Pub Date : 2024-02-25DOI: 10.1007/978-981-99-7019-3_3
Karen Frilya Celine, M. A. Dzulfikar, Ivan Koswara
{"title":"Egalitarian Price of Fairness for Indivisible Goods","authors":"Karen Frilya Celine, M. A. Dzulfikar, Ivan Koswara","doi":"10.1007/978-981-99-7019-3_3","DOIUrl":"https://doi.org/10.1007/978-981-99-7019-3_3","url":null,"abstract":"","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"26 11","pages":"23-28"},"PeriodicalIF":0.0,"publicationDate":"2024-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140433156","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}
{"title":"CANAMRF: An Attention-Based Model for Multimodal Depression Detection","authors":"Yuntao Wei, Yuzhe Zhang, Shuyang Zhang, Hone Zhang","doi":"10.1007/978-981-99-7022-3_10","DOIUrl":"https://doi.org/10.1007/978-981-99-7022-3_10","url":null,"abstract":"","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"37 11","pages":"111-116"},"PeriodicalIF":0.0,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139450759","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}
Pub Date : 2022-10-22DOI: 10.48550/arXiv.2210.12348
Yanjun Qi, Han Sun, Ningzhong Liu, Huiyu Zhou
The goal of fine-grained few-shot learning is to recognize sub-categories under the same super-category by learning few labeled samples. Most of the recent approaches adopt a single similarity measure, that is, global or local measure alone. However, for fine-grained images with high intra-class variance and low inter-class variance, exploring global invariant features and discriminative local details is quite essential. In this paper, we propose a Task-aware Dual Similarity Network(TDSNet), which applies global features and local patches to achieve better performance. Specifically, a local feature enhancement module is adopted to activate the features with strong discriminability. Besides, task-aware attention exploits the important patches among the entire task. Finally, both the class prototypes obtained by global features and discriminative local patches are employed for prediction. Extensive experiments on three fine-grained datasets demonstrate that the proposed TDSNet achieves competitive performance by comparing with other state-of-the-art algorithms.
{"title":"A Task-aware Dual Similarity Network for Fine-grained Few-shot Learning","authors":"Yanjun Qi, Han Sun, Ningzhong Liu, Huiyu Zhou","doi":"10.48550/arXiv.2210.12348","DOIUrl":"https://doi.org/10.48550/arXiv.2210.12348","url":null,"abstract":"The goal of fine-grained few-shot learning is to recognize sub-categories under the same super-category by learning few labeled samples. Most of the recent approaches adopt a single similarity measure, that is, global or local measure alone. However, for fine-grained images with high intra-class variance and low inter-class variance, exploring global invariant features and discriminative local details is quite essential. In this paper, we propose a Task-aware Dual Similarity Network(TDSNet), which applies global features and local patches to achieve better performance. Specifically, a local feature enhancement module is adopted to activate the features with strong discriminability. Besides, task-aware attention exploits the important patches among the entire task. Finally, both the class prototypes obtained by global features and discriminative local patches are employed for prediction. Extensive experiments on three fine-grained datasets demonstrate that the proposed TDSNet achieves competitive performance by comparing with other state-of-the-art algorithms.","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125457096","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}
Pub Date : 2022-10-05DOI: 10.48550/arXiv.2210.08971
H. Zhang, Chenyang Bu, Fei-Tsung Liu, Shuochen Liu, Yuhong Zhang, Xuegang Hu
Knowledge tracing (KT) is a fundamental task in educational data mining that mainly focuses on students' dynamic cognitive states of skills. The question-answering process of students can be regarded as a thinking process that considers the following two problems. One problem is which skills are needed to answer the question, and the other is how to use these skills in order. If a student wants to answer a question correctly, the student should not only master the set of skills involved in the question but also think and obtain the associative path on the skills graph. The nodes in the associative path refer to the skills needed and the path shows the order of using them. The associative path is referred to as the skill mode. Thus, obtaining the skill modes is the key to answering questions successfully. However, most existing KT models only focus on a set of skills, without considering the skill modes. We propose a KT model, called APGKT, that exploits skill modes. Specifically, we extract the subgraph topology of the skills involved in the question and combine the difficulty level of the skills to obtain the skill modes via encoding; then, through multi-layer recurrent neural networks, we obtain a student's higher-order cognitive states of skills, which is used to predict the student's future answering performance. Experiments on five benchmark datasets validate the effectiveness of the proposed model.
