2021 International Joint Conference on Neural Networks (IJCNN)最新文献

Forecasting Stock Prices Using Stock Correlation Graph: A Graph Convolutional Network Approach 用股票相关图预测股票价格:一种图卷积网络方法

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533510

Xingkun Yin, Da Yan, A. I. Almudaifer, Sibo Yan, Yang Zhou

{"title":"Forecasting Stock Prices Using Stock Correlation Graph: A Graph Convolutional Network Approach","authors":"Xingkun Yin, Da Yan, A. I. Almudaifer, Sibo Yan, Yang Zhou","doi":"10.1109/IJCNN52387.2021.9533510","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533510","url":null,"abstract":"Accurate forecasting of stock prices plays an important role in stock investment. With the advancement of AI in Fintech applications, various deep learning models have recently been developed for stock price forecasting. However, these models focus on designing sequence models to capture the temporal dependence from a stock's historical prices (and other information such as technical indicators and news), leaving the information from similar stocks underexplored. To fill this gap, we propose a novel deep learning approach for stock price forecasting, which builds and uses a stock correlation graph $G$ where nodes are stocks and edges connect highly price-correlated stocks. Our model combines the graph convolutional network (GCN) and gated recurrent unit (GRU). Specifically, the GCN is used to extract features from the price of each stock and the prices of those highly similar stocks in G. For each stock, a sequence of these extracted features are then fed into a GRU model to capture temporal dependence. The model training follows the idea of multi-task learning, where each task learns its unique RNN-based sequence predictor for one stock, but all stocks share a common GCN module to improve GCN training to more effectively propagate correlation-related market signals. Our extensive experiments on real stock price data demonstrate that our approach consistently outperforms a GRU baseline that does not consider similar stocks during prediction, which verifies the effectiveness of using a stock correlation graph.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"13 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":"115230664","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: 8

Ontological Concept Structure Aware Knowledge Transfer for Inductive Knowledge Graph Embedding 基于本体概念结构感知的归纳知识图嵌入知识转移

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533852

Chao Ren, Le Zhang, Lintao Fang, Tong Xu, Zhefeng Wang, Senchao Yuan, Enhong Chen

{"title":"Ontological Concept Structure Aware Knowledge Transfer for Inductive Knowledge Graph Embedding","authors":"Chao Ren, Le Zhang, Lintao Fang, Tong Xu, Zhefeng Wang, Senchao Yuan, Enhong Chen","doi":"10.1109/IJCNN52387.2021.9533852","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533852","url":null,"abstract":"Conventional knowledge graph embedding methods mainly assume that all entities at reasoning stage are available in the original training graph. But in real-world application scenarios, newly emerged entities are always inevitable, which results in the severe problem of out-of-knowledge-graph entities. Existing efforts on this issue mostly either utilize additional resources, e.g., entity descriptions, or simply aggregate in-knowledge-graph neighbors to embed these new entities inductively. However, high-quality additional resources are usually hard to obtain and existing neighbors of new entities may be too sparse to provide enough information for modeling these entities. Meanwhile, they may fail to integrate the rich information of ontological concepts, which provide a general figure of instance entities and usually remain unchanged in knowledge graph. To this end, we propose a novel inductive framework namely CatE to solve the sparsity problem with the enhancement from ontological concepts. Specifically, we first adopt the transformer encoder to model the complex contextual structure of the ontological concepts. Then, we further develop a template refinement strategy for generating the target entity embedding, where the concept embedding is used to form a basic skeleton of the target entity and the individual characteristics of the entity will be enriched by its existing neighbors. Finally, extensive experiments on public datasets demonstrate the effectiveness of our proposed model compared with state-of-the-art baseline methods.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"44 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":"115267334","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

Multi-Aspect Controlled Response Generation in a Multimodal Dialogue System using Hierarchical Transformer Network 基于分层变压器网络的多模态对话系统的多面向控制响应生成

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533886

Mauajama Firdaus, Nidhi Thakur, Asif Ekbal

{"title":"Multi-Aspect Controlled Response Generation in a Multimodal Dialogue System using Hierarchical Transformer Network","authors":"Mauajama Firdaus, Nidhi Thakur, Asif Ekbal","doi":"10.1109/IJCNN52387.2021.9533886","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533886","url":null,"abstract":"Multimodality in dialogues has become crucial for a thorough understanding of the intent of the user to provide better responses to fulfill user's demands. Existing dialogue systems suffer from the issue of inconsistency and dull responses. Many goal-oriented conversational systems lack the different aspect information of the products or services to present an informative and exciting response. Aspects such as the price, color, pattern, rating are essential for deciding whether to purchase/order. To alleviate the issues in the existing systems, we propose the novel task of multi-aspect guided dialogue generation. This task is introduced to focus on making the responses focused and consistent with the different aspects mentioned in the current dialogue. In our present work, we design a hierarchical transformer network to capture the dialogue context for generating the responses. For creating the responses with multiple aspects, we explicitly give the aspect vectors at the time of decoding for generation. The information of the aspects specified to the decoder controls the overall generation process. We evaluate our proposed hierarchical framework on the newly created multi-domain multi-modal dialogue (MDMMD) dataset consisting of both text and images. Experimental results show that the proposed system outperforms all the existing and baseline approaches. The aspect controlled responses are immensely consistent with the ongoing dialogue and highly diverse resolving the issues of the current systems.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"75 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":"115301895","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

