The growing interest in intelligent services and privacy protection for mobile devices has given rise to the widespread application of federated learning in Multi-access Edge Computing (MEC). Diverse user behaviors call for personalized services with heterogeneous Machine Learning (ML) models on different devices. Federated Multi-task Learning (FMTL) is proposed to train related but personalized ML models for different devices, whereas previous works suffer from excessive communication overhead during training and neglect the model heterogeneity among devices in MEC. Introducing knowledge distillation into FMTL can simultaneously enable efficient communication and model heterogeneity among clients, whereas existing methods rely on a public dataset, which is impractical in reality. To tackle this dilemma, Federated MultI-task Distillation for Multi-access Edge CompuTing (FedICT) is proposed. FedICT direct local-global knowledge aloof during bi-directional distillation processes between clients and the server, aiming to enable multi-task clients while alleviating client drift derived from divergent optimization directions of client-side local models. Specifically, FedICT includes Federated Prior Knowledge Distillation (FPKD) and Local Knowledge Adjustment (LKA). FPKD is proposed to reinforce the clients' fitting of local data by introducing prior knowledge of local data distributions. Moreover, LKA is proposed to correct the distillation loss of the server, making the transferred local knowledge better match the generalized representation. Experiments on three datasets show that FedICT significantly outperforms all compared benchmarks in various data heterogeneous and model architecture settings, achieving improved accuracy with less than 1.2% training communication overhead compared with FedAvg and no more than 75% training communication round compared with FedGKT.
translated by 谷歌翻译
Since the recent success of Vision Transformers (ViTs), explorations toward transformer-style architectures have triggered the resurgence of modern ConvNets. In this work, we explore the representation ability of DNNs through the lens of interaction complexities. We empirically show that interaction complexity is an overlooked but essential indicator for visual recognition. Accordingly, a new family of efficient ConvNets, named MogaNet, is presented to pursue informative context mining in pure ConvNet-based models, with preferable complexity-performance trade-offs. In MogaNet, interactions across multiple complexities are facilitated and contextualized by leveraging two specially designed aggregation blocks in both spatial and channel interaction spaces. Extensive studies are conducted on ImageNet classification, COCO object detection, and ADE20K semantic segmentation tasks. The results demonstrate that our MogaNet establishes new state-of-the-art over other popular methods in mainstream scenarios and all model scales. Typically, the lightweight MogaNet-T achieves 80.0\% top-1 accuracy with only 1.44G FLOPs using a refined training setup on ImageNet-1K, surpassing ParC-Net-S by 1.4\% accuracy but saving 59\% (2.04G) FLOPs.
translated by 谷歌翻译
