2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)最新文献_第5页

HIAE: Hyper-Relational Interaction Aware Embedding for Link Prediction 链接预测的超关系交互感知嵌入

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00058

Lijie Li, Peikai Yuan, Ye Wang, Jiahang Li

引用次数: 0

Generating Adversarial Examples for Low-Resource NMT via Multi-Reward Reinforcement Learning 基于多奖励强化学习的低资源NMT对抗示例生成

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00179

Shuo Sun, H. Hou, Zongheng Yang, Yisong Wang, Nier Wu

引用次数: 0

Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar Pre-Avatar:利用会说话的Avatar的自动呈现生成框架

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00153

Aolan Sun, Xulong Zhang, Tiandong Ling, Jianzong Wang, Ning Cheng, Jing Xiao

引用次数: 3

Learning Generalized Hybrid Proximity Representation for Image Recognition 学习广义混合接近表示用于图像识别

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00138

Zhiyuan Li, A. Ralescu

{"title":"Learning Generalized Hybrid Proximity Representation for Image Recognition","authors":"Zhiyuan Li, A. Ralescu","doi":"10.1109/ICTAI56018.2022.00138","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00138","url":null,"abstract":"Recently, deep metric learning techniques received attentions, as the learned distance representations are useful to capture the similarity relationship among samples and further improve the performance of various of supervised or unsupervised learning tasks. We propose a novel supervised metric learning method that can learn the distance metrics in both geometric and probabilistic space for image recognition. In contrast to the previous metric learning methods which usually focus on learning the distance metrics in Euclidean space, our proposed method is able to learn better distance representation in a hybrid approach. To achieve this, we proposed a Generalized Hybrid Metric Loss (GHM-Loss) to learn the general hybrid proximity features from the image data by controlling the trade-off between geometric proximity and probabilistic proximity. To evaluate the effectiveness of our method, we first provide theoretical derivations and proofs of the proposed loss function, then we perform extensive experiments on two public datasets to show the advantage of our method compared to other state-of-the-art metric learning methods.","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":"121045783","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

Transfer Learning for Regression through Adaptive Gaussian Process 基于自适应高斯过程的回归迁移学习

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00015

Changhua Xu, Kai Yang, Xue Chen, Xiangfeng Luo, Hang Yu

引用次数: 0

Convolutional Transformer with Similarity-based Boundary Prediction for Action Segmentation 基于相似度边界预测的卷积变换动作分割

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00131

Dazhao Du, Bing Su, Yu Li, Zhongang Qi, Lingyu Si, Ying Shan

{"title":"Convolutional Transformer with Similarity-based Boundary Prediction for Action Segmentation","authors":"Dazhao Du, Bing Su, Yu Li, Zhongang Qi, Lingyu Si, Ying Shan","doi":"10.1109/ICTAI56018.2022.00131","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00131","url":null,"abstract":"Action classification has made great progress, but segmenting and recognizing actions from long videos remains a challenging problem. Recently, Transformer-based models with strong sequence modeling ability have succeeded in many se-quence modeling tasks. However, the lack of inductive bias and the difficulty of handling long video sequences limit the application of the Transformer in the action segmentation task. In order to explore the potential of the Transformer in this task, we replace some specific linear layers in the vanilla Transformer with dilated temporal convolution, and a sparse attention mechanism is utilized to reduce the time and space complexities to process long video sequences. Besides, directly using frame-wise classification loss to train the model will cause that frames at boundaries of actions are treated equally with those in the middle of actions, and the learned features are not sensitive to boundaries. We propose a new local log-context attention module to predict whether each frame is at the beginning, middle, or end of an action. Since boundary frames are similar to their neighboring frames of different classes, our similarity-based boundary prediction helps learn more discriminative features. Extensive experiments on three datasets show the effectiveness of our method.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"8 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":"125534681","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

Improving Surrogate Model Prediction by Noise Injection into Autoencoder Latent Space 自编码器隐空间噪声注入改进代理模型预测

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00085

Michele Lazzara, Max Chevalier, Jasone Garay–Garcia, C. Lapeyre, O. Teste

引用次数: 0

A game theoretic approach to curriculum reinforcement learning 课程强化学习的博弈论方法

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00184

M. Smyrnakis, Lan Hoang

引用次数: 0

Discriminative Graph Convolutional Networks for Semi-supervised Node Classification 半监督节点分类的判别图卷积网络

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00061

Guoguo Ai, Hui Yan, Yuxin Chen

{"title":"Discriminative Graph Convolutional Networks for Semi-supervised Node Classification","authors":"Guoguo Ai, Hui Yan, Yuxin Chen","doi":"10.1109/ICTAI56018.2022.00061","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00061","url":null,"abstract":"Graph Convolutional Networks (GCNs) gain remarkable success in graph-based semi-supervised node classification task. Despite their success, most GCNs still exist several challenges. For this task, it is necessary to draw nodes in the same class close and push ones from different classes apart. However, GCNs smooth the node's representation by aggregating information within node neighborhoods, despite whether the connected nodes are from the same class or not. The smooth property overlooks the intra-class similarity and inter-class diversity, which leads to GCNs failing especially on low homophilic or heterophilic graphs where most nodes have neighbors from different classes. In this paper, we propose the Discriminative Graph Convolution Networks (DGCN), an extension of GCN model with discriminant modules: intra-class smoothness and inter-class sharpness. The modules effectively strengthen the intra-class similarity and the inter-class differences by introducing available label information into the convolution process. Extensive experiments on six benchmark datasets demonstrate the effectiveness of DGCN in semi-supervised node classification. Code available at https://github.com/AIG22/DGCN.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"15 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":"128866572","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

MFSE: A Meta-Fusion Model for Polypharmacy Side-Effect Prediction with Graph Neural Networks 基于图神经网络的多药副作用预测元融合模型

2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2022-10-01 DOI: 10.1109/ICTAI56018.2022.00089

Aggelos Ragkousis, Olga Flogera, V. Megalooikonomou

{"title":"MFSE: A Meta-Fusion Model for Polypharmacy Side-Effect Prediction with Graph Neural Networks","authors":"Aggelos Ragkousis, Olga Flogera, V. Megalooikonomou","doi":"10.1109/ICTAI56018.2022.00089","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00089","url":null,"abstract":"Despite being a very popular approach for treating complex diseases, polypharmacy can lead to increased risk of adverse side effects, many of which are observed after the drugs have been released in the market. Luckily, the significant increase in data availability of observed adverse side-effects has paved the way for machine learning approaches to assist in their prediction. In this work, we first present a novel framework for multi-relational link prediction with graph neural networks. Given a multi-relational graph, we create relation-specific vector representations for each node of the graph. With this approach, we create drug vector representations that are side-effect specific, by integrating external molecular and protein-target information with the drug information that is generated directly from the drug-drug interaction prediction graph. With our new meta-fusion approach, each information type is produced from a distinct G NN - based encoder architecture and then the integration is performed according to the side-effect type being predicted. While state-of-the-art models report maximum AUROC scores of 0.91, our technique reaches a score of 0.95. Also, we show that our fusion approach provides valuable external knowledge particularly to drug nodes in the prediction graph that have a smaller node degree.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"3 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":"126988791","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