The click-through rate (CTR) prediction task is to predict whether a user will click on the recommended item. As mind-boggling amounts of data are produced online daily, accelerating CTR prediction model training is critical to ensuring an up-to-date model and reducing the training cost. One approach to increase the training speed is to apply large batch training. However, as shown in computer vision and natural language processing tasks, training with a large batch easily suffers from the loss of accuracy. Our experiments show that previous scaling rules fail in the training of CTR prediction neural networks. To tackle this problem, we first theoretically show that different frequencies of ids make it challenging to scale hyperparameters when scaling the batch size. To stabilize the training process in a large batch size setting, we develop the adaptive Column-wise Clipping (CowClip). It enables an easy and effective scaling rule for the embeddings, which keeps the learning rate unchanged and scales the L2 loss. We conduct extensive experiments with four CTR prediction networks on two real-world datasets and successfully scaled 128 times the original batch size without accuracy loss. In particular, for CTR prediction model DeepFM training on the Criteo dataset, our optimization framework enlarges the batch size from 1K to 128K with over 0.1% AUC improvement and reduces training time from 12 hours to 10 minutes on a single V100 GPU. Our code locates at https://github.com/bytedance/LargeBatchCTR.
translated by 谷歌翻译
盒子监督的实例分割最近吸引了大量的研究工作,而在空中图像域中则收到很少的关注。与通用物体集合相比,空中对象具有大型内部差异和阶级相似性与复杂的背景。此外,高分辨率卫星图像中存在许多微小的物体。这使得最近的一对亲和力建模方法不可避免地涉及具有劣势的噪声监督。为了解决这些问题,我们提出了一种新颖的空中实例分割方法,该方法驱动网络为空中对象的一系列级别设置功能,只有盒子注释以端到端的方式。具有精心设计的能量函数的级别集方法而不是学习成对亲和力将对象分段视为曲线演进,这能够准确地恢复对象的边界并防止来自无法区分的背景和类似对象的干扰。实验结果表明,所提出的方法优于最先进的盒子监督实例分段方法。源代码可在https://github.com/liwentomng/boxLevelset上获得。
translated by 谷歌翻译
In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC). In brief, on the one hand, due to the poor recognizability and viewpoint differences between images, it is inevitable to inaccurately annotate some keypoints with offset and confusion, leading to the mismatch between two associated nodes, i.e., NNC. On the other hand, the noisy node-to-node correspondence will further contaminate the edge-to-edge correspondence, thus leading to ENC. For the BNC challenge, we propose a novel method termed Contrastive Matching with Momentum Distillation. Specifically, the proposed method is with a robust quadratic contrastive loss which enjoys the following merits: i) better exploring the node-to-node and edge-to-edge correlations through a GM customized quadratic contrastive learning paradigm; ii) adaptively penalizing the noisy assignments based on the confidence estimated by the momentum teacher. Extensive experiments on three real-world datasets show the robustness of our model compared with 12 competitive baselines.
translated by 谷歌翻译
In terms of artificial intelligence, there are several security and privacy deficiencies in the traditional centralized training methods of machine learning models by a server. To address this limitation, federated learning (FL) has been proposed and is known for breaking down ``data silos" and protecting the privacy of users. However, FL has not yet gained popularity in the industry, mainly due to its security, privacy, and high cost of communication. For the purpose of advancing the research in this field, building a robust FL system, and realizing the wide application of FL, this paper sorts out the possible attacks and corresponding defenses of the current FL system systematically. Firstly, this paper briefly introduces the basic workflow of FL and related knowledge of attacks and defenses. It reviews a great deal of research about privacy theft and malicious attacks that have been studied in recent years. Most importantly, in view of the current three classification criteria, namely the three stages of machine learning, the three different roles in federated learning, and the CIA (Confidentiality, Integrity, and Availability) guidelines on privacy protection, we divide attack approaches into two categories according to the training stage and the prediction stage in machine learning. Furthermore, we also identify the CIA property violated for each attack method and potential attack role. Various defense mechanisms are then analyzed separately from the level of privacy and security. Finally, we summarize the possible challenges in the application of FL from the aspect of attacks and defenses and discuss the future development direction of FL systems. In this way, the designed FL system has the ability to resist different attacks and is more secure and stable.
