During training, reinforcement learning systems interact with the world without considering the safety of their actions. When deployed into the real world, such systems can be dangerous and cause harm to their surroundings. Often, dangerous situations can be mitigated by defining a set of rules that the system should not violate under any conditions. For example, in robot navigation, one safety rule would be to avoid colliding with surrounding objects and people. In this work, we define safety rules in terms of the relationships between the agent and objects and use them to prevent reinforcement learning systems from performing potentially harmful actions. We propose a new safe epsilon-greedy algorithm that uses safety rules to override agents' actions if they are considered to be unsafe. In our experiments, we show that a safe epsilon-greedy policy significantly increases the safety of the agent during training, improves the learning efficiency resulting in much faster convergence, and achieves better performance than the base model.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

最近，Diffenderfer和Kailkhura提出了一种新的范式，仅通过修剪和量化随机加权的全精度神经网络，以学习紧凑而高度准确的二进制神经网络。但是，这些多质票（MPTS）的准确性对最佳的修剪比率高度敏感，这限制了其适用性。此外，原始实施没有获得任何培训或推理速度益处。在本报告中，我们讨论了克服这些局限性的几项改进。我们通过在CIFAR-10上进行实验来展示提出的技术的好处。

神经网络（NNS）和决策树（DTS）都是机器学习的流行模型，但具有相互排斥的优势和局限性。为了带来两个世界中的最好，提出了各种方法来明确或隐式地集成NN和DTS。在这项调查中，这些方法是在我们称为神经树（NTS）的学校中组织的。这项调查旨在对NTS进行全面审查，并尝试确定它们如何增强模型的解释性。我们首先提出了NTS的彻底分类学，该分类法表达了NNS和DTS的逐步整合和共同进化。之后，我们根据NTS的解释性和绩效分析，并建议解决其余挑战的可能解决方案。最后，这项调查以讨论有条件计算和向该领域的有希望的方向进行讨论结束。该调查中审查的论文列表及其相应的代码可在以下网址获得：https：//github.com/zju-vipa/awesome-neural-trees

原型零件网络（Protopnet）引起了广泛的关注，并增加了许多随访研究，因为它的自我解释特性可解释人工智能（XAI）。但是，当直接在视觉变压器（VIT）骨架上应用原始网络时，学到的原型存在“分心”问题：它们具有相对较高的可能性，即被背景激活，并且对前景的关注较少。建模长期依赖性的强大能力使得基于变压器的Protopnet难以专注于原型部分，从而严重损害了其固有的解释性。本文提出了原型零件变压器（ProtoPformer），以适当有效地应用基于原型的方法，并使用VIT进行可解释的图像识别。提出的方法介绍了根据VIT的建筑特征捕获和突出目标的代表性整体和部分特征的全局和局部原型。采用了全球原型，以提供对象的全球视图，以指导本地原型集中在前景上，同时消除背景的影响。之后，明确监督局部原型，以专注于它们各自的原型视觉部分，从而提高整体可解释性。广泛的实验表明，我们提出的全球和本地原型可以相互纠正并共同做出最终决策，这些决策分别忠实，透明地从整体和地方的角度缔合过程。此外，ProtoPformer始终取得优于基于原型的原型基线（SOTA）的卓越性能和可视化结果。我们的代码已在https://github.com/zju-vipa/protopformer上发布。

当前的AI系统旨在解决近世界问题的假设，即基础世界或多或少是相同的。但是，当处理现实世界问题时，这些假设可能无效，因为可能会发生突然和意外的变化。为了有效地在现实世界中部署AI驱动的系统，AI系统应该能够快速处理开放世界的新颖性。不可避免地，处理开放世界的新颖性引发了一个重要的新颖性困难问题。知道一种新颖性是否比另一种新颖性更难处理，可以帮助研究人员系统地训练他们的系统。此外，它还可以用作对新颖性AI系统的性能的测量。在本文中，我们建议将新颖性的难度定义为在引入新颖性后执行已知任务的相对困难。我们提出了一种通用方法，可用于近似难度。我们介绍了使用我们的方法的难度的近似值，并显示了它如何与旨在处理新颖性的AI剂的评估结果保持一致。

由于对隐私保护的关注不断增加，因此如何在不同数据源上建立机器学习（ML）模型具有安全保证，这越来越受欢迎。垂直联合学习（VFL）描述了这种情况，其中ML模型建立在不同参与方的私人数据上，该数据与同一集合相同的实例中拥有不相交的功能，这适合许多现实世界中的协作任务。但是，我们发现VFL现有的解决方案要么支持有限的输入功能，要么在联合执行过程中遭受潜在数据泄漏的损失。为此，本文旨在研究VFL方案中ML模式的功能和安全性。具体来说，我们介绍了BlindFL，这是VFL训练和推理的新型框架。首先，为了解决VFL模型的功能，我们建议联合源层团结不同各方的数据。联合源层可以有效地支持各种特征，包括密集，稀疏，数值和分类特征。其次，我们在联合执行期间仔细分析了安全性，并正式化了隐私要求。基于分析，我们设计了安全，准确的算法协议，并进一步证明了在理想真实的仿真范式下的安全保证。广泛的实验表明，BlindFL支持各种数据集和模型，同时获得强大的隐私保证。

作为一个新兴的安全学习范式，在利用跨机构私人数据中，垂直联合学习（VFL）有望通过启用广告商和发布者私人拥有的补充用户属性的联合学习来改善广告模型。但是，将其应用于广告系统有两个关键的挑战：a）标记的重叠样本的有限规模，b）实时跨机构服务的高成本。在本文中，我们提出了一个半监督的拆卸框架VFED-SSD，以减轻这两个限制。我们确定：i）广告系统中有大量未标记的重叠数据，ii）我们可以通过分解联合模型来保持模型性能和推理成本之间的平衡。具体而言，我们开发了一个自制任务匹配的配对检测（MPD），以利用垂直分区的未标记数据并提出拆分知识蒸馏（SplitKD）架构，以避免跨机构服务。对三个工业数据集的实证研究表现出我们方法的有效性，在本地部署模式和联合部署模式下，所有数据集的中位数AUC分别提高了0.86％和2.6％。总体而言，我们的框架为实时展示广告提供了一种有效的联邦增强解决方案，其部署成本和大量绩效提升。

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.

低成本单眼的3D对象检测在自主驾驶中起着基本作用，而其精度仍然远非令人满意。在本文中，我们挖掘了3D对象检测任务，并将其重构为对象本地化和外观感知的子任务，这有​​利于整个任务的互惠信息的深度挖掘。我们介绍了一个名为DFR-Net的动态特征反射网络，其中包含两种新的独立模块：（i）首先将任务特征分开的外观定位特征反射模块（ALFR），然后自相互反映互核特征; （ii）通过自学习方式自适应地重建各个子任务的培训过程的动态内部交易模块（DIT）。关于挑战基蒂数据集的广泛实验证明了DFR网的有效性和泛化。我们在基蒂测试集中的所有单眼3D对象探测器中排名第一（直到2021年3月16日）。所提出的方法在许多尖端的3D检测框架中也容易在较忽略的成本下以忽略的成本来播放。该代码将公开可用。