International Conference on Neural Information Processing最新文献_第2页

Multimodal Neural Network For Demand Forecasting 需求预测的多模态神经网络

International Conference on Neural Information Processing Pub Date : 2022-10-20 DOI: 10.48550/arXiv.2210.11502

Nitesh Kumar, K. Dheenadayalan, Suprabath Reddy, Sumant Kulkarni

引用次数: 2

Binary Orthogonal Non-negative Matrix Factorization 二元正交非负矩阵分解

International Conference on Neural Information Processing Pub Date : 2022-10-19 DOI: 10.48550/arXiv.2210.10660

S. F. Hafshejani, D. Gaur, S. Hossain, R. Benkoczi

引用次数: 0

DAGKT: Difficulty and Attempts Boosted Graph-based Knowledge Tracing DAGKT:难度和尝试提高了基于图的知识追踪

International Conference on Neural Information Processing Pub Date : 2022-10-18 DOI: 10.48550/arXiv.2210.15470

Rui Luo, Fei-Tsung Liu, Wen-yao Liang, Yuhong Zhang, Chenyang Bu, Xuegang Hu

引用次数: 1

Explainable Causal Analysis of Mental Health on Social Media Data 社交媒体数据对心理健康的可解释因果分析

International Conference on Neural Information Processing Pub Date : 2022-10-16 DOI: 10.48550/arXiv.2210.08430

Chandni Saxena, Muskan Garg, G. Saxena

{"title":"Explainable Causal Analysis of Mental Health on Social Media Data","authors":"Chandni Saxena, Muskan Garg, G. Saxena","doi":"10.48550/arXiv.2210.08430","DOIUrl":"https://doi.org/10.48550/arXiv.2210.08430","url":null,"abstract":"With recent developments in Social Computing, Natural Language Processing and Clinical Psychology, the social NLP research community addresses the challenge of automation in mental illness on social media. A recent extension to the problem of multi-class classification of mental health issues is to identify the cause behind the user's intention. However, multi-class causal categorization for mental health issues on social media has a major challenge of wrong prediction due to the overlapping problem of causal explanations. There are two possible mitigation techniques to solve this problem: (i) Inconsistency among causal explanations/ inappropriate human-annotated inferences in the dataset, (ii) in-depth analysis of arguments and stances in self-reported text using discourse analysis. In this research work, we hypothesise that if there exists the inconsistency among F1 scores of different classes, there must be inconsistency among corresponding causal explanations as well. In this task, we fine tune the classifiers and find explanations for multi-class causal categorization of mental illness on social media with LIME and Integrated Gradient (IG) methods. We test our methods with CAMS dataset and validate with annotated interpretations. A key contribution of this research work is to find the reason behind inconsistency in accuracy of multi-class causal categorization. The effectiveness of our methods is evident with the results obtained having category-wise average scores of $81.29 %$ and $0.906$ using cosine similarity and word mover's distance, respectively.","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131034405","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

Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction 联合稀疏度提升和冗余缩减的神经网络压缩

International Conference on Neural Information Processing Pub Date : 2022-10-14 DOI: 10.48550/arXiv.2210.07451

T. M. Khan, S. Naqvi, A. Robles-Kelly, E. Meijering

{"title":"Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction","authors":"T. M. Khan, S. Naqvi, A. Robles-Kelly, E. Meijering","doi":"10.48550/arXiv.2210.07451","DOIUrl":"https://doi.org/10.48550/arXiv.2210.07451","url":null,"abstract":"Compression of convolutional neural network models has recently been dominated by pruning approaches. A class of previous works focuses solely on pruning the unimportant filters to achieve network compression. Another important direction is the design of sparsity-inducing constraints which has also been explored in isolation. This paper presents a novel training scheme based on composite constraints that prune redundant filters and minimize their effect on overall network learning via sparsity promotion. Also, as opposed to prior works that employ pseudo-norm-based sparsity-inducing constraints, we propose a sparse scheme based on gradient counting in our framework. Our tests on several pixel-wise segmentation benchmarks show that the number of neurons and the memory footprint of networks in the test phase are significantly reduced without affecting performance. MobileNetV3 and UNet, two well-known architectures, are used to test the proposed scheme. Our network compression method not only results in reduced parameters but also achieves improved performance compared to MobileNetv3, which is an already optimized architecture.","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"5 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123470462","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: 5

IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels 基于动态伪标签的子域内自适应对抗学习分割方法

International Conference on Neural Information Processing Pub Date : 2022-10-07 DOI: 10.48550/arXiv.2210.03435