translated by 谷歌翻译
暴露于霉菌孢子和花粉等生物 - 大紫胶会导致不利的健康影响。需要一种便携式且具有成本效益的设备来长期监测和量化各种生物紫胶。为了满足这一需求,我们提出了一种移动性和成本效益的无标签生物透射剂传感器,该传感器拍摄了由虚拟撞击器集中的流动颗粒物的全息图像,该图像有选择地放慢速度,并引导颗粒大于6微米,以飞过大于6微米成像窗口。流动的颗粒被脉冲激光二极管照亮,在无镜头移动成像设备中的CMOS图像传感器上施放了其内联全息图。该照明包含三个短脉冲,在一个脉冲中流动粒子可以忽略不计,同一粒子的一式三份全息图记录在单个框架上,然后才退出成像视野视野,从而揭示了每个粒子的不同视角。虚拟撞击器中的颗粒通过差异检测方案进行定位,并且深层神经网络基于获得的全息图像,以无标签的方式对气溶胶类型进行了分类。我们使用不同类型的花粉(即,百慕大,榆树,橡树,松树,小麦和小麦)使用虚拟撞击器证明了这种移动生物 - 大气探测器的成功,并实现了92.91%的盲目分类精度。这种移动性和成本效益的设备重约700 g,可用于长时间对各种生物透气体的无标记感应和量化,因为它基于无弹药的虚拟撞击器,该虚拟撞击器不会捕获或固定颗粒物。
translated by 谷歌翻译
背景和目标:现有的医学图像分割的深度学习平台主要集中于完全监督的细分,该分段假设可以使用充分而准确的像素级注释。我们旨在开发一种新的深度学习工具包,以支持对医学图像分割的注释有效学习,该学习可以加速并简单地开发具有有限注释预算的深度学习模型,例如,从部分,稀疏或嘈杂的注释中学习。方法:我们提出的名为Pymic的工具包是用于医学图像分割任务的模块化深度学习平台。除了支持开发高性能模型以进行全面监督分割的基本组件外,它还包含几个高级组件,这些高级组件是针对从不完善的注释中学习的几个高级组件,例如加载带注释和未经通知的图像,未经通知的,部分或无效的注释图像的损失功能,以及多个网络之间共同学习的培训程序。Pymic构建了Pytorch框架,并支持半监督,弱监督和噪声的学习方法用于医学图像分割。结果:我们介绍了基于PYMIC的四个说明性医学图像细分任务:(1)在完全监督的学习上实现竞争性能; (2)半监督心脏结构分割,只有10%的训练图像; (3)使用涂鸦注释弱监督的分割; (4)从嘈杂的标签中学习以进行胸部X光片分割。结论:Pymic工具包易于使用,并促进具有不完美注释的医学图像分割模型的有效开发。它是模块化和灵活的,它使研究人员能够开发出低注释成本的高性能模型。源代码可在以下网址获得:https://github.com/hilab-git/pymic。
translated by 谷歌翻译
无监督的时间序列异常检测对各种域中目标系统的潜在故障有助于。当前的最新时间序列异常检测器主要集中于设计高级神经网络结构和新的重建/预测学习目标,以尽可能准确地学习数据正常(正常模式和行为)。但是,这些单级学习方法可以被训练数据中未知异常(即异常污染)所欺骗。此外,他们的正常学习也缺乏对感兴趣异常的知识。因此,他们经常学习一个有偏见的,不准确的正态边界。本文提出了一种新型的单级学习方法,称为校准的一级分类,以解决此问题。我们的单级分类器以两种方式进行校准:(1)通过适应性地惩罚不确定的预测,这有助于消除异常污染的影响,同时强调单级模型对一级模型有信心的预测,并通过区分正常情况来确定(2)来自本机异常示例的样本,这些样本是根据原始数据基于原始数据模拟真实时间序列异常行为的。这两个校准导致耐污染的,异常的单级学习,从而产生了显着改善的正态性建模。对六个现实世界数据集进行的广泛实验表明,我们的模型大大优于12个最先进的竞争对手,并获得了6%-31%的F1分数提高。源代码可在\ url {https://github.com/xuhongzuo/couta}中获得。
