检索结果-南通市图书馆

Granger causal representation learning for groups of time series

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 56-68页

作者： Ruichu CAI Yunjin WU Xiaokai HUANG Wei CHEN Tom Z.J.FU Zhifeng HAO School of computer Science Guangdong University of Technology Peng Cheng laboratory College of Science Shantou University

Discovering causality from multivariate time series is an important but challenging *** existing methods focus on estimating the Granger causal structures among multivariate time series,while ignoring the prior knowledge of these time series, e.g., the group of the time series. Focusing on discovering the Granger causal structures among groups of time series, we propose a Granger causal representation learning method to solve this problem. First, we use the multiset canonical correlation analysis method to learn the Granger causal representation of each group of time series. Then, we model the Granger causal relationships among the learned Granger causal representations using a recurrent neural network with temporal information. Finally, we formulate the above two stages into one unified optimization problem, which is efficiently solved using the augmented Lagrangian method. We conduct extensive experiments on synthetic and real-world datasets to validate the correctness and effectiveness of the proposed method.

关键词： Granger causal discovery Granger causal representation learning time series data recurrent neural network multiset canonical correlation analysis

When debugging encounters artificial intelligence: state of the art and open challenges

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 42-84页

作者： Yi SONG Xiaoyuan XIE Baowen XU School of computer Science Wuhan University State Key laboratory of Novel Software Technology Nanjing University

Both software debugging and artificial intelligence techniques are hot topics in the current field of software engineering. Debugging techniques, which comprise fault localization and program repair, are an important part of the software development lifecycle for ensuring the quality of software systems. As the scale and complexity of software systems grow, developers intend to improve the effectiveness and efficiency of software debugging via artificial intelligence(artificial intelligence for software debugging, AI4SD). On the other hand, many artificial intelligence models are being integrated into safety-critical areas such as autonomous driving, image recognition, and audio processing, where software debugging is highly necessary and urgent(software debugging for artificial intelligence, SD4AI). An AI-enhanced debugging technique could assist in debugging AI systems more effectively, and a more robust and reliable AI approach could further guarantee and support debugging techniques. Therefore, it is important to take AI4SD and SD4AI into consideration comprehensively. In this paper, we want to show readers the path, the trend, and the potential that these two directions interact with each other. We select and review a total of 165 papers in AI4SD and SD4AI for answering three research questions, and further analyze opportunities and challenges as well as suggest future directions of this cross-cutting area.

关键词： software debugging fault localization program repair artificial intelligence machine learning

Multi-instance partial-label learning: towards exploiting dual inexact supervision

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第3期67卷 48-61页

作者： Wei TANG Weijia ZHANG Min-Ling ZHANG School of computer Science and Engineering Southeast University Key laboratory of computer Network and Information Integration (Southeast university) Ministry of Education School of Information and Physical Sciences The University of Newcastle

Weakly supervised machine learning algorithms are able to learn from ambiguous samples or labels, e.g., multi-instance learning or partial-label learning. However, in some real-world tasks, each training sample is associated with not only multiple instances but also a candidate label set that contains one groundtruth label and some false positive labels. Specifically, at least one instance pertains to the ground-truth label while no instance belongs to the false positive labels. In this paper, we formalize such problems as multi-instance partial-label learning(MIPL). Existing multi-instance learning algorithms and partial-label learning algorithms are suboptimal for solving MIPL problems since the former fails to disambiguate a candidate label set, and the latter cannot handle a multi-instance bag. To address these issues, a tailored algorithm named MIPLGP, i.e., multi-instance partial-label learning with Gaussian processes, is *** first assigns each instance with a candidate label set in an augmented label space, then transforms the candidate label set into a logarithmic space to yield the disambiguated and continuous labels via an exclusive disambiguation strategy, and last induces a model based on the Gaussian processes. Experimental results on various datasets validate that MIPLGP is superior to well-established multi-instance learning and partial-label learning algorithms for solving MIPL problems.

