2021 International Joint Conference on Neural Networks (IJCNN)最新文献_第9页

A novel asynchronous sequential logic model of central pattern generator for quadruped robot: systematic design and efficient implementation 一种新的四足机器人中心模式发生器异步顺序逻辑模型:系统设计与高效实现

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533960

Shoichiro Komaki, Kentaro Takeda, H. Torikai

引用次数: 1

Group-Based Deep Transfer Learning with Mixed Gate Control for Cross- Domain Recommendation 基于群的混合门控制深度迁移学习跨域推荐

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533861

Mingze Sun, Daiyue Xue, Weipeng Wang, Qifu Hu, Jianping Yu

{"title":"Group-Based Deep Transfer Learning with Mixed Gate Control for Cross- Domain Recommendation","authors":"Mingze Sun, Daiyue Xue, Weipeng Wang, Qifu Hu, Jianping Yu","doi":"10.1109/IJCNN52387.2021.9533861","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533861","url":null,"abstract":"For modern recommender systems, the issue of data sparsity still often arises in many cases. To address this challenge, Cross-Domain Recommendation (CDR) has been explored by transferring knowledge learned from the source domain to alleviate the data sparsity in the target domain, and existing methods typically assume intra-domain samples share more commonalities than variabilities. However, it can also cause negative effects when there exists a high diversity among intra-domain samples. In this paper, we propose a novel Mixed Gate Control (MGC) model to fulfill 1) the division of samples into groups according to their commonalities and 2) the transfer of knowledge based on groups. We stack up multiple MGC layers into Multiple Layers MGC (ML-MGC) and apply it to a large-scale bundle retrieval system in a listed internet company. We conduct experiments on its own commercial dataset and two public real-world datasets. Experimental results show the superiority of our model against state-of-the-art methods for the CDR task. Finally, we present a case study to illustrate the groups identified by our model.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129997758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

ICE-GAN: Identity-Aware and Capsule-Enhanced GAN with Graph-Based Reasoning for Micro-Expression Recognition and Synthesis 基于图形推理的微表情识别和合成的身份感知和胶囊增强GAN

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533988

Jianhui Yu, Chaoyi Zhang, Yang Song, Weidong (Tom) Cai

引用次数: 3

Domain-Aware Multiagent Reinforcement Learning in Navigation 导航领域感知多智能体强化学习

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533975

Ifrah Saeed, Andrew C. Cullen, S. Erfani, T. Alpcan

{"title":"Domain-Aware Multiagent Reinforcement Learning in Navigation","authors":"Ifrah Saeed, Andrew C. Cullen, S. Erfani, T. Alpcan","doi":"10.1109/IJCNN52387.2021.9533975","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533975","url":null,"abstract":"Multiagent reinforcement learning has shown success in guiding the agents' behaviour in systems that have realworld significance. In these frameworks, agents learn how to interact with the environment and other agents while satisfying their objectives. Unfortunately, the level of complexity of realworld problems requires a significant investment of computational resources before multiagent reinforcement learning methods are able to deliver results. However, by incorporating a priori domain knowledge, more computationally-efficient algorithms can be developed. In this paper, for the first time, we present a Domain-Aware Multiagent Actor-Critic (DAMAC) algorithm, which integrates domain knowledge with the centralised learning and decentralised execution multiagent reinforcement learning approach using domain-specific solvers. Our experiments show that our algorithm achieves substantial high reward and reduces the training time by two orders of magnitude as compared to other multiagent reinforcement learning algorithms. This enables the adoption of this powerful framework in more resource-constrained scenarios.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134261970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Neural Architecture Search Based on Evolutionary Algorithms with Fitness Approximation 基于适应度逼近进化算法的神经结构搜索

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533986

Chao Pan, Xin Yao

{"title":"Neural Architecture Search Based on Evolutionary Algorithms with Fitness Approximation","authors":"Chao Pan, Xin Yao","doi":"10.1109/IJCNN52387.2021.9533986","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533986","url":null,"abstract":"Designing advanced neural architectures to tackle specific tasks involves weeks or even months of intensive investigation by experts with rich domain knowledge. In recent years, neural architecture search (NAS) has attracted the interest of many researchers due to its ability to automatically design efficient neural architectures. Among different search strategies, evolutionary algorithms have achieved significant successes as derivative-free optimization algorithms. However, the tremendous computational resource consumption of the evolutionary neural architecture search dramatically restricts its application. In this paper, we explore how fitness approximation-based evolutionary algorithms can be applied to neural architecture search and propose NAS-EA-FA to accelerate the search process. We further exploit data augmentation and diversity of neural architectures to enhance the algorithm, and present NAS-EA-FA V2. Experiments show that NAS-EA-FA V2 is at least five times faster than other state-of-the-art neural architecture search algorithms like regularized evolution and iterative neural predictor on NASBench-101, and it is also the most effective and stable algorithm on NASBench-201. All the code used in this paper is available at https://github.com/fzjcdt/NAS-EA-FA.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134265245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