Xuewei Li, Weilun Zhang, Jie Gao, Xuzhou Fu, Jian Yu

{"title":"IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels","authors":"Xuewei Li, Weilun Zhang, Jie Gao, Xuzhou Fu, Jian Yu","doi":"10.48550/arXiv.2210.03435","DOIUrl":"https://doi.org/10.48550/arXiv.2210.03435","url":null,"abstract":"Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal. To this end, in this paper, Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels(IDPL) is proposed. The whole process consists of 3 steps: Firstly, the instance-level pseudo label dynamic generation module is proposed, which fuses the class matching information in global classes and local instances, thus adaptively generating the optimal threshold for each class, obtaining high-quality pseudo labels. Secondly, the subdomain classifier module based on instance confidence is constructed, which can dynamically divide the target domain into easy and difficult subdomains according to the relative proportion of easy and difficult instances. Finally, the subdomain adversarial learning module based on self-attention is proposed. It uses multi-head self-attention to confront the easy and difficult subdomains at the class level with the help of generated high-quality pseudo labels, so as to focus on mining the features of difficult categories in the high-entropy region of target domain images, which promotes class-level conditional distribution alignment between the subdomains, improving the segmentation performance of difficult categories. For the difficult categories, the experimental results show that the performance of IDPL is significantly improved compared with other latest mainstream methods.","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121723997","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

Double Attention-based Lightweight Network for Plant Pest Recognition 基于双关注的植物病虫害识别轻量级网络

International Conference on Neural Information Processing Pub Date : 2022-10-04 DOI: 10.48550/arXiv.2210.09956

Sivasubramaniam Janarthan, S. Thuseethan, S. Rajasegarar, J. Yearwood

引用次数: 0

Improving Document Image Understanding with Reinforcement Finetuning 增强微调提高文档图像理解能力

International Conference on Neural Information Processing Pub Date : 2022-09-26 DOI: 10.48550/arXiv.2209.12561

Bao-Sinh Nguyen, Dung Tien Le, Hieu M. Vu, Tuan-Anh Dang Nguyen, Minh Le Nguyen, Hung Le

引用次数: 0

A Deep Investigation of RNN and Self-attention for the Cyrillic-Traditional Mongolian Bidirectional Conversion 西里尔-传统蒙古语双向转换RNN与自关注的深入研究

International Conference on Neural Information Processing Pub Date : 2022-09-24 DOI: 10.48550/arXiv.2209.11963

Muhan Na, Rui Liu, Feilong, Guanglai Gao

{"title":"A Deep Investigation of RNN and Self-attention for the Cyrillic-Traditional Mongolian Bidirectional Conversion","authors":"Muhan Na, Rui Liu, Feilong, Guanglai Gao","doi":"10.48550/arXiv.2209.11963","DOIUrl":"https://doi.org/10.48550/arXiv.2209.11963","url":null,"abstract":"Cyrillic and Traditional Mongolian are the two main members of the Mongolian writing system. The Cyrillic-Traditional Mongolian Bidirectional Conversion (CTMBC) task includes two conversion processes, including Cyrillic Mongolian to Traditional Mongolian (C2T) and Traditional Mongolian to Cyrillic Mongolian conversions (T2C). Previous researchers adopted the traditional joint sequence model, since the CTMBC task is a natural Sequence-to-Sequence (Seq2Seq) modeling problem. Recent studies have shown that Recurrent Neural Network (RNN) and Self-attention (or Transformer) based encoder-decoder models have shown significant improvement in machine translation tasks between some major languages, such as Mandarin, English, French, etc. However, an open problem remains as to whether the CTMBC quality can be improved by utilizing the RNN and Transformer models. To answer this question, this paper investigates the utility of these two powerful techniques for CTMBC task combined with agglutinative characteristics of Mongolian language. We build the encoder-decoder based CTMBC model based on RNN and Transformer respectively and compare the different network configurations deeply. The experimental results show that both RNN and Transformer models outperform the traditional joint sequence model, where the Transformer achieves the best performance. Compared with the joint sequence baseline, the word error rate (WER) of the Transformer for C2T and T2C decreased by 5.72% and 5.06% respectively.","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123876798","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

Boosting Star-GANs for Voice Conversion with Contrastive Discriminator 基于对比鉴别器的增强star - gan语音转换

International Conference on Neural Information Processing Pub Date : 2022-09-21 DOI: 10.48550/arXiv.2209.10088

Shijing Si, Jianzong Wang, Xulong Zhang, Xiaoyang Qu, Ning Cheng, Jing Xiao

引用次数: 1