关键词： machine learning multi-instance partial-label learning multi-instance learning partial-label learning Gaussian processes

Towards kernelizing the classifier for hyperbolic data

在线全文

学校读者我要写书评

暂无评论

Frontiers of computer Science 2024年第1期18卷 17-31页

作者： Meimei YANG Qiao LIU Xinkai SUN Na SHI Hui XUE School of computer Science and Engineering Southeast UniversityNanjing 210096China MOE Key laboratory of computer Science and Information Integration(Southeast university) Nanjing 210096China

Data hierarchy,as a hidden property of data structure,exists in a wide range of machine learning applications.A common practice to classify such hierarchical data is first to encode the data in the Euclidean space,and then train a Euclidean ***,such a paradigm leads to a performance drop due to distortion of data embedding in the Euclidean *** relieve this issue,hyperbolic geometry is investigated as an alternative space to encode the hierarchical data for its higher ability to capture the hierarchical *** methods cannot explore the full potential of the hyperbolic geometry,in the sense that such methods define the hyperbolic operations in the tangent plane,causing the distortion of data *** this paper,we develop two novel kernel formulations in the hyperbolic space,with one being positive definite(PD)and another one being indefinite,to solve the classification tasks in hyperbolic *** PD one is defined via mapping the hyperbolic data to the Drury-Arveson(DA)space,which is a special reproducing kernel Hilbert space(RKHS).To further increase the discrimination of the classifier,an indefinite kernel is further defined in the Krein ***,we design a 2-layer nested indefinite kernel which first maps hyperbolic data into the DA spaces,followed by a mapping from the DA spaces to the Krein *** experiments on real-world datasets demonstrate the superiority ofthe proposed kernels.

关键词： data hierarchy hyperbolic cgeometry drury-arveson space krein space

Retrieval-and-alignment based large-scale indoor point cloud semantic segmentation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 164-180页

作者： Zongyi XU Xiaoshui HUANG Bo YUAN Yangfu WANG Qianni ZHANG Weisheng LI Xinbo GAO School of computer Science and Technology Chongqing University of Posts and Telecommunications Shanghai Artificial Intelligence laboratory School of Electronic Engineering and computer Science Queen Mary University of London

Current methods for point cloud semantic segmentation depend on the extraction of descriptive features. However, unlike images, point clouds are irregular and often lack texture information, making it demanding to extract discriminative features. In addition, noise, outliers, and uneven point distribution are commonly present in point clouds, which further complicates the segmentation task. To address these problems, a novel architecture is proposed for direct and accurate large-scale point cloud segmentation based on point cloud retrieval and alignment. The proposed approach involves using a feature-based point cloud retrieval method for searching for reference point clouds with annotations from a dataset. In the following segmentation stage, an overlap-based point cloud registration method has been developed to align the target and reference point clouds. For accurate and robust alignment, an overlap region estimation module is trained to locate the optimal overlap region between two pieces of point clouds in a coarse-to-fine manner. In the detected overlap region, the global and local features of the points are extracted and combined for featuremetric registration to obtain accurate transformation parameters between the target and reference point clouds. After alignment, the annotated segmentation of the reference is transferred to the target point clouds to obtain accurate segmentation results. Extensive experiments are conducted to show that the developed method outperforms the state-of-the-art approaches in terms of both accuracy and robustness against noise and outliers.

关键词： point cloud semantic segmentation large-scale indoor point clouds point cloud alignment overlap estimation label transfer

Building a domain-specific compiler for emerging processors with a reusable approach

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第1期67卷 20-38页

作者： Mingzhen LI Yi LIU Bangduo CHEN Hailong YANG Zhongzhi LUAN Depei QIAN State Key laboratory of Software Development Environment School of computer Science and Engineering Beihang University

High-performance computing and deep learning domains have been motivating the design of domain-specific *** these processors can provide promising computation capability,they are notorious for exotic programming *** improve programming productivity and fully exploit the performance potential of these processors,domain-specific compilers(DSCs) have been ***,building DSCs for emerging processors requires tremendous engineering efforts because the commonly used compilation stack is difficult to be *** to the advent of multilevel intermediate representation(MLIR),DSC developers can leverage reusable infrastructure to extend their customized functionalities without rebuilding the entire compilation *** this paper,we further demonstrate the effectiveness of MLIR by extending its reusable infrastructure to embrace a heterogeneous many-core processor(Sunway processor).In particular,we design a new Sunway dialect and corresponding backend for the Sunway processor,fully exploiting its architectural advantage and hiding its programming *** show the ease of building a DSC,we leverage the Sunway dialect and existing MLIR dialects to build a stencil compiler for the Sunway *** experimental results show that our stencil compiler,built with a reusable approach,can even perform better than state-of-the-art stencil compilers.