{"title":"APGKT: Exploiting Associative Path on Skills Graph for Knowledge Tracing","authors":"H. Zhang, Chenyang Bu, Fei-Tsung Liu, Shuochen Liu, Yuhong Zhang, Xuegang Hu","doi":"10.48550/arXiv.2210.08971","DOIUrl":"https://doi.org/10.48550/arXiv.2210.08971","url":null,"abstract":"Knowledge tracing (KT) is a fundamental task in educational data mining that mainly focuses on students' dynamic cognitive states of skills. The question-answering process of students can be regarded as a thinking process that considers the following two problems. One problem is which skills are needed to answer the question, and the other is how to use these skills in order. If a student wants to answer a question correctly, the student should not only master the set of skills involved in the question but also think and obtain the associative path on the skills graph. The nodes in the associative path refer to the skills needed and the path shows the order of using them. The associative path is referred to as the skill mode. Thus, obtaining the skill modes is the key to answering questions successfully. However, most existing KT models only focus on a set of skills, without considering the skill modes. We propose a KT model, called APGKT, that exploits skill modes. Specifically, we extract the subgraph topology of the skills involved in the question and combine the difficulty level of the skills to obtain the skill modes via encoding; then, through multi-layer recurrent neural networks, we obtain a student's higher-order cognitive states of skills, which is used to predict the student's future answering performance. Experiments on five benchmark datasets validate the effectiveness of the proposed model.","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127748502","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}
Pub Date : 2022-09-05DOI: 10.48550/arXiv.2209.01728
Peiwang Tang, Xianchao Zhang
Some data from multiple sources can be modeled as multimodal time-series events which have different sampling frequencies, data compositions, temporal relations and characteristics. Different types of events have complex nonlinear relationships, and the time of each event is irregular. Neither the classical Recurrent Neural Network (RNN) model nor the current state-of-the-art Transformer model can deal with these features well. In this paper, a features fusion framework for multimodal irregular time-series events is proposed based on the Long Short-Term Memory networks (LSTM). Firstly, the complex features are extracted according to the irregular patterns of different events. Secondly, the nonlinear correlation and complex temporal dependencies relationship between complex features are captured and fused into a tensor. Finally, a feature gate are used to control the access frequency of different tensors. Extensive experiments on MIMIC-III dataset demonstrate that the proposed framework significantly outperforms to the existing methods in terms of AUC (the area under Receiver Operating Characteristic curve) and AP (Average Precision).
{"title":"Features Fusion Framework for Multimodal Irregular Time-series Events","authors":"Peiwang Tang, Xianchao Zhang","doi":"10.48550/arXiv.2209.01728","DOIUrl":"https://doi.org/10.48550/arXiv.2209.01728","url":null,"abstract":"Some data from multiple sources can be modeled as multimodal time-series events which have different sampling frequencies, data compositions, temporal relations and characteristics. Different types of events have complex nonlinear relationships, and the time of each event is irregular. Neither the classical Recurrent Neural Network (RNN) model nor the current state-of-the-art Transformer model can deal with these features well. In this paper, a features fusion framework for multimodal irregular time-series events is proposed based on the Long Short-Term Memory networks (LSTM). Firstly, the complex features are extracted according to the irregular patterns of different events. Secondly, the nonlinear correlation and complex temporal dependencies relationship between complex features are captured and fused into a tensor. Finally, a feature gate are used to control the access frequency of different tensors. Extensive experiments on MIMIC-III dataset demonstrate that the proposed framework significantly outperforms to the existing methods in terms of AUC (the area under Receiver Operating Characteristic curve) and AP (Average Precision).","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"155 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114767886","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}
Estimating the average treatment effect (ATE) from observational data is challenging due to selection bias. Existing works mainly tackle this challenge in two ways. Some researchers propose constructing a score function that satisfies the orthogonal condition, which guarantees that the established ATE estimator is"orthogonal"to be more robust. The others explore representation learning models to achieve a balanced representation between the treated and the controlled groups. However, existing studies fail to 1) discriminate treated units from controlled ones in the representation space to avoid the over-balanced issue; 2) fully utilize the"orthogonality information". In this paper, we propose a moderately-balanced representation learning (MBRL) framework based on recent covariates balanced representation learning methods and orthogonal machine learning theory. This framework protects the representation from being over-balanced via multi-task learning. Simultaneously, MBRL incorporates the noise orthogonality information in the training and validation stages to achieve a better ATE estimation. The comprehensive experiments on benchmark and simulated datasets show the superiority and robustness of our method on treatment effect estimations compared with existing state-of-the-art methods.