One-Shot Imitation Learning on Heterogeneous Associated Tasks via Conjugate Task Graph 基于共轭任务图的异构关联任务单次模仿学习

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533467

Tiancheng Huang, Feng Zhao, Donglin Wang

引用次数: 2

Quantum Convolutional Neural Network on Protein Distance Prediction 量子卷积神经网络在蛋白质距离预测中的应用

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533405

Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Xinghua Zhu, Jie Liu, Jing Xiao

{"title":"Quantum Convolutional Neural Network on Protein Distance Prediction","authors":"Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Xinghua Zhu, Jie Liu, Jing Xiao","doi":"10.1109/IJCNN52387.2021.9533405","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533405","url":null,"abstract":"Proteins are linear polymers that fold into an incredible variety of three-dimensional structures that enable sophisticated functionality for biology. Predicting protein distance with high precision remains challenging, particularly for small protein families. As deep learning achieves remarkable success in many areas, deep learning also allows scientists to predict proteins' three-dimensional structure. As convolutional neural networks have a powerful ability to learn data features at multiple levels of abstraction, we deploy CNN to predict protein distance. To accelerate the training process, we apply a quantum convolutional neural network(QCNN) to improve the protein structure prediction efficiently. For QCNN, the conventional convolutional layer is transformed to a quantum convolution or quanvolutional layer. Since the protein data has large input, we explore the large dimension of these quantum transformations. And in experiments, we compare the different number of layers in QCNN during the training phase. We found the QCNN is similar to CNN that is the deeper layer can get better performance. The simulations show the proposed method can accelerate the convergence while maintaining the performance.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133975753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Drug-drug Interaction Prediction with Common Structural Patterns 基于共同结构模式的药物-药物相互作用预测

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533382

Jiongmin Zhang, Xin Yang, Ying Qian

引用次数: 1

Interpretable Goal Recognition for Path Planning with ART Networks 基于ART网络的路径规划可解释目标识别

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/ijcnn52387.2021.9534409

Yue Hu, Kai Xu, Budhitama Subagdja, A. Tan, Quanjun Yin

{"title":"Interpretable Goal Recognition for Path Planning with ART Networks","authors":"Yue Hu, Kai Xu, Budhitama Subagdja, A. Tan, Quanjun Yin","doi":"10.1109/ijcnn52387.2021.9534409","DOIUrl":"https://doi.org/10.1109/ijcnn52387.2021.9534409","url":null,"abstract":"Goal recognition for path planning is an important task of intention identification and situation awareness, requiring an observer to predict the goal of an evader given observations of its movements. While existing models based on planning or Markov Decision Process (MDP) show superior performance over traditional library based methods, they require much effort in model design and can hardly provide legible decision rules for their users. To make the system more user-friendly while preserving accuracy of goal inference, this paper proposes a novel self-organizing neural network based inference model, which learns compact rule sets through generalizing the streaming observations of an evader. More critically, the system manifests a high level of interpretability with the linguistic if-then rule base, making it easily comprehensible for human decision makers. We conducted extensive experiments on a large-scale real-world road network. Results show that the proposed model produces accuracy comparable to those of two state-of-the-art methods while uniquely providing legible inference rules and strong robustness against multiple goals with missing data.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131843919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Attention-Based Graph Neural Network for News Recommendation 基于注意力的新闻推荐图神经网络

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534339

Zhenyan Ji, Mengdan Wu, Jirui Liu, J. E. Armendáriz-Iñigo

{"title":"Attention-Based Graph Neural Network for News Recommendation","authors":"Zhenyan Ji, Mengdan Wu, Jirui Liu, J. E. Armendáriz-Iñigo","doi":"10.1109/IJCNN52387.2021.9534339","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534339","url":null,"abstract":"News recommendation aims to alleviate the big explosion of news information and helps users find their interesting news. Existing news recommendation models model users' historical click news as users' interests. Although they have achieved acceptable recommendation accuracy, they suffer from severe data sparse problems because of the limited news clicked by users. Further, the user's historical click sequence information has different effects on the user's interest, and simply combining them can not reflect this difference. Therefore, we propose an attention-based graph neural network news recommendation model. In our model, muti-channel convolutional neural network is used to generate news representations, and recurrent neural network is used to extract the news sequence information that users clicked on. Users, news, and topics are modeled as three types of nodes in a heterogeneous graph, and their relationships are modeled as edges. Graph neural network is used to effectively extract the structural information from heterogeneous graph, and helps to solve the problem of sparse data. Taking into account the different effects of different information on recommendation results, we use the attention mechanism to fuse this information distinctively. Extensive experiments conducted on the real online news datasets show that our model is superior to advanced deep learning-based recommendation methods.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127575422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2