首页 > 最新文献

IJCAI : proceedings of the conference最新文献

英文 中文
Transfer of Temporal Logic Formulas in Reinforcement Learning 时间逻辑公式在强化学习中的迁移
Pub Date : 2019-08-01 DOI: 10.24963/IJCAI.2019/557
Zhe Xu, U. Topcu
Transferring high-level knowledge from a source task to a target task is an effective way to expedite reinforcement learning (RL). For example, propositional logic and first-order logic have been used as representations of such knowledge. We study the transfer of knowledge between tasks in which the timing of the events matters. We call such tasks temporal tasks. We concretize similarity between temporal tasks through a notion of logical transferability, and develop a transfer learning approach between different yet similar temporal tasks. We first propose an inference technique to extract metric interval temporal logic (MITL) formulas in sequential disjunctive normal form from labeled trajectories collected in RL of the two tasks. If logical transferability is identified through this inference, we construct a timed automaton for each sequential conjunctive subformula of the inferred MITL formulas from both tasks. We perform RL on the extended state which includes the locations and clock valuations of the timed automata for the source task. We then establish mappings between the corresponding components (clocks, locations, etc.) of the timed automata from the two tasks, and transfer the extended Q-functions based on the established mappings. Finally, we perform RL on the extended state for the target task, starting with the transferred extended Q-functions. Our implementation results show, depending on how similar the source task and the target task are, that the sampling efficiency for the target task can be improved by up to one order of magnitude by performing RL in the extended state space, and further improved by up to another order of magnitude using the transferred extended Q-functions.
将高级知识从源任务转移到目标任务是加速强化学习(RL)的有效途径。例如,命题逻辑和一阶逻辑被用来表示这些知识。我们研究任务之间的知识转移,其中事件的时间很重要。我们称这类任务为临时任务。我们通过逻辑可转移性的概念将时间任务之间的相似性具体化,并在不同但相似的时间任务之间开发了一种迁移学习方法。我们首先提出了一种推理技术,从两个任务的RL中收集的标记轨迹中提取顺序析取范式的度量间隔时间逻辑(MITL)公式。如果通过这种推断确定了逻辑可转移性,我们为从两个任务推断出的MITL公式的每个顺序合取子公式构造一个时间自动机。我们对扩展状态执行强化学习,扩展状态包括源任务的时间自动机的位置和时钟值。然后,我们在两个任务的时间自动机的相应组件(时钟,位置等)之间建立映射,并在建立映射的基础上传递扩展的q函数。最后,我们从传递的扩展q函数开始,对目标任务的扩展状态执行强化学习。我们的实现结果表明,根据源任务和目标任务的相似程度,通过在扩展状态空间中执行RL,目标任务的采样效率可以提高一个数量级,并使用转移的扩展q函数进一步提高一个数量级。
{"title":"Transfer of Temporal Logic Formulas in Reinforcement Learning","authors":"Zhe Xu, U. Topcu","doi":"10.24963/IJCAI.2019/557","DOIUrl":"https://doi.org/10.24963/IJCAI.2019/557","url":null,"abstract":"Transferring high-level knowledge from a source task to a target task is an effective way to expedite reinforcement learning (RL). For example, propositional logic and first-order logic have been used as representations of such knowledge. We study the transfer of knowledge between tasks in which the timing of the events matters. We call such tasks temporal tasks. We concretize similarity between temporal tasks through a notion of logical transferability, and develop a transfer learning approach between different yet similar temporal tasks. We first propose an inference technique to extract metric interval temporal logic (MITL) formulas in sequential disjunctive normal form from labeled trajectories collected in RL of the two tasks. If logical transferability is identified through this inference, we construct a timed automaton for each sequential conjunctive subformula of the inferred MITL formulas from both tasks. We perform RL on the extended state which includes the locations and clock valuations of the timed automata for the source task. We then establish mappings between the corresponding components (clocks, locations, etc.) of the timed automata from the two tasks, and transfer the extended Q-functions based on the established mappings. Finally, we perform RL on the extended state for the target task, starting with the transferred extended Q-functions. Our implementation results show, depending on how similar the source task and the target task are, that the sampling efficiency for the target task can be improved by up to one order of magnitude by performing RL in the extended state space, and further improved by up to another order of magnitude using the transferred extended Q-functions.","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"19 1","pages":"4010-4018"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74383366","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: 42
Learning Disentangled Semantic Representation for Domain Adaptation 面向领域自适应的解纠缠语义表示学习
Pub Date : 2019-08-01 DOI: 10.24963/ijcai.2019/285
Ruichu Cai, Zijian Li, Pengfei Wei, Jie Qiao, Kun Zhang, Z. Hao
Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information. Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data. In DSR, we assume the data generation process is controlled by two independent sets of variables, i.e., the semantic latent variables and the domain latent variables. Under the above assumption, we employ a variational auto-encoder to reconstruct the semantic latent variables and domain latent variables behind the data. We further devise a dual adversarial network to disentangle these two sets of reconstructed latent variables. The disentangled semantic latent variables are finally adapted across the domains. Experimental studies testify that our model yields state-of-the-art performance on several domain adaptation benchmark datasets.
领域自适应是一项重要而富有挑战性的任务。现有的领域自适应方法大都存在领域信息与语义信息纠缠的问题,难以在特征空间上提取出领域不变的表示。与以往对纠缠特征空间的研究不同,我们的目标是在数据的潜在解纠缠语义表示(DSR)中提取领域不变的语义信息。在DSR中,我们假设数据生成过程由两组独立的变量控制,即语义潜变量和领域潜变量。在上述假设下,我们采用变分自编码器重构数据背后的语义潜变量和领域潜变量。我们进一步设计了一个对偶对抗网络来解开这两组重构的潜在变量。最后对解耦后的语义潜变量进行跨域适配。实验研究证明,我们的模型在几个领域自适应基准数据集上产生了最先进的性能。
{"title":"Learning Disentangled Semantic Representation for Domain Adaptation","authors":"Ruichu Cai, Zijian Li, Pengfei Wei, Jie Qiao, Kun Zhang, Z. Hao","doi":"10.24963/ijcai.2019/285","DOIUrl":"https://doi.org/10.24963/ijcai.2019/285","url":null,"abstract":"Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information. Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data. In DSR, we assume the data generation process is controlled by two independent sets of variables, i.e., the semantic latent variables and the domain latent variables. Under the above assumption, we employ a variational auto-encoder to reconstruct the semantic latent variables and domain latent variables behind the data. We further devise a dual adversarial network to disentangle these two sets of reconstructed latent variables. The disentangled semantic latent variables are finally adapted across the domains. Experimental studies testify that our model yields state-of-the-art performance on several domain adaptation benchmark datasets.","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"39 1","pages":"2060-2066"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80396367","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: 86
Learning Disentangled Semantic Representation for Domain Adaptation. 学习用于领域适应的分离语义表征
Ruichu Cai, Zijian Li, Pengfei Wei, Jie Qiao, Kun Zhang, Zhifeng Hao

Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information. Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data. In DSR, we assume the data generation process is controlled by two independent sets of variables, i.e., the semantic latent variables and the domain latent variables. Under the above assumption, we employ a variational auto-encoder to reconstruct the semantic latent variables and domain latent variables behind the data. We further devise a dual adversarial network to disentangle these two sets of reconstructed latent variables. The disentangled semantic latent variables are finally adapted across the domains. Experimental studies testify that our model yields state-of-the-art performance on several domain adaptation benchmark datasets.

领域适应是一项重要但极具挑战性的任务。现有的大多数领域适配方法都难以在具有纠缠领域信息和语义信息的特征空间上提取领域不变表示。与以往在纠缠特征空间上所做的努力不同,我们的目标是在数据的潜在非纠缠语义表示(DSR)中提取领域不变的语义信息。在 DSR 中,我们假设数据生成过程由两组独立的变量控制,即语义潜变量和领域潜变量。在上述假设下,我们采用变分自动编码器来重构数据背后的语义潜变量和领域潜变量。我们进一步设计了一个双对抗网络,以拆分这两组重建的潜变量。最后,被分解的语义潜变量将被跨域调整。实验研究证明,我们的模型在多个领域适应基准数据集上取得了一流的性能。
{"title":"Learning Disentangled Semantic Representation for Domain Adaptation.","authors":"Ruichu Cai, Zijian Li, Pengfei Wei, Jie Qiao, Kun Zhang, Zhifeng Hao","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information. Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data. In DSR, we assume the data generation process is controlled by two independent sets of variables, i.e., the semantic latent variables and the domain latent variables. Under the above assumption, we employ a variational auto-encoder to reconstruct the semantic latent variables and domain latent variables behind the data. We further devise a dual adversarial network to disentangle these two sets of reconstructed latent variables. The disentangled semantic latent variables are finally adapted across the domains. Experimental studies testify that our model yields state-of-the-art performance on several domain adaptation benchmark datasets.</p>","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"2019 ","pages":"2060-2066"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6759585/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141285567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Exploring Computational User Models for Agent Policy Summarization. 探索用于Agent策略总结的计算用户模型。
Isaac Lage, Daphna Lifschitz, Finale Doshi-Velez, Ofra Amir