资金机构在很大程度上依赖于领域专家与研究建议之间的主题匹配来分配提案审查员。随着建议越来越跨学科,概述提案的跨学科性质是一项挑战,此后,找到具有适当专业知识的专家审阅者。解决这一挑战的重要步骤是准确对建议的跨学科标签进行分类。现有的方法论和申请相关文献,例如文本分类和提案分类,不足以共同解决跨学科建议数据引入的三个关键独特问题:1)提案的纪律标签的层次结构,谷物,例如,从信息科学到AI,再到AI的基础。 2)在提案中起着不同作用的各种主要文本部分的异质语义; 3)提案的数量在非学科和跨学科研究之间存在不平衡。我们可以同时解决该提案的跨学科性质时的三个问题吗?为了回答这个问题,我们提出了一个层次混音多标签分类框架,我们称之为H-Mixup。 H-Mixup利用基于变压器的语义信息提取器和基于GCN的跨学科知识提取器来解决第一期和第二个问题。 H-Mixup开发了Wold级混音,Word级cutmix,歧管混音和文档级混音的融合训练方法,以解决第三期。
translated by 谷歌翻译
室外(OOD)检测是面向任务的对话框系统中的关键组件,旨在确定查询是否不在预定义的支持的意图集之外。事实证明,先前基于软磁性的检测算法对OOD样品被过度自信。在本文中,我们分析了过度自信的OOD来自由于训练和测试分布之间的不匹配而导致的分布不确定性,这使得该模型无法自信地做出预测,因此可能导致异常软磁得分。我们提出了一个贝叶斯OOD检测框架,以使用Monte-Carlo辍学来校准分布不确定性。我们的方法是灵活的,并且可以轻松地插入现有的基于软磁性的基线和增益33.33 \%OOD F1改进,而与MSP相比仅增加了0.41 \%的推理时间。进一步的分析表明,贝叶斯学习对OOD检测的有效性。
translated by 谷歌翻译
链接预测的任务旨在解决由于难以从现实世界中收集事实而引起的不完整知识的问题。基于GCN的模型由于其复杂性而广泛应用于解决链接预测问题,但基于GCN的模型在结构和培训过程中遇到了两个问题。 1)GCN层的转化方法在基于GCN的知识表示模型中变得越来越复杂; 2)由于知识图收集过程的不完整,标记为负样本中有许多未收集的真实事实。因此,本文研究了相邻节点的信息聚合系数(自我注意)的特征,并重新设计了GAT结构的自我注意力。同时,受到人类思维习惯的启发,我们在预训练的模型上设计了一种半监督的自训练方法。基准数据集FB15K-237和WN18RR上的实验结果表明,我们提出的自我发项机制和半监督的自我训练方法可以有效地提高链接预测任务的性能。例如,如果您查看FB15K-237,则建议的方法将@1的命中率提高了约30%。
translated by 谷歌翻译
深层自然语言处理(NLP)模型的快速发展导致迫切需要对这些模型单独提出的统一理解。由于缺乏解释低级(例如单词)和高级(例如,短语)特征的统一措施,现有方法无法满足一个框架中不同模型的需求。我们已经开发了一个视觉分析工具DeepNLPVI,以使对文本分类的NLP模型有统一的理解。关键思想是一种基于信息的度量,它提供了有关模型的每一层如何维护样本中输入单词信息的定量解释。我们在每个层的内部和界面信息中对单词对最终预测的重要性以及单词之间的关系(例如短语的形成)进行建模。多层可视化由语料库级,样本级别和单词级可视化组成,支持从整体训练集到单个样本的分析。关于分类任务和模型比较的两个案例研究表明,DeepNLPVI可以帮助用户有效地确定样本和模型架构引起的潜在问题,然后进行明智的改进。
translated by 谷歌翻译
有效地发现满足各种性能要求的分子可以显着受益药物发现行业。由于搜索整个化学空间是不可行的,因此最近的作品采用了用于目标定向分子产生的生成模型。它们倾向于利用迭代过程,优化每次迭代时的分子发生模型的参数,以产生有望的分子以进一步验证。利用评估来评估每次迭代的产生的分子,为模型优化提供方向。然而,最先前的作品需要大量的昂贵且耗时的评估,例如湿法实验和分子动态模拟,导致缺乏实用性。为了减少迭代过程中的评估,我们提出了一种在潜在空间中的成本效益的演化策略,其优化了分子潜在载波。我们采用预先训练的分子生成模型来映射潜伏和观察空间,利用大规模未标记的分子来学习化学知识。为了进一步减少昂贵的评估数量,我们将一个筛选器预先介绍为评估的代理。我们对多种优化任务进行了广泛的实验,将建议的框架与几种先进技术进行比较,表明所提出的框架更好地实现了更好的评估。
translated by 谷歌翻译
Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization ability of neural networks, train robust neural networks, and provide interpretability for neural networks. In this work, we introduce adversarial training in time series analysis to enhance the neural networks for better generalization ability by taking the finance field as an example. Rethinking existing research on adversarial training, we propose the adaptively scaled adversarial training (ASAT) in time series analysis, by rescaling data at different time slots with adaptive scales. Experimental results show that the proposed ASAT can improve both the generalization ability and the adversarial robustness of neural networks compared to the baselines. Compared to the traditional adversarial training algorithm, ASAT can achieve better generalization ability and similar adversarial robustness.
translated by 谷歌翻译
事实证明,数据混合对提高深神经网络的概括能力是有效的。虽然早期方法通过手工制作的策略(例如线性插值)混合样品,但最新方法利用显着性信息通过复杂的离线优化来匹配混合样品和标签。但是,在精确的混合政策和优化复杂性之间进行了权衡。为了应对这一挑战,我们提出了一个新颖的自动混合(Automix)框架,其中混合策略被参数化并直接实现最终分类目标。具体而言,Automix将混合分类重新定义为两个子任务(即混合样品生成和混合分类)与相应的子网络,并在双层优化框架中求解它们。对于这一代,可学习的轻质混合发电机Mix Block旨在通过在相应混合标签的直接监督下对贴片的关系进行建模,以生成混合样品。为了防止双层优化的降解和不稳定性,我们进一步引入了动量管道以端到端的方式训练汽车。与在各种分类场景和下游任务中的最新图像相比,九个图像基准的广泛实验证明了汽车的优势。
translated by 谷歌翻译
批准方法,例如批处理[Ioffe和Szegedy,2015],体重[Salimansand Kingma,2016],实例[Ulyanov等,2016]和层归一化[Baet al。,2016]已广泛用于现代机器学习中。在这里,我们研究了体重归一化方法(WN)方法[Salimans和Kingma,2016年],以及一种称为重扎式投影梯度下降(RPGD)的变体,用于过多散热性最小二乘回归。 WN和RPGD用比例G和一个单位向量W重新绘制权重,因此目标函数变为非convex。我们表明,与原始目标的梯度下降相比,这种非凸式配方具有有益的正则化作用。这些方法适应性地使重量正规化并收敛于最小L2规范解决方案,即使初始化远非零。对于G和W的某些步骤,我们表明它们可以收敛于最小规范解决方案。这与梯度下降的行为不同,梯度下降的行为仅在特征矩阵范围内的一个点开始时才收敛到最小规范解,因此对初始化更敏感。
translated by 谷歌翻译