2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)最新文献_第7页

Optimized Echo State Network based on PSO and Gradient Descent for Choatic Time Series Prediction 基于粒子群优化和梯度下降的回声状态网络Choatic时间序列预测

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00115

Rebh Soltani, Emna Benmohamed, Hela Ltifi

引用次数: 4

Implicit and Explicit Emotion Enhanced Empathetic Dialogue Generation 内隐和外显情绪增强共情对话的产生

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00211

Qingmeng Zhu, Chen Li, Hao He, Hetian Song, Ziyin Gu, Wenjing Ying

{"title":"Implicit and Explicit Emotion Enhanced Empathetic Dialogue Generation","authors":"Qingmeng Zhu, Chen Li, Hao He, Hetian Song, Ziyin Gu, Wenjing Ying","doi":"10.1109/ICTAI56018.2022.00211","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00211","url":null,"abstract":"Empathetic conversation systems identify the users' emotions and give appropriate responses, which is crucial to improve users' experiences. However, existing empathetic dialogue models (especially to the dominant pre-trained language model-based systems) did not focus on modelling the holistic properties of implicit and explicit emotions. In this paper, we propose an Implicit and Explicit Emotion Enhanced (IEEE) empathetic dialogue generation model to handle such challenges. Specifically, we first propose a prompt tuning-based approach to mine emotional words as additional information to obtain the users' explicit emotion. A variational auto-encoder is then introduced to extract the topic words of the input sequence as additional priori knowledge to get the implicit emotion related information. Finally, a pre-trained language model is utilized as the auto-regressive decoder to generate empathetic responses related to the content of the topics and user emotions. To demonstrate the effectiveness of the proposed approach, IEEE has been tested on empathic dialogue dataset. The experimental results show that our method achieves better performance than some competitive models.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129374948","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: 0

Sequential Recommendation with Dual Learning 顺序推荐与双重学习

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00017

Chenliang Zhang, Lingfeng Shi

引用次数: 0

A Dilated Transformer Network for Time Series Anomaly Detection 一种用于时间序列异常检测的扩展变压器网络

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00016

Bo Wu, Zhenjie Yao, Yanhui Tu, Yixin Chen

引用次数: 0

Local-guided Global Collaborative Learning Transformer for Vehicle Reidentification 车辆再识别的局部引导全局协同学习转换器

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00122

Yanling Shi, Xiaofei Zhang, X. Tan

{"title":"Local-guided Global Collaborative Learning Transformer for Vehicle Reidentification","authors":"Yanling Shi, Xiaofei Zhang, X. Tan","doi":"10.1109/ICTAI56018.2022.00122","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00122","url":null,"abstract":"Vehicle reidentification(ReID) has attracted much attention and is significant for traffic security surveillance. Due to the variety of views of the same vehicle captured by different camera and the great similarity in the visual appearance of different vehicles, it is necessary to explore how to effectively utilize local detail information to achieve collaborative perception to highlight discriminative appearance features. Different from existing local feature exploration methods that focus on using extra part or keypoint information, we propose a global collaborative learning Transformer guided by local abstract features, named LG-CoT, which aims to highlight the highest-attention regions of vehicle images. We adopt Vision Transformer(ViT) as our backbone to extract global features and obtain all local tokens. To reduce the distribution from the background and drive the network to focus more on details, all attention maps containing low-level texture information and high-level semantic information are multiplied to obtain the local regions with highest-attention. Finally, we design a local-attention-guided pose-optimization feature encoding module, which can help the global features focus on local regions adaptively. Extensive experiments on two popular datasets and a dataset we built in a T-junction traffic scene suggest that our method can achieve comparable performance.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114251228","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: 0

PWPROP: A Progressive Weighted Adaptive Method for Training Deep Neural Networks PWPROP:一种渐进式加权自适应深度神经网络训练方法

