检索结果-内蒙古大学图书馆

Comparing Recommendation Algorithms in Session-based E-commerce Sites

学校读者我要写书评

暂无评论

Comparing Recommendation Algorithms in Session-based E-comme...

2020 International Conference on Intelligent Computing, Automation and Systems, ICICAS 2020

作者： Peng, Mingtian Zhang, Jiahe Wen, Shilin Liu, Chi Harold TravelSky Technology Limited Beijing Eng. Res. Ctr. of Civ. Aviat. Big Data and Key Lab. of Intelligent Passenger Serv. of Civ. Aviat.-CAAC Beijing China College of Computer Science Beijing Institute of Technology Beijing China

ISBN: (纸本)9781728191461

Recommender systems have become widely used in various website applications. With the integration of deep learning and recommender systems, the classic Session-based Recommender System (SRS) appears, which can obtain implicit feedback from explicit interactions. Some scholars have pro-posed many effective recommendation algorithms to provide better recommendation service in SRS. In order to compare the performance of these session-based recommendation algorithms, we consider a simple E-commerce SRS scenario and choose four representative session-based recommendation algorithms in this paper. Then we do some evaluation experiments. The experimental results show that the combination of local preferences and global preferences will improve the recommendation performance significantly, and for GNNs and RNN s in session recommendation based on deep learning, we also conclude that the prediction effect of GNN s is slightly superior to RNN s on long sessions. © 2020 IEEE.

关键词： Recommender systems

MoCA: Incorporating multi-stage domain pretraining and cross-guided multimodal attention for Textbook Question Answering

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Fangzhi Lin, Qika Liu, Jun Zhang, Lingling Zhao, Tianzhe Chai, Qi Pan, Yudai Department of Computer Science and Technology Xi'an Jiaotong University China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D Xi'an Jiaotong University China

Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams. Compared with Visual Question Answering(VQA), TQA contains a large number of uncommon terminologies and various diagram inputs. It brings new challenges to the representation capability of language model for domain-specific spans. And it also pushes the multimodal fusion to a more complex level. To tackle the above issues, we propose a novel model named MoCA, which incorporates multi-stage domain pretraining and multimodal cross attention for the TQA task. Firstly, we introduce a multi-stage domain pretraining module to conduct unsupervised post-pretraining with the span mask strategy and supervised pre-finetune. Especially for domain post-pretraining, we propose a heuristic generation algorithm to employ the terminology corpus. Secondly, to fully consider the rich inputs of context and diagrams, we propose cross-guided multimodal attention to update the features of text, question diagram and instructional diagram based on a progressive strategy. Further, a dual gating mechanism is adopted to improve the model ensemble. The experimental results show the superiority of our model, which outperforms the state-of-the-art methods by 2.21% and 2.43% for validation and test split respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Textbooks

Boosting black-box attack with partially transferred conditional adversarial distribution

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Feng, Yan Wu, Baoyuan Fan, Yanbo Liu, Li Li, Zhifeng Xia, Shutao Tsinghua Shenzhen International Graduate School Tsinghua University China School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China Tencent AI Lab China

This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown. One promising approach to improve attack performance is utilizing the adversarial transferability between some white-box surrogate models and the target model (i.e., the attacked model). However, due to the possible differences on model architectures and training datasets between surrogate and target models, dubbed "surrogate biases", the contribution of adversarial transferability to improving the attack performance may be weakened. To tackle this issue, we innovatively propose a black-box attack method by developing a novel mechanism of adversarial transferability, which is robust to the surrogate biases. The general idea is transferring partial parameters of the conditional adversarial distribution (CAD) of surrogate models, while learning the untransferred parameters based on queries to the target model, to keep the flexibility to adjust the CAD of the target model on any new benign sample. Extensive experiments on benchmark datasets and attacking against real-world API demonstrate the superior attack performance of the proposed method. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Pixel-wise dense detector for image inpainting

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Ruisong Quan, Weize Wu, Baoyuan Li, Zhifeng Yan, Dong-Ming National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Data Science Chinese University of Hong Kong Shenzhen Hong Kong Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data China Tencent AI Lab Shenzhen China

Recent GAN-based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar, which inevitably lose the position information of visual artifacts. Moreover, the adversarial loss and reconstruction loss (e.g., `1 loss) are combined with tradeoff weights, which are also difficult to tune. In this paper, we propose a novel detection-based generative framework for image inpainting, which adopts the min-max strategy in an adversarial process. The generator follows an encoder-decoder architecture to fill the missing regions, and the detector using weakly supervised learning localizes the position of artifacts in a pixel-wise manner. Such position information makes the generator pay attention to artifacts and further enhance them. More importantly, we explicitly insert the output of the detector into the reconstruction loss with a weighting criterion, which balances the weight of the adversarial loss and reconstruction loss automatically rather than manual operation. Experiments on multiple public datasets show the superior performance of the proposed framework. The source code is available at https://***/Evergrow/GDN_Inpainting. Copyright © 2020, The Authors. All rights reserved.