translated by 谷歌翻译
Meta强化学习(META-RL)旨在学习一项政策,同时并迅速适应新任务。它需要大量从培训任务中汲取的数据,以推断任务之间共享的共同结构。如果没有沉重的奖励工程,长期任务中的稀疏奖励加剧了元RL样品效率的问题。 Meta-RL中的另一个挑战是任务之间难度级别的差异,这可能会导致一个简单的任务主导共享策略的学习,从而排除政策适应新任务。这项工作介绍了一个新颖的目标功能,可以在培训任务中学习动作翻译。从理论上讲,我们可以验证带有操作转换器的传输策略的值可以接近源策略的值和我们的目标函数(大约)上限的值差。我们建议将动作转换器与基于上下文的元元算法相结合,以更好地收集数据,并在元训练期间更有效地探索。我们的方法从经验上提高了稀疏奖励任务上元RL算法的样本效率和性能。
translated by 谷歌翻译
病理诊断依赖于组织学染色的薄组织样品的目视检查,其中使用不同类型的污渍来对比并突出各种所需的组织学特征。但是,破坏性的组织化学染色程序通常是不可逆的,因此很难在同一组织段上获得多个污渍。在这里,我们通过层叠的深神经网络(C-DNN)演示了虚拟的染色转移框架,以数字化将苏木精和曙红(H&E)染色的组织图像转化为其他类型的组织学染色。与单个神经网络结构不同,该结构仅将一种染色类型作为一种输入来输出另一种染色类型的数字输出图像,C-DNN首先使用虚拟染色将自动荧光显微镜图像转换为H&E,然后执行从H&E到另一个域的染色转换以级联的方式染色。在训练阶段的这种级联结构使该模型可以直接利用H&E和目标特殊污渍的组织化学染色图像数据。该优势减轻了配对数据获取的挑战,并提高了从H&E到另一个污渍的虚拟污渍转移的图像质量和色彩准确性。我们使用肾针芯活检组织切片验证了这种C-DNN方法的出色性能,并将H&E染色的组织图像成功地转移到虚拟PAS(周期性酸 - 雪)染色中。该方法使用现有的,组织化学染色的幻灯片提供了特殊污渍的高质量虚拟图像,并通过执行高度准确的污渍转换来创造数字病理学的新机会。
translated by 谷歌翻译
开发了基于深度学习的虚拟染色是为了将图像与无标签的组织截面形成鲜明对比,以数字方式与组织学染色相匹配,组织学染色是耗时,劳动密集型且与组织破坏性的。标准的虚拟染色需要在无标签组织的整个幻灯片成像过程中使用高的自动对焦精度,这会消耗总成像时间的很大一部分,并可能导致组织光损伤。在这里,我们介绍了一个快速的虚拟染色框架,该框架可以染色未标记的组织的散焦自动荧光图像,从而达到与无焦标签图像的虚拟染色相同的性能,还可以通过降低显微镜的自动焦点来节省大量的成像时间。该框架结合了一个虚拟自动化的神经网络,以数字重新聚焦了散落的图像,然后使用连续的网络将重新聚焦的图像转换为几乎染色的图像。这些级联网络构成了协作推理方案:虚拟染色模型通过培训期间的样式损失使虚拟自动化网络正常。为了证明该框架的功效,我们使用人肺组织训练并盲目地测试了这些网络。使用较低的焦点精度的4倍焦点,我们成功地将专注于重点的自动荧光图像转换为高质量的虚拟H&E图像,与使用精心注重的自动荧光输入图像的标准虚拟染色框架相匹配。在不牺牲染色质量的情况下,该框架减少了无标签的全滑动图像(WSI)虚拟染色所需的总图像获取时间〜32%,同时降低了约89%的自动对焦时间,并且具有〜89%消除病理学中费力且昂贵的组织化学染色过程的潜力。
translated by 谷歌翻译