关键词： domain-specific compiler emerging processor reusable dialect performance optimization MLIR

Advances and challenges in artificial intelligence text generation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2024年第1期25卷 64-83页

作者： Bing LI Peng YANG Yuankang SUN Zhongjian HU Meng YI School of computer Science and Engineering Southeast UniversityNanjing 210000China Key laboratory of computer Network and Information Integration Ministry of EducationSoutheast UniversityNanjing 210000China

Text generation is an essential research area in artificial intelligence(AI)technology and natural language processing and provides key technical support for the rapid development of AI-generated content(AIGC).It is based on technologies such as natural language processing,machine learning,and deep learning,which enable learning language rules through training models to automatically generate text that meets grammatical and semantic *** this paper,we sort and systematically summarize the main research progress in text generation and review recent text generation papers,focusing on presenting a detailed understanding of the technical *** addition,several typical text generation application systems are ***,we address some challenges and future directions in AI text *** conclude that improving the quality,quantity,interactivity,and adaptability of generated text can help fundamentally advance AI text generation development.

关键词： AI text generation Natural language processing Machine learning Deep learning

维普期刊数据库

Perception field based imitation learning for unlabeled multi-agent pathfinding

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 115-135页

作者： Wenjie CHU Ailun YU Wei ZHANG Haiyan ZHAO Zhi JIN School of computer Science Peking University Key laboratory of High-Confidence Software Technologies (Peking university) Ministry of Education

This paper proposes an imitation learning method to learn a universal agent policy for unlabeled multi-agent pathfinding(unlabeled MAPF) in grid environments. The method transforms the unlabeled MAPF problem into a series of temporal-independent homogeneous classification problems for each *** on this transformation, a neural network is designed to imitate a distance-optimal expert *** neural network consists of two successive modules: perception field learner and field integrating *** former refines and encodes the current system state into a perception field for each agent by combining a set of learnable field-generating functions. The latter takes an agent's perception field as input and decides the agent's next action based on a triplet cross-attention mechanism. We evaluate our method on a diverse set of unlabeled MAPF tasks. Compared with state-of-the-art counterparts, the experimental results manifest the superiority of the proposed method in both generalization ability and scalability.

关键词： unlabeled multi-agent pathfinding perception field triplet cross-attention multi-agent imitation learning learning-based planning

CPT: a pre-trained unbalanced transformer for both Chinese language understanding and generation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 43-55页

作者： Yunfan SHAO Zhichao GENG Yitao LIU Junqi DAI Hang YAN Fei YANG Zhe LI Hujun BAO Xipeng QIU School of computer Science Fudan University Shanghai Key laboratory of Intelligent Information Processing Fudan University Zhejiang Lab

In this paper, we take the advantage of previous pre-trained models(PTMs) and propose a novel Chinese pre-trained unbalanced transformer(CPT). Different from previous Chinese PTMs, CPT is designed to utilize the shared knowledge between natural language understanding(NLU) and natural language generation(NLG) to boost the performance. CPT consists of three parts: a shared encoder, an understanding decoder, and a generation decoder. Two specific decoders with a shared encoder are pretrained with masked language modeling(MLM) and denoising auto-encoding(DAE) tasks, *** the partially shared architecture and multi-task pre-training, CPT can(1) learn specific knowledge of both NLU or NLG tasks with two decoders and(2) be fine-tuned flexibly that fully exploits the potential of the model. Moreover, the unbalanced transformer saves the computational and storage cost, which makes CPT competitive and greatly accelerates the inference of text generation. Experimental results on a wide range of Chinese NLU and NLG tasks show the effectiveness of CPT.

关键词： pre-trained model transformer language model generation unified model