检索结果-内蒙古大学图书馆

Neural Network Algorithm of Multi-team Game and Its application in Parallel-Link Communication Networks Flow Control 12th

学校读者我要写书评

暂无评论

Neural Network Algorithm of Multi-team Game and Its Applicat...

12th EAI International Conference on Simulation Tools and Techniques, SIMUtools 2020

作者： Liu, Zixin Yang, Huawei Xiong, Lianglin School of Mathematics and Statistics Guizhou University of Finance and Economics Guiyang China Guizhou Key Laboratory of Big Data Statistics Analysis Guizhou University of Finance and Economics Guiyang China School of Big Data Application and Economics Guizhou University of Finance and Economics Guiyang China School of Mathematics and Computer Science Yunnan Minzu University Kunming China

ISBN: (纸本)9783030727918

This paper investigates the approximate calculation problem of noninferior Nash equilibrium (NNE) in multi-team game. Combined with variational inequalities theory, Nash equilibrium theory, and dynamic system theory, a projection neural network (PNN) algorithm for computing NNE of multi-team game with smooth payoff functions is derived. Utilizing stable theory, stability criteria of NNE in multi-team game are further given. As an application, a flow control model of parallel-link communication networks based on multi-team game and neural network algorithm is elaborated. Finally, a simulation result for two teams, two communication links, and two users in each team parallel-linkcommunication network is also given to illustrate the effectiveness of the PNN algorithm proposed in this paper. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2021.

关键词： Flow control

Estimating early fundraising performance of innovations via graph-based market environment model

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wu, Likang Li, Zhi Zhao, Hongke Pan, Zhen Liu, Qi Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China College of Management and Economics Tianjin University

Well begun is half done. In the crowdfunding market, the early fundraising performance of the project is a concerned issue for both creators and platforms. However, estimating the early fundraising performance before the project published is very challenging and still under-explored. To that end, in this paper, we present a focused study on this important problem in a market modeling view. Specifically, we propose a Graph-based Market Environment model (GME) for estimating the early fundraising performance of the target project by exploiting the market environment. In addition, we discriminatively model the market competition and market evolution by designing two graph-based neural network architectures and incorporating them into the joint optimization stage. Finally, we conduct extensive experiments on the real-world crowdfunding data collected from ***. The experimental results clearly demonstrate the effectiveness of our proposed model for modeling and estimating the early fundraising performance of the target project. Copyright © 2019, The Authors. All rights reserved.

关键词： Crowdsourcing

Transcribing content from structural images with spotlight mechanism

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yin, Yu Huang, Zhenya Chen, Enhong Liu, Qi Zhang, Fuzheng Xie, Xing Hu, Guoping Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Microsoft Research Asia IFLYTEK Research

Transcribing content from structural images, e.g., writing notes from music scores, is a challenging task as not only the content objects should be recognized, but the internal structure should also be preserved. Existing image recognition methods mainly work on images with simple content (e.g., text lines with characters), but are not capable to identify ones with more complex content (e.g., structured code), which often follow a fine-grained grammar. To this end, in this paper, we propose a hierarchical Spotlight Transcribing Network (STN) framework followed by a two-stage "where-to-what" solution. Specifically, we first decide "where-tolook" through a novel spotlight mechanism to focus on different areas of the original image following its structure. Then, we decide "what-to-write" by developing a GRU based network with the spotlight areas for transcribing the content accordingly. Moreover, we propose two implementations on the basis of STN, i.e., STNM and STNR, where the spotlight movement follows the Markov property and Recurrent modeling, respectively. We also design a reinforcement method to refine our STN framework by self-improving the spotlight mechanism. We conduct extensive experiments on many structural image datasets, where the results clearly demonstrate the effectiveness of STN framework. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

Variance reduced local SGD with lower communication complexity

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liang, Xianfeng Shen, Shuheng Liu, Jingchang Pan, Zhen Chen, Enhong Cheng, Yifei Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Hong Kong University of Science and Technology