AI agents support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey strengths and weaknesses of such agents by demonstrating their behavior in a subset of informative states. Some policy summarization methods extract a summary that optimizes the ability to reconstruct the agent's policy under the assumption that users will deploy inverse reinforcement learning. In this paper, we explore the use of different models for extracting summaries. We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance. Together, our results suggest that it is important to carefully consider user models in policy summarization.

人工智能代理支持高风险的决策过程,从驾驶汽车到开处方,这使得人类用户理解它们的行为变得越来越重要。策略总结方法旨在通过展示智能体在信息状态子集中的行为来传达这些智能体的优势和劣势。一些策略总结方法在假设用户将部署逆强化学习的情况下,提取一个优化智能体策略重构能力的总结。在本文中,我们探讨了使用不同的模型来提取摘要。我们引入了一种基于模仿学习的政策总结方法;我们通过计算模拟证明,用于提取摘要的模型与用于重建策略的模型之间的不匹配会导致较差的重建质量;我们通过一项以人为对象的研究证明,人们在不同的环境中使用不同的模型来重建策略,将摘要提取模型与这些模型相匹配可以提高性能。总之,我们的结果表明,在策略总结中仔细考虑用户模型是很重要的。
{"title":"Exploring Computational User Models for Agent Policy Summarization.","authors":"Isaac Lage,&nbsp;Daphna Lifschitz,&nbsp;Finale Doshi-Velez,&nbsp;Ofra Amir","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>AI agents support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey strengths and weaknesses of such agents by demonstrating their behavior in a subset of informative states. Some policy summarization methods extract a summary that optimizes the ability to reconstruct the agent's policy under the assumption that users will deploy inverse reinforcement learning. In this paper, we explore the use of different models for extracting summaries. We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance. Together, our results suggest that it is important to carefully consider user models in policy summarization.</p>","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"28 ","pages":"1401-1407"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7901848/pdf/nihms-1067306.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"25402383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Medical Concept Representation Learning from Multi-source Data. 从多源数据中学习医学概念表征
Pub Date : 2019-07-01 DOI: 10.24963/ijcai.2019/680
Tian Bai, Brian L Egleston, Richard Bleicher, Slobodan Vucetic

Representing words as low dimensional vectors is very useful in many natural language processing tasks. This idea has been extended to medical domain where medical codes listed in medical claims are represented as vectors to facilitate exploratory analysis and predictive modeling. However, depending on a type of a medical provider, medical claims can use medical codes from different ontologies or from a combination of ontologies, which complicates learning of the representations. To be able to properly utilize such multi-source medical claim data, we propose an approach that represents medical codes from different ontologies in the same vector space. We first modify the Pointwise Mutual Information (PMI) measure of similarity between the codes. We then develop a new negative sampling method for word2vec model that implicitly factorizes the modified PMI matrix. The new approach was evaluated on the code cross-reference problem, which aims at identifying similar codes across different ontologies. In our experiments, we evaluated cross-referencing between ICD-9 and CPT medical code ontologies. Our results indicate that vector representations of codes learned by the proposed approach provide superior cross-referencing when compared to several existing approaches.

