检索结果-内蒙古大学图书馆

Large-scale Nonparallel Support Vector Ordinal Regression Solver

学校读者我要写书评

暂无评论

Procedia computer science 2017年 108卷 1261-1270页

作者： Huadong Wang Jianyu Miao Seyed Mojtaba Hosseini Bamakan Lingfeng Niu Yong Shi Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68118 USA

Large-scale linear classification is widely used in many areas. Although SVM-based models for ordinal regression problem are proven to be powerful techniques, the performance with nonlinear kernels are often suffering from time consuming. Recently, linear SVC not only is shown to obtain competitive performance in most of the cases, but also it is considerably fast during the process of training and testing. However, few studies focused on linear SVM-based ordinal regression models. In this paper, we propose a new approach, called linear Nonparallel Support Vector Ordinal Regression (NPSVOR), which can deal with large-scale problems. An efficient algorithm based on Alternating Direction Method of Multipliers (ADMM) is designed to solve the proposed model. Our experiments are performed on large document data sets to demonstrate the effectiveness of the proposed method.

关键词： Ordinal Regression Support Vector Machine ADMM

General Two-Stage Network Systems Based on Stackelberg Game

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhang, Linyan Zhang, Jian Guo, Chuanyin School of Economics and Management Beijing Information Science & Technology University Beijing100192 China Research Center for Knowledge Management Beijing100192 China Beijing Key Lab of Green Development Decision Based on Big Data Beijing100192 China

Noncooperative approach is a key technique for modeling network systems. In general, there are two types of noncooperative network models in the literature. One is the bilevel model based on Stackelberg game, which is often transformed into a parametric linear program. The other is the leader-follower model, which uses only Stackelberg game concept, which may yield an infeasible solution. The current study shows that the bilevel model can be solved by using two linear models, without having to resort to solving heuristic parametric linear models. Furthermore, the global optimal solution is guaranteed for the nonlinear bilevel model. We prove the equivalence between the bilevel technique and our two linear-model approach. We further improve the existing leader-follower models, and as well the newly developed approaches are extended to general two-stage structures. The newly developed approaches are illustrated with a numerical data set and a real-world case. © 2023, The Authors. All rights reserved.

关键词： Linear programming

GPTR: Gestalt-Perception Transformer for Diagram Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Xin Zhang, Lingling Liu, Jun Fan, Jinfu You, Yang Wu, Yaqiang Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University China Department of Control Science and Engineering Tongji University Shanghai China Department of Computer Science National University of Singapore Singapore Lenovo Research Beijing China

Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its visual features are sparser than those of natural images. In addition, diagrams usually express diverse knowledge, in which there are many low-frequency object categories in diagrams. These lead to the fact that traditional data-driven detection model is not suitable for diagrams. In this work, we propose a gestalt-perception transformer model for diagram object detection, which is based on an encoder-decoder architecture. Gestalt perception contains a series of laws to explain human perception, that the human visual system tends to perceive patches in an image that are similar, close or connected without abrupt directional changes as a perceptual whole object. Inspired by these thoughts, we build a gestalt-perception graph in transformer encoder, which is composed of diagram patches as nodes and the relationships between patches as edges. This graph aims to group these patches into objects via laws of similarity, proximity, and smoothness implied in these edges, so that the meaningful objects can be effectively detected. The experimental results demonstrate that the proposed GPTR achieves the best results in the diagram object detection task. Our model also obtains comparable results over the competitors in natural image object detection. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

LadRa-Net: Locally-aware dynamic re-read attention net for sentence semantic matching

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Kun Lv, Guangyi Wu, Le Chen, Enhong Liu, Qi Wang, Meng Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology Anhui Hefei230029 China AI Lab at Lenovo Research Beijing100094 China University of Science and Technology of China Hefei230026 China

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks, such as Natural Language Inference (NLI), Paraphrase Identification (PI), and so on. Much recent progress has been made in this area, especially attention-based methods and pre-trained language model based methods. However, most of these methods focus on all the important parts in sentences in a static way and only emphasize how important the words are to the query, inhibiting the ability of attention mechanism. In order to overcome this problem and boost the performance of attention mechanism, we propose a novel dynamic re-read attention, which can pay close attention to one small region of sentences at each step and re-read the important parts for better sentence representations. Based on this attention variation, we develop a novel Dynamic Re-read Network (DRr-Net) for sentence semantic matching. Moreover, selecting one small region in dynamic re-read attention seems insufficient for sentence semantics, and employing pre-trained language models as input encoders will introduce incomplete and fragile representation problems. To this end, we extend DRr-Net to Locally-Aware Dynamic Re-read Attention Net (LadRa-Net), in which local structure of sentences is employed to alleviate the shortcoming of Byte-Pair Encoding (BPE) in pre-trained language models and boost the performance of dynamic reread attention. Extensive experiments on two popular sentence semantic matching tasks demonstrate that DRr-Net can significantly improve the performance of sentence semantic matching. Meanwhile, LadRa-Net is able to achieve better performance by considering the local structures of sentences. In addition, it is exceedingly interesting that some discoveries in our experiments are consistent with some findings of psychological research. © 2021, CC BY.