{"title":"Moderately-Balanced Representation Learning for Treatment Effects with Orthogonality Information","authors":"Yiyan Huang, Cheuk Hang Leung, Shumin Ma, Qi Wu, Dongdong Wang, Zhixiang Huang","doi":"10.48550/arXiv.2209.01956","DOIUrl":"https://doi.org/10.48550/arXiv.2209.01956","url":null,"abstract":"Estimating the average treatment effect (ATE) from observational data is challenging due to selection bias. Existing works mainly tackle this challenge in two ways. Some researchers propose constructing a score function that satisfies the orthogonal condition, which guarantees that the established ATE estimator is\"orthogonal\"to be more robust. The others explore representation learning models to achieve a balanced representation between the treated and the controlled groups. However, existing studies fail to 1) discriminate treated units from controlled ones in the representation space to avoid the over-balanced issue; 2) fully utilize the\"orthogonality information\". In this paper, we propose a moderately-balanced representation learning (MBRL) framework based on recent covariates balanced representation learning methods and orthogonal machine learning theory. This framework protects the representation from being over-balanced via multi-task learning. Simultaneously, MBRL incorporates the noise orthogonality information in the training and validation stages to achieve a better ATE estimation. The comprehensive experiments on benchmark and simulated datasets show the superiority and robustness of our method on treatment effect estimations compared with existing state-of-the-art methods.","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130603299","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}
Pub Date : 2021-11-01DOI: 10.1007/978-3-030-89363-7_20
Dinh-Truong Do, Nguyen Ha Thanh, Thang Bui, Dinh-Hieu Vo
{"title":"VSEC: Transformer-based Model for Vietnamese Spelling Correction","authors":"Dinh-Truong Do, Nguyen Ha Thanh, Thang Bui, Dinh-Hieu Vo","doi":"10.1007/978-3-030-89363-7_20","DOIUrl":"https://doi.org/10.1007/978-3-030-89363-7_20","url":null,"abstract":"","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"64 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127895594","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}
Pub Date : 2021-10-17DOI: 10.1007/978-3-030-89370-5_22
Qing Yuan, Songfeng Lu, Yan Huang, Wuxin Sha
{"title":"SIN: Superpixel Interpolation Network","authors":"Qing Yuan, Songfeng Lu, Yan Huang, Wuxin Sha","doi":"10.1007/978-3-030-89370-5_22","DOIUrl":"https://doi.org/10.1007/978-3-030-89370-5_22","url":null,"abstract":"","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122386958","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}
Pub Date : 2021-10-16DOI: 10.1007/978-3-031-20868-3_30
Zihang Wan
{"title":"Multi-View Stereo Network with attention thin volume","authors":"Zihang Wan","doi":"10.1007/978-3-031-20868-3_30","DOIUrl":"https://doi.org/10.1007/978-3-031-20868-3_30","url":null,"abstract":"","PeriodicalId":272217,"journal":{"name":"Pacific Rim International Conference on Artificial Intelligence","volume":"2006 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127636039","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：