SPAD+: An Improved Probabilistic Anomaly Detector based on One-dimensional Histograms SPAD+:一种基于一维直方图的改进概率异常检测器

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534162

Sunil Aryal, Arbind Agrahari Baniya, Imran Razzak, K. Santosh

引用次数: 0

Augmenting Training Data for Low-Resource Neural Machine Translation via Bilingual Word Embeddings and BERT Language Modelling 基于双语词嵌入和BERT语言建模的低资源神经机器翻译训练数据增强

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534211

Akshai Ramesh, Haque Usuf Uhana, V. Parthasarathy, Rejwanul Haque, Andy Way

{"title":"Augmenting Training Data for Low-Resource Neural Machine Translation via Bilingual Word Embeddings and BERT Language Modelling","authors":"Akshai Ramesh, Haque Usuf Uhana, V. Parthasarathy, Rejwanul Haque, Andy Way","doi":"10.1109/IJCNN52387.2021.9534211","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534211","url":null,"abstract":"Neural machine translation (NMT) is often described as ‘data hungry’ as it typically requires large amounts of parallel data in order to build a good-quality machine translation (MT) system. However, most of the world's language-pairs are low-resource or extremely low-resource. This situation becomes even worse if a specialised domain is taken into consideration for translation. In this paper, we present a novel data augmentation method which makes use of bilingual word embeddings (BWEs) learned from monolingual corpora and bidirectional encoder representations from transformer (BERT) language models (LMs). We augment a parallel training corpus by introducing new words (i.e. out-of-vocabulary (OOV) items) and increasing the presence of rare words on both sides of the original parallel training corpus. Our experiments on the simulated low-resource German–English and French–English translation tasks show that the proposed data augmentation strategy can significantly improve state-of-the-art NMT systems and outperform the state-of-the-art data augmentation approach for low-resource NMT.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"17 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":"116854563","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

Deep Neural Networks Ensemble for Lung Nodule Detection on Chest CT Scans 基于深度神经网络集成的胸部CT肺结节检测

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534176

P. Ardimento, Lerina Aversano, M. Bernardi, Marta Cimitile

引用次数: 6

Semi-paired Image-to-Image Translation using Neighbor-based Generative Adversarial Networks 基于邻域生成对抗网络的半配对图像到图像翻译

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534353

Le Xu, Weiling Cai, Honghan Zhou

{"title":"Semi-paired Image-to-Image Translation using Neighbor-based Generative Adversarial Networks","authors":"Le Xu, Weiling Cai, Honghan Zhou","doi":"10.1109/IJCNN52387.2021.9534353","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534353","url":null,"abstract":"Image-to-image translation aims at learning the mapping between an input image and an output image using a training set of aligned image pairs. In reality, obtaining paired images is difficult and expensive. Generally, the data often exist in the form of partial pairing, that is, a small number of images are paired and most of the images are not paired. In this paper, we present a semi-paired image-to-image translation approach using neighbor-based generative adversarial networks. Our goal is to break the restriction that training images must be paired, and meanwhile guarantee the quality of image translation. For the unpaired images, we introduce an inverse mapping and cycle consistency loss to enforce the image reconstruction; for the paired images, we make full use of the one-to-one strong correlation to guide the image translation. To further take advantage of the paired images, our approach employs neighbor images to further expand the paired information and establishes the neighbor-based cycle consistency. Our method is characterized by flexibility and adaptability under various scenarios, such as target deformation, day-night transformation, etc. Compared with the previous methods, the experimental results prove the superiority of our method.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"37 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":"117127630","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 Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost 机器学习、深度学习和XGBoost自动学习工具的比较

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534091

Luís Ferreira, A. Pilastri, C. Martins, Pedro Miguel Pires, Paulo Cortez

{"title":"A Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost","authors":"Luís Ferreira, A. Pilastri, C. Martins, Pedro Miguel Pires, Paulo Cortez","doi":"10.1109/IJCNN52387.2021.9534091","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534091","url":null,"abstract":"This paper presents a benchmark of supervised Automated Machine Learning (AutoML) tools. Firstly, we analyze the characteristics of eight recent open-source AutoML tools (Auto-Keras, Auto-PyTorch, Auto-Sklearn, AutoGluon, H2O AutoML, rminer, TPOT and TransmogrifAI) and describe twelve popular OpenML datasets that were used in the benchmark (divided into regression, binary and multi-class classification tasks). Then, we perform a comparison study with hundreds of computational experiments based on three scenarios: General Machine Learning (GML), Deep Learning (DL) and XGBoost (XGB). To select the best tool, we used a lexicographic approach, considering first the average prediction score for each task and then the computational effort. The best predictive results were achieved for GML, which were further compared with the best OpenML public results. Overall, the best GML AutoML tools obtained competitive results, outperforming the best OpenML models in five datasets. These results confirm the potential of the general-purpose AutoML tools to fully automate the Machine Learning (ML) algorithm selection and tuning.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"25 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":"117129853","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: 34

Unsupervised Discovery of Transitional Skills for Deep Reinforcement Learning 深度强化学习过渡技能的无监督发现

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533820

Qiangxing Tian, Jinxin Liu, Guanchu Wang, Donglin Wang

引用次数: 9

Solar Image Hashing by Intermediate Descriptor and Autoencoder 基于中间描述符和自编码器的太阳图像哈希

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533490

Rafał Grycuk, R. Scherer

引用次数: 0