关键词： Pixels

A Solution-Based Tabu Search Algorithm for the Resource-Constrained Project Scheduling Problem with Step Deterioration

学校读者我要写书评

暂无评论

Mathematical Problems in Engineering 2023年第1期2023卷

作者： Dai, Huafeng Li, Lei Mao, Run Liu, Xingyue Zhou, Kun School of Mechanical Engineering Chengdu University Chengdu610105 China Technology and Equipment of Rail Transit Operation and Maintenance Key Laboratory of Sichuan Province Chengdu610031 China CNPC National Engineering Research Center for Oil & Gas Drilling Equipment Co. Ltd. Chengdu610052 China School of Information Science and Engineering Chengdu University Chengdu610105 China Key Lab. of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou310018 China

This paper integrates the classical resource-constrained project scheduling problem with step deterioration and accordingly presents a solution-based tabu search (SB-TS) algorithm to solve it with challenging computations. First, we choose successor list size as the priority rule to generate the initial solution of the presented methods. Next, the corresponding solution decoding and calculation ways are defined to update the related configuration at each iteration. Compared with the state-of-the-art methods, in terms of the known datasets, the proposed SB-TS finds the optimal solution for each instance in J30 and shows strongly competitive performance in J60, J90, and J120. Then, on newly generated datasets, where the step deterioration is attached to, the comparison experimental data state that the SB-TS with high-quality solution is superior to the move-based tabu search (MB-TS) algorithm. In addition, two key components are investigated to emphasize their attributions to the proposed algorithm. © 2023 Huafeng Dai et al.

关键词： Deterioration

Continual learning via inter-task synaptic mapping

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fubing, Mao Weiwei, Weng Pratama, Mahardhika Kien Yee, Edward Yapp National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab. Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Singapore Institute of Manufacturing Technology A*Star Singapore Singapore

Learning from streaming tasks leads a model to catastrophically erase unique experiences it absorbs from previous episodes. While regularization techniques such as LWF, SI, EWC have proven themselves as an effective avenue to overcome this issue by constraining important parameters of old tasks from changing when accepting new concepts, these approaches do not exploit common information of each task which can be shared to existing neurons. As a result, they do not scale well to large-scale problems since the parameter importance variables quickly explode. An Inter-Task Synaptic Mapping (ISYANA) is proposed here to underpin knowledge retention for continual learning. ISYANA combines task-to-neuron relationship as well as concept-to-concept relationship such that it prevents a neuron to embrace distinct concepts while merely accepting relevant concept. Numerical study in the benchmark continual learning problems has been carried out followed by comparison against prominent continual learning algorithms. ISYANA exhibits competitive performance compared to state of the arts. Codes of ISYANA is made available in https://***/ContinualAL/ISYANAKBS. © 2021, CC BY-NC-SA.

关键词： Neurons

Joint Compression and Deadline Optimization for Wireless Federated Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Maojun Li, Yang Liu, Dongzhu Jin, Richeng Zhu, Guangxu Zhong, Caijun Quek, Tony Q.S. The College of information Science and Electronic Engineering Zhejiang University Hangzhou China China Academy of Information and Communications Technology Beijing China School of Computing Science University of Glasgow United Kingdom The Department of Information and Communication Engineering Zhejiang University Hangzhou310007 China The Zhejiang–Singapore Innovation and AI Joint Research Lab Hangzhou310007 China Hangzhou310007 China The Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China The Peng Cheng Laboratory Guangdong Shenzhen518055 China Guangdong Guangzhou510555 China The Singapore University of Technology and Design Singapore487372 Singapore