在许多自然语言处理任务中,将单词表示为低维向量非常有用。这一想法已扩展到医疗领域,医疗索赔中列出的医疗代码被表示为向量,以促进探索性分析和预测建模。然而,根据医疗服务提供者的类型,医疗报销单可能使用来自不同本体或本体组合的医疗代码,这就使得表征的学习变得复杂。为了能够正确利用这种多源医疗索赔数据,我们提出了一种在同一向量空间中表示来自不同本体的医疗代码的方法。我们首先修改了代码间相似性的点式互信息(PMI)度量。然后,我们为 word2vec 模型开发了一种新的负采样方法,该方法可对修改后的 PMI 矩阵进行隐式因式分解。我们在代码交叉引用问题上对新方法进行了评估,该问题旨在识别不同本体中的相似代码。在实验中,我们评估了 ICD-9 和 CPT 医疗代码本体之间的交叉引用。我们的结果表明,与现有的几种方法相比,拟议方法学习的代码矢量表示提供了更优越的交叉引用效果。
{"title":"Medical Concept Representation Learning from Multi-source Data.","authors":"Tian Bai, Brian L Egleston, Richard Bleicher, Slobodan Vucetic","doi":"10.24963/ijcai.2019/680","DOIUrl":"10.24963/ijcai.2019/680","url":null,"abstract":"<p><p>Representing words as low dimensional vectors is very useful in many natural language processing tasks. This idea has been extended to medical domain where medical codes listed in medical claims are represented as vectors to facilitate exploratory analysis and predictive modeling. However, depending on a type of a medical provider, medical claims can use medical codes from different ontologies or from a combination of ontologies, which complicates learning of the representations. To be able to properly utilize such multi-source medical claim data, we propose an approach that represents medical codes from different ontologies in the same vector space. We first modify the Pointwise Mutual Information (PMI) measure of similarity between the codes. We then develop a new negative sampling method for word2vec model that implicitly factorizes the modified PMI matrix. The new approach was evaluated on the code cross-reference problem, which aims at identifying similar codes across different ontologies. In our experiments, we evaluated cross-referencing between ICD-9 and CPT medical code ontologies. Our results indicate that vector representations of codes learned by the proposed approach provide superior cross-referencing when compared to several existing approaches.</p>","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"2019 ","pages":"4897-4903"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7047512/pdf/nihms-1558151.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37693039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Exploring Computational User Models for Agent Policy Summarization 探索用于Agent策略总结的计算用户模型
Pub Date : 2019-05-01 DOI: 10.24963/ijcai.2019/194
Isaac Lage, Daphna Lifschitz, F. Doshi-Velez, Ofra Amir
AI agents support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey strengths and weaknesses of such agents by demonstrating their behavior in a subset of informative states. Some policy summarization methods extract a summary that optimizes the ability to reconstruct the agent's policy under the assumption that users will deploy inverse reinforcement learning. In this paper, we explore the use of different models for extracting summaries. We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance. Together, our results suggest that it is important to carefully consider user models in policy summarization.
人工智能代理支持高风险的决策过程,从驾驶汽车到开处方,这使得人类用户理解它们的行为变得越来越重要。策略总结方法旨在通过展示智能体在信息状态子集中的行为来传达这些智能体的优势和劣势。一些策略总结方法在假设用户将部署逆强化学习的情况下,提取一个优化智能体策略重构能力的总结。在本文中,我们探讨了使用不同的模型来提取摘要。我们引入了一种基于模仿学习的政策总结方法;我们通过计算模拟证明,用于提取摘要的模型与用于重建策略的模型之间的不匹配会导致较差的重建质量;我们通过一项以人为对象的研究证明,人们在不同的环境中使用不同的模型来重建策略,将摘要提取模型与这些模型相匹配可以提高性能。总之,我们的结果表明,在策略总结中仔细考虑用户模型是很重要的。
{"title":"Exploring Computational User Models for Agent Policy Summarization","authors":"Isaac Lage, Daphna Lifschitz, F. Doshi-Velez, Ofra Amir","doi":"10.24963/ijcai.2019/194","DOIUrl":"https://doi.org/10.24963/ijcai.2019/194","url":null,"abstract":"AI agents support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey strengths and weaknesses of such agents by demonstrating their behavior in a subset of informative states. Some policy summarization methods extract a summary that optimizes the ability to reconstruct the agent's policy under the assumption that users will deploy inverse reinforcement learning. In this paper, we explore the use of different models for extracting summaries. We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance. Together, our results suggest that it is important to carefully consider user models in policy summarization.","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"31 1","pages":"1401-1407"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82365179","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: 55
Hierarchical Active Learning with Group Proportion Feedback. 基于群体比例反馈的分层主动学习。
Pub Date : 2018-07-01 DOI: 10.24963/ijcai.2018/351
Zhipeng Luo, Milos Hauskrecht