To accelerate the training of machine learning models, distributed stochastic gradient descent (SGD) and its variants have been widely adopted, which apply multiple workers in parallel to speed up training. Among them, Local SGD has gained much attention due to its lower communication cost. Nevertheless, when the data distribution on workers is non-identical, Local SGD requires O(T 3 4 N 3 4 ) communications to maintain its linear iteration speedup property, where T is the total number of iterations and N is the number of workers. In this paper, we propose Variance Reduced Local SGD (VRL-SGD) to further reduce the communication complexity. Benefiting from eliminating the dependency on the gradient variance among workers, we theoretically prove that VRL-SGD achieves a linear iteration speedup with a lower communication complexity O(T 1 2 N 3 2 ) even if workers access non-identical datasets. We conduct experiments on three machine learning tasks, and the experimental results demonstrate that VRL-SGD performs impressively better than Local SGD when the data among workers are quite diverse. Copyright © 2019, The Authors. All rights reserved.

关键词： Computational complexity

Improved Method for Intersection Multi-Events Traffic Signal Induction Control in Intelligent Connected New Energy Vehicles 1

学校读者我要写书评

暂无评论

Improved Method for Intersection Multi-Events Traffic Signal...

1st International Conference on Intelligent Transportation and Smart Cities, ICITSC 2024

作者： Wang, Ruihan Liang, Zijun Li, Yuqi Zhan, Xuejuan Wang, Ruipeng Deng, Ran Niu, Yiran Kumari, Saru School of Urban Construction and Transportation Hefei University Hefei230601 China Anhui Provincial Key Laboratory of Urban Rail Transit Safety and Emergency Management Hefei China Anhui Province Transportation Big Data Analysis and Application Engineering Laboratory Hefei China Department of Mathematics Ch. Charan Singh University Meerut India

ISBN: (纸本)9781643685205

Traditional fixed signal timing often leads to issues such as green light empty and residual queue at intersections. Traffic signal induction control can automatically adjust signal timing based on vehicle arrivals, but it still struggles to handle immediate control of special traffic events like long queue, exit overflow and intersection deadlock. Furthermore, it does not account for the impact of intelligent connected new energy vehicles (ICNEVs). So we propose an improved method for intersection multi-events traffic signal induction control in ICNEVs. The method involves deploying various types of detectors at intersections to identify events like green light empty, long queue, exit overflow, and intersection deadlock. Establish the induction control logic rules corresponding to different events, and consider the permeability optimization control parameters of ICNEVs at intersection. Finally, the proposed method is validated using real intersection data through the VISSIM traffic simulation software. The results demonstrate that the method effectively reduces the average queue length and delay at intersections. It also reveals that the higher the permeability of ICNEVs, the better the performance of intersection induction control. © 2024 The Authors.

关键词： Traffic signals

Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Likang Wang, Hao Chen, Enhong Li, Zhi Zhao, Hongke Ma, Jianhui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Anhui Hefei China College of Management and Economics Tianjin University Tianjin China

Network-aware cascade size prediction aims to predict the final reposted number of user-generated information via modeling the propagation process in social networks. Estimating the user's reposting probability by social influence, namely state activation plays an important role in the information diffusion process. Therefore, Graph Neural Networks (GNN), which can simulate the information interaction between nodes, has been proved as an effective scheme to handle this prediction task. However, existing studies including GNN-based models usually neglect a vital factor of user's preference which influences the state activation deeply. To that end, we propose a novel framework to promote cascade size prediction by enhancing the user preference modeling according to three stages, i.e., preference topics generation, preference shift modeling, and social influence activation. Our end-to-end method makes the user activating process of information diffusion more adaptive and accurate. Extensive experiments on two large-scale real-world datasets have clearly demonstrated the effectiveness of our proposed model compared to state-of-the-art baselines. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

Incorporating BERT into parallel sequence decoding with adapters 20

学校读者我要写书评

暂无评论

Incorporating BERT into parallel sequence decoding with adap...

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Junliang Guo Zhirui Zhang Linli Xu Hao-Ran Wei Boxing Chen Enhong Chen Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Alibaba DAMO Academy Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and IFLYTEK Co. Ltd.