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00081

D. Wang, Tao Xu, Huatian Zhang, Fanhua Shang, Hongying Liu, Yuanyuan Liu, Shengmei Shen

{"title":"PWPROP: A Progressive Weighted Adaptive Method for Training Deep Neural Networks","authors":"D. Wang, Tao Xu, Huatian Zhang, Fanhua Shang, Hongying Liu, Yuanyuan Liu, Shengmei Shen","doi":"10.1109/ICTAI56018.2022.00081","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00081","url":null,"abstract":"In recent years, adaptive optimization methods for deep learning have attracted considerable attention. AMSGRAD indicates that the adaptive methods may be hard to converge to optimal solutions of some convex problems due to the divergence of its adaptive learning rate as in ADAM. However, we find that AMSGRAD may generalize worse than ADAM for some deep learning tasks. We first show that AMSGRAD may not find a flat minimum. So how can we design an optimization method to find a flat minimum with low training loss? Few works focus on this important problem. We propose a novel progressive weighted adaptive optimization algorithm, called PWPROP, with fewer hyperparameters than its counterparts such as ADAM. By intuitively constructing a “sharp-flat minima” model, we show that how different second-order estimates affect the ability to escape a sharp minimum. Moreover, we also prove that PWPROP can address the non-convergence issue of ADAM and has a sublinear convergence rate for non-convex problems. Extensive experimental results show that PWPROP is effective and suitable for various deep learning architectures such as Transformer, and achieves state-of-the-art results.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127529478","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: 0

BiGNN: A Bilateral-Branch Graph Neural Network to Solve Popularity Bias in Recommendation BiGNN:一种解决推荐中人气偏差的双边分支图神经网络

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00129

Yingshuai Kou, Neng Gao, Yifei Zhang, Chenyang Tu, Cunqing Ma

{"title":"BiGNN: A Bilateral-Branch Graph Neural Network to Solve Popularity Bias in Recommendation","authors":"Yingshuai Kou, Neng Gao, Yifei Zhang, Chenyang Tu, Cunqing Ma","doi":"10.1109/ICTAI56018.2022.00129","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00129","url":null,"abstract":"Traditional recommendation methods aim to recom-mend personalized items by analyzing user's history interaction data. They ignore the fact that the data follows a long-tail distribution, which means that a small number of popular items account for most of the interaction records. This phenomenon causes the model to recommend more popular items, resulting in a severe popularity bias. In order to pay more attention to the long-tail items and debias the popular bias, we propose a Bilateral-Branch Graph Neural Network(BiGNN). In the long- tail branch, we construct a separate long-tail sub graph by eliminating the popular items with high degree. When the Graph Neural Network(GNN) aggregates information layer by layer in the subgraph, the receptive field of the single hop becomes larger, which increases the exposure of the long-tail items. Besides, another branch takes the original interaction graph as input to learn the general data distribution and generate the global embeddings of users and items. The two branches use the same GNN structure and share parameters. We employ the point-wise mutual information (PMI) strategy to indicate interaction between users and reconstruct the long-tail sub graph. The two branches are aggregated through an accumulated learning module, which makes the model first learn the conventional patterns and then pay attention to the long-tail data gradually. Extensive experiments on three real-world datasets show that BiGNN evidently outperforms the state-of- the-art methods consistently.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"8 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125858396","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

