In this work, we propose a self-supervised multi-agent system, termed a memory-like adaptive modeling multi-agent learning system (MAMMALS), that realizes online learning towards behavioral pattern clustering tasks for time series. Encoding the visual behaviors as discrete time series(DTS), and training and modeling them in the multi-agent system with a bio-memory-like form. We finally implemented a fully decentralized multi-agent system design framework and completed its feasibility verification in a surveillance video application scenario on vehicle path clustering. In multi-agent learning, using learning methods designed for individual agents will typically perform poorly globally because of the behavior of ignoring the synergy between agents.
translated by 谷歌翻译
在非参数环境中,因果结构通常仅在马尔可夫等效性上可识别,并且出于因果推断的目的,学习马尔可夫等效类(MEC)的图形表示很有用。在本文中,我们重新审视了贪婪的等效搜索(GES)算法,该算法被广泛引用为一种基于分数的算法,用于学习基本因果结构的MEC。我们观察到,为了使GES算法在非参数设置中保持一致,不必设计评估图的评分度量。取而代之的是,足以插入有条件依赖度量的一致估计器来指导搜索。因此,我们提出了GES算法的重塑,该算法比基于标准分数的版本更灵活,并且很容易将自己带到非参数设置,并具有条件依赖性的一般度量。此外,我们提出了一种神经条件依赖性(NCD)度量,该措施利用深神经网络的表达能力以非参数方式表征条件独立性。我们根据标准假设建立了重新构架GES算法的最佳性,并使用我们的NCD估计器来决定条件独立性的一致性。这些结果共同证明了拟议的方法。实验结果证明了我们方法在因果发现中的有效性,以及使用我们的NCD度量而不是基于内核的措施的优势。
translated by 谷歌翻译
机器学习在数据通信网络中信息流动的动态分析的各种模型中获得了增长的势头。这些初步模型通常依赖于货架上的学习模型来预测历史统计,同时忽视管理这些流动的产生行为的物理。本文介绍了流动神经网络(FlONNN),以改善具有学习物理偏差的特征表示。这由在嵌入层上工作的感应层来实现,以施加物理连接的数据相关,以及具有停止梯度的自我监督的学习策略,以使学习的物理通用。对于短时间性的网络预测任务,Flownn实现了17% - 71%的损失减少,而不是合成和现实世界网络数据集的最先进的基线,这表明了这种新方法的强度。代码将可用。
translated by 谷歌翻译
$ \ texttt {gcastle} $是一个端到端Python工具箱,用于因果结构学习。它提供了从模拟器或现实世界数据集的生成数据,从数据学习因果结构的功能,以及评估学到的图表,以及有用的实践,例如先验知识插入,初步邻域选择和后处理以删除错误发现。与相关包相比,$ \ texttt {gcastle} $包括许多最近开发的基于渐变的因果发现方法,具有可选的GPU加速。$ \ texttt {gcastle} $为可以直接尝试代码以及具有图形用户干扰的从业者来为研究人员提供方便。当前版本也提供了电信中的三个现实世界数据集。$ \ texttt {gcastle} $可在Apache许可证2.0下获得\ url {https://github.com/huawei-noah/trustworthyai/tree/master/gcastle}。
translated by 谷歌翻译
我们介绍了一种组合变分AutiCencoders(VAE)和深度度量学习的方法,以通过高维和结构化输入空间执行贝叶斯优化(BO)。通过从深度度量学习中调整思路,我们使用BlackBox功能的标签指导来构建VAE潜在空间,促进高斯工艺拟合并产生改善的BO性能。重要的是,对于BO问题设置,我们的方法在半监督的制度中运行,其中只有少数标记的数据点。我们在三个现实世界任务中运行实验,在惩罚的LOGP分子生成基准上实现最先进的结果,只使用先前方法所需的标记数据的3%。作为一种理论贡献,我们提出了vae bo遗憾的证据。
translated by 谷歌翻译
本文提出了在适当的监督信息下进行分解的生成因果代表(亲爱的)学习方法。与实施潜在变量独立性的现有分解方法不同,我们考虑了一种基本利益因素可以因果关系相关的一般情况。我们表明,即使在监督下,先前具有独立先验的方法也无法解散因果关系。在这一发现的激励下,我们提出了一种称为DEAR的新的解开学习方法,该方法可以使因果可控的产生和因果代表学习。这种新公式的关键要素是使用结构性因果模型(SCM)作为双向生成模型的先验分布。然后,使用合适的GAN算法与发电机和编码器共同训练了先验,并与有关地面真相因子及其基本因果结构的监督信息合并。我们提供了有关该方法的可识别性和渐近收敛性的理论理由。我们对合成和真实数据集进行了广泛的实验,以证明DEAR在因果可控生成中的有效性,以及在样本效率和分布鲁棒性方面,学到的表示表示对下游任务的好处。
translated by 谷歌翻译
学习分离旨在寻找低维表示,该表示由观察数据的多个解释性和生成因素组成。变异自动编码器(VAE)的框架通常用于将独立因素从观察中解散。但是,在实际情况下,具有语义的因素不一定是独立的。取而代之的是,可能存在基本的因果结构,从而使这些因素取决于这些因素。因此,我们提出了一个名为Causalvae的新的基于VAE的框架,该框架包括一个因果层,将独立的外源性因子转化为因果内源性因素,这些因子与数据中的因果关系相关概念相对应。我们进一步分析了模型,表明从观测值中学到的拟议模型可以在一定程度上恢复真实的模型。实验是在各种数据集上进行的,包括合成和真实的基准Celeba。结果表明,因果关系学到的因果表示是可以解释的,并且其因果关系作为定向无环形图(DAG)的因果关系良好地鉴定出来。此外,我们证明了所提出的Causalvae模型能够通过因果因素的“操作”来生成反事实数据。
translated by 谷歌翻译