Learning of classification models in practice often relies on nontrivial human annotation effort in which humans assign class labels to data instances. As this process can be very time consuming and costly, finding effective ways to reduce the annotation cost becomes critical for building such models. In this work we solve this problem by exploring a new approach that actively learns classification models from groups, which are subpopulations of instances, and human feedback on the groups. Each group is labeled with a number in [0,1] interval representing a human estimate of the proportion of instances with one of the class labels in this subpopulation. To form the groups to be annotated, we develop a hierarchical active learning framework that divides the whole population into smaller subpopulations, which allows us to gradually learn more refined models from the subpopulations and their class proportion labels. Our extensive experiments on numerous datasets show that our method is competitive and outperforms existing approaches for reducing the human annotation cost.

在实践中,分类模型的学习通常依赖于人类的大量注释工作,其中人类将类标签分配给数据实例。由于此过程非常耗时且成本高昂,因此找到降低注释成本的有效方法对于构建此类模型至关重要。在这项工作中,我们通过探索一种新的方法来解决这个问题,该方法主动地从组中学习分类模型,组是实例的子种群,以及人类对组的反馈。每一组都用[0,1]区间内的一个数字来标记,这个数字表示人类对该子群体中具有其中一个类标签的实例的比例的估计。为了形成要注释的组,我们开发了一个分层主动学习框架,将整个种群划分为更小的子种群,这使我们能够从子种群及其类比例标签中逐渐学习更精细的模型。我们在大量数据集上的广泛实验表明,我们的方法在降低人工注释成本方面具有竞争力,并且优于现有的方法。
{"title":"Hierarchical Active Learning with Group Proportion Feedback.","authors":"Zhipeng Luo,&nbsp;Milos Hauskrecht","doi":"10.24963/ijcai.2018/351","DOIUrl":"https://doi.org/10.24963/ijcai.2018/351","url":null,"abstract":"<p><p>Learning of classification models in practice often relies on nontrivial human annotation effort in which humans assign class labels to data instances. As this process can be very time consuming and costly, finding effective ways to reduce the annotation cost becomes critical for building such models. In this work we solve this problem by exploring a new approach that actively learns classification models from groups, which are subpopulations of instances, and human feedback on the groups. Each group is labeled with a number in [0,1] interval representing a human estimate of the proportion of instances with one of the class labels in this subpopulation. To form the groups to be annotated, we develop a hierarchical active learning framework that divides the whole population into smaller subpopulations, which allows us to gradually learn more refined models from the subpopulations and their class proportion labels. Our extensive experiments on numerous datasets show that our method is competitive and outperforms existing approaches for reducing the human annotation cost.</p>","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"2018 ","pages":"2532-2538"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6258042/pdf/nihms967729.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36721463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
Relatedness-based Multi-Entity Summarization. 基于关联的多实体摘要。
Pub Date : 2017-08-01 DOI: 10.24963/ijcai.2017/147
Kalpa Gunaratna, Amir Hossein Yazdavar, Krishnaprasad Thirunarayan, Amit Sheth, Gong Cheng

Representing world knowledge in a machine processable format is important as entities and their descriptions have fueled tremendous growth in knowledge-rich information processing platforms, services, and systems. Prominent applications of knowledge graphs include search engines (e.g., Google Search and Microsoft Bing), email clients (e.g., Gmail), and intelligent personal assistants (e.g., Google Now, Amazon Echo, and Apple's Siri). In this paper, we present an approach that can summarize facts about a collection of entities by analyzing their relatedness in preference to summarizing each entity in isolation. Specifically, we generate informative entity summaries by selecting: (i) inter-entity facts that are similar and (ii) intra-entity facts that are important and diverse. We employ a constrained knapsack problem solving approach to efficiently compute entity summaries. We perform both qualitative and quantitative experiments and demonstrate that our approach yields promising results compared to two other stand-alone state-of-the-art entity summarization approaches.