A Chunked Local Aggregation Strategy in Federated Learning 联邦学习中的分块局部聚合策略

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00014

Haibing Zhao, Weiqin Tong, Xiaoli Zhi, Tong Liu

{"title":"A Chunked Local Aggregation Strategy in Federated Learning","authors":"Haibing Zhao, Weiqin Tong, Xiaoli Zhi, Tong Liu","doi":"10.1109/ICTAI56018.2022.00014","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00014","url":null,"abstract":"Federated Learning (FL) is a distributed machine learning technology that trains models on large-scale distributed devices while keeping training data localized and privatized. However, in settings where data is distributed in a not independent and identically distributed (non-I.I.D.) fashion, the single joint model produced by FL suffers in terms of test set accuracy and communication costs. And a multi-layer topology are widely deployed for FL in real scenarios. Therefore, we propose FedBox, a chunked local aggregation federated learning framework to improve the generalization ability and aggregation efficiency of model in non-I.I.D. data by adapting to the topology of the real network. Moreover, we study the adaptive gradient descent (AGC) to mitigate the feature shift caused by training non-I.I.D. data. In this work, we modified the aggregation strategy of FL by introducing a virtual node layer based on local stochastic gradient methods (SGD), and separate the edge node cluster by the similarity between the local update model and the global update model. We show that FedBox can effectively improve convergence speed and test accuracy, while reducing communication cost. Training results on FederatedEMNIST, Cifar10, Cifar100 and Shakespeare datasets indicate that FedBox allows model training to converge in fewer communication rounds and improves training accuracy by up to 3.1% compared with FedAVG. In addition, we make an empirical analysis of the extended range of virtual nodes.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126054691","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: 0

A voting mechanism-based approach for identifying key nodes in complex networks 基于投票机制的复杂网络关键节点识别方法

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00207

Jun Chen, Xuesong Jiang, Xiumei Wei, Yihong Li

{"title":"A voting mechanism-based approach for identifying key nodes in complex networks","authors":"Jun Chen, Xuesong Jiang, Xiumei Wei, Yihong Li","doi":"10.1109/ICTAI56018.2022.00207","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00207","url":null,"abstract":"Many mechanisms, such as epidemic spread, rumor spread, and the spread of social emergencies, are closely related to complex network dynamics, and mining their key nodes plays an important role in understanding the structure and function of the network and maintaining its stable operation. In response to the problem that the key node identification methods in complex networks cannot comprehensively consider global and local information and ignore low-degree nodes, this study proposes a new method based on the voting mechanism. Firstly, the CI value of the network nodes is calculated using the CI algorithm, and initialized the voting ability of nodes by CI values, fully considering the local information of the nodes as well as the influence of low-degree nodes. Secondly, the concept of voting probability is introduced to distinguish the votes of network nodes for their different neighboring nodes through the voting probability, to consider more local information, and to comprehensively assess the importance of the nodes, and ultimately, it is more important to get nodes with the larger voting score. Comparing several classical key node identification methods, the experimental results show that this method can effectively identify key nodes and has a high accuracy rate in different complex networks.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126551987","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

Dual-Neighborhood Feature Aggregation Network for Point Cloud Semantic Segmentation 基于双邻域特征聚合网络的点云语义分割

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00020

Minghong Chen, Guanghui Zhang, Wenjun Shi, Dongchen Zhu, Xiaolin Zhang, Jiamao Li

{"title":"Dual-Neighborhood Feature Aggregation Network for Point Cloud Semantic Segmentation","authors":"Minghong Chen, Guanghui Zhang, Wenjun Shi, Dongchen Zhu, Xiaolin Zhang, Jiamao Li","doi":"10.1109/ICTAI56018.2022.00020","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00020","url":null,"abstract":"Neighborhood construction plays a key role in point cloud processing. However, existing models only use a single neighborhood construction method to extract neighborhood features, which limits their scene understanding ability. In this paper, we propose a learnable Dual-Neighborhood Feature Aggregation (DNFA) module embedded in the encoder that builds and aggregates comprehensive surrounding knowledge of point clouds. In this module, we first construct two kinds of neighborhoods and design corresponding feature enhancement blocks, including a Basic Local Structure Encoding (BLSE) block and an Extended Context Encoding (ECE) block. The two blocks mine structural and contextual cues for enhancing neighborhood features, respectively. Second, we propose a Geometry-Aware Compound Aggregation (GACA) block, which introduces a functionally complementary compound pooling strategy to aggregate richer neighborhood features. To fully learn the neighborhood distribution, we absorb the geometric location information during the aggregation process. The proposed module is integrated into an MLP-based large-scale 3D processing architecture, which constitutes a 3D semantic segmentation network called DNFA-Net. Extensive experiments on public datasets containing indoor and outdoor scenes validate the superiority of DNFA-Net.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121658310","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: 0