本文研究了从观察数据学习因果关系的问题。我们用二进制图邻接矩阵参数化的形式重整结构方程模型(SEM),并显示,如果原始SEM是可识别的,则可以识别二进制邻接矩阵到真实因果图的超图在温和的条件下。然后,我们利用所述重新设计的SEM来开发一种因果结构学习方法,可以通过利用对非循环性和Gumbel-Softmax方法的平滑表征来实现基于梯度的优化来有效地接受训练,以近似于二进制邻接矩阵。发现获得的条目通常在零或一个附近,并且可以容易地阈值以识别边缘。我们对合成和实时数据集进行实验,以验证所提出的方法的有效性,并表明它容易包括不同的平滑模型功能,并在考虑大多数数据集中实现了大大提高的性能。
translated by 谷歌翻译
The development of social media user stance detection and bot detection methods rely heavily on large-scale and high-quality benchmarks. However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research. To address these issues, we propose a Multi-Relational Graph-Based Twitter Account Detection Benchmark (MGTAB), the first standardized graph-based benchmark for account detection. To our knowledge, MGTAB was built based on the largest original data in the field, with over 1.55 million users and 130 million tweets. MGTAB contains 10,199 expert-annotated users and 7 types of relationships, ensuring high-quality annotation and diversified relations. In MGTAB, we extracted the 20 user property features with the greatest information gain and user tweet features as the user features. In addition, we performed a thorough evaluation of MGTAB and other public datasets. Our experiments found that graph-based approaches are generally more effective than feature-based approaches and perform better when introducing multiple relations. By analyzing experiment results, we identify effective approaches for account detection and provide potential future research directions in this field. Our benchmark and standardized evaluation procedures are freely available at: https://github.com/GraphDetec/MGTAB.
translated by 谷歌翻译
Interview has been regarded as one of the most crucial step for recruitment. To fully prepare for the interview with the recruiters, job seekers usually practice with mock interviews between each other. However, such a mock interview with peers is generally far away from the real interview experience: the mock interviewers are not guaranteed to be professional and are not likely to behave like a real interviewer. Due to the rapid growth of online recruitment in recent years, recruiters tend to have online interviews, which makes it possible to collect real interview data from real interviewers. In this paper, we propose a novel application named EZInterviewer, which aims to learn from the online interview data and provides mock interview services to the job seekers. The task is challenging in two ways: (1) the interview data are now available but still of low-resource; (2) to generate meaningful and relevant interview dialogs requires thorough understanding of both resumes and job descriptions. To address the low-resource challenge, EZInterviewer is trained on a very small set of interview dialogs. The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource. Evaluation results on a real-world job interview dialog dataset indicate that we achieve promising results to generate mock interviews. With the help of EZInterviewer, we hope to make mock interview practice become easier for job seekers.
translated by 谷歌翻译