Federated edge learning (FEEL) is a popular distributed learning framework for privacy-preserving at the edge, in which densely distributed edge devices periodically exchange model-updates with the server to complete the global model training. Due to limited bandwidth and uncertain wireless environment, FEEL may impose heavy burden to the current communication system. In addition, under the common FEEL framework, the server needs to wait for the slowest device to complete the update uploading before starting the aggregation process, leading to the straggler issue that causes prolonged communication time. In this paper, we propose to accelerate FEEL from two aspects: i.e., 1) performing data compression on the edge devices and 2) setting a deadline on the edge server to exclude the straggler devices. However, undesired gradient compression errors and transmission outage are introduced by the aforementioned operations respectively, affecting the convergence of FEEL as well. In view of these practical issues, we formulate a training time minimization problem, with the compression ratio and deadline to be optimized. To this end, an asymptotically unbiased aggregation scheme is first proposed to ensure zero optimality gap after convergence, and the impact of compression error and transmission outage on the overall training time are quantified through convergence analysis. Then, the formulated problem is solved in an alternating manner, based on which, the novel joint compression and deadline optimization (JCDO) algorithm is derived. Numerical experiments for different use cases in FEEL including image classification and autonomous driving show that the proposed method is nearly 30X faster than the vanilla FedSGD algorithm, and outperforms the state-of-the-art schemes. © 2023, CC BY.

关键词： Autonomous vehicles

HMRNet: High and Multi-Resolution Network with Bidirectional Feature Calibration for Brain Structure Segmentation in Radiotherapy

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fu, Hao Wang, Guotai Lei, Wenhui Xu, Wei Zhao, Qianfei Zhang, Shichuan Li, Kang Zhang, Shaoting The School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu611731 China Shanghai AI Laboratory Shanghai200030 China Department of Radiation Oncology Sichuan Cancer Hospital and Institute University of Electronic Science and Technology of China Chengdu610042 China West China Hospital-SenseTime Joint Lab West China Biomedical Big Data Center Sichuan University West China Hospital Chengdu610041 China SenseTime Research Shanghai200233 China

Accurate segmentation of Anatomical brain Barriers to Cancer spread (ABCs) plays an important role for automatic delineation of Clinical Target Volume (CTV) of brain tumors in radiotherapy. Despite that variants of U-Net are state-of-the-art segmentation models, they have limited performance when dealing with ABCs structures with various shapes and sizes, especially thin structures (e.g., the falx cerebri) that span only few slices. To deal with this problem, we propose a High and Multi-Resolution Network (HMRNet) that consists of a multi-scale feature learning branch and a high-resolution branch, which can maintain the high-resolution contextual information and extract more robust representations of anatomical structures with various scales. We further design a Bidirectional Feature Calibration (BFC) block to enable the two branches to generate spatial attention maps for mutual feature calibration. Considering the different sizes and positions of ABCs structures, our network was applied after a rough localization of each structure to obtain fine segmentation results. Experiments on the MICCAI 2020 ABCs challenge dataset showed that: 1) Our proposed two-stage segmentation strategy largely outperformed methods segmenting all the structures in just one stage;2) The proposed HMRNet with two branches can maintain high-resolution representations and is effective to improve the performance on thin structures;3) The proposed BFC block outperformed existing attention methods using monodirectional feature calibration. Our method won the second place of ABCs 2020 challenge and has a potential for more accurate and reasonable delineation of CTV of brain tumors. © 2022, CC BY.

关键词： Brain

An improved linear population size reduction based parameters with adaptive learning mechanism differential evolution (iLPALMDE) for real-parameter single objective black box optimization 2nd

学校读者我要写书评

暂无评论

An improved linear population size reduction based parameter...

2nd International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2018

作者： Meng, Zhenyu Pan, Jeng-Shyang Zheng, Wei-Min Li, Xiaoqing Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology Fuzhou China Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9783030045814

In this paper, we proposed an improved Linear population size reduction based Parameters with Adaptive Learning Mechanism Differential Evolution (iLPALMDE) for real-parameter single objective black box optimization. The LPALMDE algorithm is a state-of-the-art DE variant proposed recently, nevertheless, it still has some weakness, e.g. the update scheme of crossover rate is heavily dependent on the number of individuals in each group, which may fall into a bad adaptation of crossover rate when population size becomes small in the linear population size reduction scheme. Therefore, a new adaptation scheme of crossover rate was advanced in this paper to tackle the weakness. This novel improved algorithm is verified under the CEC2013 benchmarks, and experiment results shows that it was competitive with other state of the art DE variants. © Springer Nature Switzerland AG 2019.

关键词： Population statistics