluation, and validation of a software implementation of model-based dynamic fire risk prediction for wooden homes using local weather data. A key feature of the implementation is that the software architecture has been designed to support the use of different underlying cloud-based weather data services, and the integration as a service in third-party smart systems embedding fire risk predictions. The performed evaluation shows that the implementation is efficient, as weather data can be retrieved, preprocessed and fire risk predictions computed within seconds using only in the order of Kb’s of memory; and accurate considering our sets of data, as the fire risks computed by the implementation have been validated against a set of in-situ measurements.

SkyRover: A Modular Simulator for Cross-Domain Pathfinding

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ma, Wenhui Li, Wenhao Jin, Bo Lu, Changhong Wang, Xiangfeng School of Computer Science and Technology East China Normal University China School of Computer Science and Technology Tongji University China School of Mathematical Sciences East China Normal University China Key Laboratory of Mathematics and Engineering Applications MoE China

Unmanned Aerial Vehicles (UAVs) and Automated Guided Vehicles (AGVs) increasingly collaborate in logistics, surveillance, inspection tasks and etc. However, existing simulators often focus on a single domain, limiting cross-domain study. This paper presents the SkyRover, a modular simulator for UAV-AGV multi-agent pathfinding (MAPF). SkyRover supports realistic agent dynamics, configurable 3D environments, and convenient APIs for external solvers and learning methods. By unifying ground and aerial operations, it facilitates cross-domain algorithm design, testing, and benchmarking. Experiments highlight SkyRover’s capacity for efficient pathfinding and high-fidelity simulations in UAV-AGV coordination. Project is available at https://***/view/mapf3d/home. © 2025, CC BY.

关键词： Unmanned aerial vehicles (UAV)

Distributed Deep Learning System for Efficient Face Recognition in Surveillance System 3

学校读者我要写书评

暂无评论

Distributed Deep Learning System for Efficient Face Recognit...

3rd International Conference on Advanced Information science and System, AISS 2021

作者： Liu, Jinjin Chen, Zhifeng Li, Xiaonan Wei, Tongxin School of Computer Science Zhongyuan University of Technology China and State Key Laboratory of Mathematical Engineering and Advanced Computing China State Key Laboratory of Mathematical Engineering and Advanced Computing China School of Computer Science Zhongyuan University of Technology China School of Cyberspace Security Zhengzhou University China

ISBN: (纸本)9781450385862

In view of the bandwidth consumption caused by data stream transmission in video analysis system and the demand for accurate online real-time analysis of massive data, this paper proposes a deep learning model framework for face recognition employed in the embedded system. Through data collaboration, the cloud could build a more complex data set with a small amount of uploaded data gathered by the end devices. And the framework collaboration makes sure that the fully-trained cloud model directly download or distillate knowledge to the end devices. Experiments show that the deep model not only realizes the real-time response and the accurate response of the cloud system, but also greatly reduces the bandwidth consumption caused by sample data transmission in the model training process. © 2021 ACM.

关键词： Distillation

Uniform Coherence in Amalgamated Algebra Along an Ideal

学校读者我要写书评

暂无评论

Uniform Coherence in Amalgamated Algebra Along an Ideal

International Conference on Algebra and its Applications, ICAA 2023

作者： Ismaili, Karima Alaoui Kim, Hwankoo Mahdou, Najib Department of Mathematics Faculty of Sciences of Rabat Mohammed V University in Rabat B.P. 1014 Rabat Morocco Division of Computer Engineering Hoseo University Dongnam-gu Korea Republic of Modelling and Mathematical Structures Laboratory Department of Mathematics Faculty of Science and Technology of Fez University S.M. Ben Abdellah Fez Fez city2202 Morocco

ISBN: (纸本)9789819767977

The concept of uniform coherence was first introduced by Soublin and has since been extensively explored by numerous researchers. A ring A is defined as uniformly coherent if there exists a function : N → N, where N represents the set of natural numbers, such that for every n ∈ N and each nonzero homomorphism f: An → A, the kernel ker( f ) can be generated by (n) elements. In this paper, we investigate how the property of uniform coherence is transferred to commuta-tive ring extensions. We establish necessary and sufficient conditions for rings such as A ⋈f J, A ⋈ I, and A ∝ E to possess uniform coherence, covering various classes of ideals and A-modules. Our study contributes to the development of new classes of rings that meet this criterion, and we also introduce new families of rings that demonstrate the distinctiveness of the categories of Noetherian and uniformly coherent rings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Amalgamated algebra Coherent Noetherian Trivial ring extension Uniformly coherent