关键词： Computational linguistics

A Brief Survey of Distribution Robust Graph Neural Networks

学校读者我要写书评

暂无评论

Procedia computer science 2024年 242卷 1281-1286页

作者： Lei Zheng Pei Quan Yong Shi Lingfeng Niu The School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China The College of Economics and Management Beijing University of Technology Beijing 100124 China The School of Economics and Management University of Chinese Academy of Sciences Beijing 1001090 China

Graph neural network is a powerful tool for solving various graph tasks, such as node classification and graph classification. However, there is increasing evidence suggesting that it is sensitive to distribution shifts and its performance is reduced by at least 10% when distribution shifts happen. In the last three years, to solve the wide existing distribution shifts, some distribution robust strategies have been designed specifically for graph neural networks. It is also one of the popular research topics in graph neural networks in recent years. Therefore, in this paper, we divide these strategies into three categories depending on the specific problems they solve: distribution shift for semi-supervised node classification, distribution shift for unsupervised node classification, and out-of-distribution shift for graph classification. Furthermore, we discuss and summarize the strategies for each type of problem. After investigating these strategies, we put forward future development direction.

关键词： Graph neural networks Shift robust Distribution generalization

Towards Unified Token Learning for Vision-Language Tracking

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

Review of bankruptcy prediction using machine learning and deep learning techniques

学校读者我要写书评

暂无评论

Procedia computer science 2019年 162卷 895-899页

作者： Yi Qu Pei Quan Minglong Lei Yong Shi School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Faculty of Information Technology Beijing University of Technology Beijing 100124 China College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA

Bankruptcy prediction has long been a significant issue in finance and management science, which attracts the attention of researchers and practitioners. With the great development of modern information technology, it has evolved into using machine learning or deep learning algorithms to do the prediction, from the initial analysis of financial statements. In this paper, we will review the machine learning or deep learning models used in bankruptcy prediction, including the classical machine learning models such as Multivariant Discriminant Analysis (MDA), Logistic Regression (LR), Ensemble method, Neural Networks (NN) and Support Vector Machines (SVM), and major deep learning methods such as Deep Belief Network (DBN) and Convolutional Neural Network (CNN). In each model, the specific process of experiment and characteristics will be summarized through analyzing some typical articles. Finally, possible innovative changes of bankruptcy prediction and its future trends will be discussed.

关键词： Bankruptcy prediction Machine learning Deep learning

Concatenated Attention Neural Network for Image Restoration

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tian, YingJie Wang, YiQi Yang, LinRui Qi, ZhiQuan School of Economics and Management University of Chinese Academy of Sciences Beijing China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China School of Computer Science Technology University of Chinese Academy of Sciences Beijing China Sino-Danish College University of Chinese Academy of Sciences China

In this paper, we present a general framework for low-levelvision tasks including image compression artifacts reduction and image denoising. Under this framework, a novel concatenated attention neural network (CANet) is specifically designed for image restoration. The main contributions of this paper are as follows: First, by applying concise but effective concatenation and feature selection mechanism, we establish a novel connection mechanism which connect different modules in the modules stacking network. Second, both pixel-wise and channel-wise attention mechanisms are used in each module convolution layer, which promotes further extraction of more essential information in images. Lastly, we demonstrate that CANet achieves better results than previous state-of-the-art approaches with sufficient experiments in compression artifacts removing and image denoising. Copyright © 2020, The Authors. All rights reserved.

关键词： Feature extraction

Learning graphon autoencoders for generative graph modeling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Hongteng Zhao, Peilin Huang, Junzhou Luo, Dixin Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China Tencent AI Lab United States School of Computer Science and Technology Beijing Institue of Technology China

Graphon is a nonparametric model that generates graphs with arbitrary sizes and can be induced from graphs easily. Based on this model, we propose a novel algorithmic framework called graphon autoencoder to build an interpretable and scalable graph generative model. This framework treats observed graphs as induced graphons in functional space and derives their latent representations by an encoder that aggregates Chebshev graphon filters. A linear graphon factorization model works as a decoder, leveraging the latent representations to reconstruct the induced graphons (and the corresponding observed graphs). We develop an efficient learning algorithm to learn the encoder and the decoder, minimizing the Wasserstein distance between the model and data distributions. This algorithm takes the KL divergence of the graph distributions conditioned on different graphons as the underlying distance and leads to a reward-augmented maximum likelihood estimation. The graphon autoencoder provides a new paradigm to represent and generate graphs, which has good generalizability and transferability. © 2021, CC BY.

关键词： Graphic methods