以机器可处理的格式表示世界知识是很重要的,因为实体及其描述推动了知识丰富的信息处理平台、服务和系统的巨大增长。知识图谱的主要应用包括搜索引擎(如谷歌搜索和微软必应)、电子邮件客户端(如Gmail)和智能个人助理(如谷歌Now、亚马逊Echo和苹果Siri)。在本文中,我们提出了一种方法,可以通过分析实体的相关性来总结关于实体集合的事实,而不是孤立地总结每个实体。具体而言,我们通过选择:(i)相似的实体间事实和(ii)重要且多样化的实体内事实来生成信息丰富的实体摘要。我们采用一种约束背包问题求解方法来有效地计算实体摘要。我们进行了定性和定量实验,并证明与其他两种独立的最先进的实体总结方法相比,我们的方法产生了有希望的结果。
{"title":"Relatedness-based Multi-Entity Summarization.","authors":"Kalpa Gunaratna,&nbsp;Amir Hossein Yazdavar,&nbsp;Krishnaprasad Thirunarayan,&nbsp;Amit Sheth,&nbsp;Gong Cheng","doi":"10.24963/ijcai.2017/147","DOIUrl":"https://doi.org/10.24963/ijcai.2017/147","url":null,"abstract":"<p><p>Representing world knowledge in a machine processable format is important as entities and their descriptions have fueled tremendous growth in knowledge-rich information processing platforms, services, and systems. Prominent applications of knowledge graphs include search engines (e.g., Google Search and Microsoft Bing), email clients (e.g., Gmail), and intelligent personal assistants (e.g., Google Now, Amazon Echo, and Apple's Siri). In this paper, we present an approach that can summarize facts about a collection of entities by analyzing their relatedness in preference to summarizing each entity in isolation. Specifically, we generate informative entity summaries by selecting: (i) inter-entity facts that are similar and (ii) intra-entity facts that are important and diverse. We employ a constrained knapsack problem solving approach to efficiently compute entity summaries. We perform both qualitative and quantitative experiments and demonstrate that our approach yields promising results compared to two other stand-alone state-of-the-art entity summarization approaches.</p>","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"2017 ","pages":"1060-1066"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5644492/pdf/nihms911351.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35532066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 15
Predicting Alzheimer's Disease Cognitive Assessment via Robust Low-Rank Structured Sparse Model. 基于鲁棒低秩结构稀疏模型的阿尔茨海默病认知评估预测。
Pub Date : 2017-08-01 DOI: 10.24963/ijcai.2017/542
Jie Xu, Cheng Deng, Xinbo Gao, Dinggang Shen, Heng Huang

Alzheimer's disease (AD) is a neurodegenerative disorder with slow onset, which could result in the deterioration of the duration of persistent neurological dysfunction. How to identify the informative longitudinal phenotypic neuroimaging markers and predict cognitive measures are crucial to recognize AD at early stage. Many existing models related imaging measures to cognitive status using regression models, but they did not take full consideration of the interaction between cognitive scores. In this paper, we propose a robust low-rank structured sparse regression method (RLSR) to address this issue. The proposed model simultaneously selects effective features and learns the underlying structure between cognitive scores by utilizing novel mixed structured sparsity inducing norms and low-rank approximation. In addition, an efficient algorithm is derived to solve the proposed non-smooth objective function with proved convergence. Empirical studies on cognitive data of the ADNI cohort demonstrate the superior performance of the proposed method.