ISBN: (纸本)9781713829546

While large scale pre-trained language models such as BERT [5] have achieved great success on various natural language understanding tasks, how to efficiently and effectively incorporate them into sequence-to-sequence models and the corresponding text generation tasks remains a non-trivial problem. In this paper, we propose to address this problem by taking two different BERT models as the encoder and decoder respectively, and fine-tuning them by introducing simple and lightweight adapter modules, which are inserted between BERT layers and tuned on the task-specific dataset. In this way, we obtain a flexible and efficient model which is able to jointly leverage the information contained in the source-side and target-side BERT models, while bypassing the catastrophic forgetting problem. Each component in the framework can be considered as a plug-in unit, making the framework flexible and task agnostic. Our framework is based on a parallel sequence decoding algorithm named Mask-Predict [8] considering the bi-directional and conditional independent nature of BERT, and can be adapted to traditional autoregressive decoding easily. We conduct extensive experiments on neural machine translation tasks where the proposed method consistently outperforms autoregressive baselines while reducing the inference latency by half, and achieves 36.49/33.57 BLEU scores on IWSLT14 German-English/WMT14 German-English translation. When adapted to autoregressive decoding, the proposed method achieves 30.60/43.56 BLEU scores on WMT14 English-German/English-French translation, on par with the state-of-the-art baseline models.

关键词：

AdaptSSR: pre-training user model with augmentation-adaptive self-supervised ranking 23

学校读者我要写书评

暂无评论

AdaptSSR: pre-training user model with augmentation-adaptive...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yang Yu Qi Liu Kai Zhang Yuren Zhang Chao Song Min Hou Yuqing Yuan Zhihao Ye Zaixi Zhang Sanshi Lei Yu Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence OPPO Research Institute Hefei University of Technology

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on massive user behavior sequences with a contrastive learning task. Generally, these methods assume different views of the same behavior sequence constructed via data augmentation are semantically consistent, i.e., reflecting similar characteristics or interests of the user, and thus maximizing their agreement in the feature space. However, due to the diverse interests and heavy noise in user behaviors, existing augmentation methods tend to lose certain characteristics of the user or introduce noisy behaviors. Thus, forcing the user model to directly maximize the similarity between the augmented views may result in a negative transfer. To this end, we propose to replace the contrastive learning task with a new pretext task: Augmentation-Adaptive Self-Supervised Ranking (AdaptSSR), which alleviates the requirement of semantic consistency between the augmented views while pre-training a discriminative user model. Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users. We further employ an in-batch hard negative sampling strategy to facilitate model training. Moreover, considering the distinct impacts of data augmentation on different behavior sequences, we design an augmentation-adaptive fusion mechanism to automatically adjust the similarity order constraint applied to each sample based on the estimated similarity between the augmented views. Extensive experiments on both public and industrial datasets with six downstream tasks verify the effectiveness of AdaptSSR.

关键词：

Fine-tuning by curriculum learning for non-autoregressive neural machine translation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Guo, Junliang Tan, Xu Xu, Linli Qin, Tao Chen, Enhong Liu, Tie-Yan Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Microsoft Research

Non-autoregressive translation (NAT) models remove the dependence on previous target tokens and generate all target tokens in parallel, resulting in significant inference speedup but at the cost of inferior translation accuracy compared to autoregressive translation (AT) models. Considering that AT models have higher accuracy and are easier to train than NAT models, and both of them share the same model configurations, a natural idea to improve the accuracy of NAT models is to transfer a well-trained AT model to an NAT model through fine-tuning. However, since AT and NAT models differ greatly in training strategy, straightforward fine-tuning does not work well. In this work, we introduce curriculum learning into fine-tuning for NAT. Specifically, we design a curriculum in the fine-tuning process to progressively switch the training from autoregressive generation to non-autoregressive generation. Experiments on four benchmark translation datasets show that the proposed method achieves good improvement (more than 1 BLEU score) over previous NAT baselines in terms of translation accuracy, and greatly speed up (more than 10 times) the inference process over AT baselines. Copyright © 2019, The Authors. All rights reserved.

关键词： Curricula