阿尔茨海默病(AD)是一种发病缓慢的神经退行性疾病,可导致持续性神经功能障碍持续时间的恶化。如何识别信息丰富的纵向表型神经影像学标志物并预测认知措施是早期识别AD的关键。现有的许多模型使用回归模型将影像学测量与认知状态联系起来,但没有充分考虑认知评分之间的相互作用。在本文中,我们提出了一种鲁棒低秩结构化稀疏回归方法(RLSR)来解决这个问题。该模型利用新颖的混合结构稀疏性诱导规范和低秩近似,在选择有效特征的同时学习认知分数之间的底层结构。在此基础上,推导了求解非光滑目标函数的有效算法,并证明了算法的收敛性。对ADNI队列认知数据的实证研究证明了该方法的优越性能。
{"title":"Predicting Alzheimer's Disease Cognitive Assessment via Robust Low-Rank Structured Sparse Model.","authors":"Jie Xu,&nbsp;Cheng Deng,&nbsp;Xinbo Gao,&nbsp;Dinggang Shen,&nbsp;Heng Huang","doi":"10.24963/ijcai.2017/542","DOIUrl":"https://doi.org/10.24963/ijcai.2017/542","url":null,"abstract":"<p><p>Alzheimer's disease (AD) is a neurodegenerative disorder with slow onset, which could result in the deterioration of the duration of persistent neurological dysfunction. How to identify the informative longitudinal phenotypic neuroimaging markers and predict cognitive measures are crucial to recognize AD at early stage. Many existing models related imaging measures to cognitive status using regression models, but they did not take full consideration of the interaction between cognitive scores. In this paper, we propose a robust low-rank structured sparse regression method (RLSR) to address this issue. The proposed model simultaneously selects effective features and learns the underlying structure between cognitive scores by utilizing novel mixed structured sparsity inducing norms and low-rank approximation. In addition, an efficient algorithm is derived to solve the proposed non-smooth objective function with proved convergence. Empirical studies on cognitive data of the ADNI cohort demonstrate the superior performance of the proposed method.</p>","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"2017 ","pages":"3880-3886"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.24963/ijcai.2017/542","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36031641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 17
Causal Discovery from Nonstationary/Heterogeneous Data: Skeleton Estimation and Orientation Determination. 从非稳态/异构数据中发现因果关系:骨架估计与方向确定
Pub Date : 2017-08-01 DOI: 10.24963/ijcai.2017/187
Kun Zhang, Biwei Huang, Jiji Zhang, Clark Glymour, Bernhard Schölkopf

It is commonplace to encounter nonstationary or heterogeneous data, of which the underlying generating process changes over time or across data sets (the data sets may have different experimental conditions or data collection conditions). Such a distribution shift feature presents both challenges and opportunities for causal discovery. In this paper we develop a principled framework for causal discovery from such data, called Constraint-based causal Discovery from Nonstationary/heterogeneous Data (CD-NOD), which addresses two important questions. First, we propose an enhanced constraint-based procedure to detect variables whose local mechanisms change and recover the skeleton of the causal structure over observed variables. Second, we present a way to determine causal orientations by making use of independence changes in the data distribution implied by the underlying causal model, benefiting from information carried by changing distributions. Experimental results on various synthetic and real-world data sets are presented to demonstrate the efficacy of our methods.

非平稳或异质数据是司空见惯的现象,其基本生成过程会随时间或数据集的变化而变化(数据集可能具有不同的实验条件或数据收集条件)。这种分布变化特征既是因果发现的挑战,也是机遇。在本文中,我们开发了一个从此类数据中发现因果关系的原则性框架,称为基于约束的非平稳/异构数据因果关系发现(CD-NOD),它解决了两个重要问题。首先,我们提出了一种基于约束的增强程序,用于检测局部机制发生变化的变量,并恢复观测变量的因果结构骨架。其次,我们提出了一种利用底层因果模型所隐含的数据分布的独立性变化来确定因果方向的方法,从而从分布变化所携带的信息中获益。我们展示了各种合成数据集和真实世界数据集的实验结果,以证明我们方法的有效性。
{"title":"Causal Discovery from Nonstationary/Heterogeneous Data: Skeleton Estimation and Orientation Determination.","authors":"Kun Zhang, Biwei Huang, Jiji Zhang, Clark Glymour, Bernhard Schölkopf","doi":"10.24963/ijcai.2017/187","DOIUrl":"10.24963/ijcai.2017/187","url":null,"abstract":"<p><p>It is commonplace to encounter nonstationary or heterogeneous data, of which the underlying generating process changes over time or across data sets (the data sets may have different experimental conditions or data collection conditions). Such a distribution shift feature presents both challenges and opportunities for causal discovery. In this paper we develop a principled framework for causal discovery from such data, called Constraint-based causal Discovery from Nonstationary/heterogeneous Data (CD-NOD), which addresses two important questions. First, we propose an enhanced constraint-based procedure to detect variables whose local mechanisms change and recover the skeleton of the causal structure over observed variables. Second, we present a way to determine causal orientations by making use of independence changes in the data distribution implied by the underlying causal model, benefiting from information carried by changing distributions. Experimental results on various synthetic and real-world data sets are presented to demonstrate the efficacy of our methods.</p>","PeriodicalId":73334,"journal":{"name":"IJCAI : proceedings of the conference","volume":"2017 ","pages":"1347-1353"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5617646/pdf/nihms904880.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35461829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
IJCAI : proceedings of the conference
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1