Federated learning (FL) is a method to train model with distributed data from numerous participants such as IoT devices. It inherently assumes a uniform capacity among participants. However, participants have diverse computational resources in practice due to different conditions such as different energy budgets or executing parallel unrelated tasks. It is necessary to reduce the computation overhead for participants with inefficient computational resources, otherwise they would be unable to finish the full training process. To address the computation heterogeneity, in this paper we propose a strategy for estimating local models without computationally intensive iterations. Based on it, we propose Computationally Customized Federated Learning (CCFL), which allows each participant to determine whether to perform conventional local training or model estimation in each round based on its current computational resources. Both theoretical analysis and exhaustive experiments indicate that CCFL has the same convergence rate as FedAvg without resource constraints. Furthermore, CCFL can be viewed of a computation-efficient extension of FedAvg that retains model performance while considerably reducing computation overhead.
translated by 谷歌翻译
The last several years have witnessed remarkable progress in video-and-language (VidL) understanding. However, most modern VidL approaches use complex and specialized model architectures and sophisticated pretraining protocols, making the reproducibility, analysis and comparisons of these frameworks difficult. Hence, instead of proposing yet another new VidL model, this paper conducts a thorough empirical study demystifying the most important factors in the VidL model design. Among the factors that we investigate are (i) the spatiotemporal architecture design, (ii) the multimodal fusion schemes, (iii) the pretraining objectives, (iv) the choice of pretraining data, (v) pretraining and finetuning protocols, and (vi) dataset and model scaling. Our empirical study reveals that the most important design factors include: temporal modeling, video-to-text multimodal fusion, masked modeling objectives, and joint training on images and videos. Using these empirical insights, we then develop a step-by-step recipe, dubbed VindLU, for effective VidL pretraining. Our final model trained using our recipe achieves comparable or better than state-of-the-art results on several VidL tasks without relying on external CLIP pretraining. In particular, on the text-to-video retrieval task, our approach obtains 61.2% on DiDeMo, and 55.0% on ActivityNet, outperforming current SOTA by 7.8% and 6.1% respectively. Furthermore, our model also obtains state-of-the-art video question-answering results on ActivityNet-QA, MSRVTT-QA, MSRVTT-MC and TVQA. Our code and pretrained models are publicly available at: https://github.com/klauscc/VindLU.
translated by 谷歌翻译
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although tremendous efforts have been made to recall precise and complete locations for each class, existing methods still commonly suffer from the unsolicited Out-of-Candidate (OC) error predictions that not belongs to the label candidates, which could be avoidable since the contradiction with image-level class tags is easy to be detected. In this paper, we develop a group ranking-based Out-of-Candidate Rectification (OCR) mechanism in a plug-and-play fashion. Firstly, we adaptively split the semantic categories into In-Candidate (IC) and OC groups for each OC pixel according to their prior annotation correlation and posterior prediction correlation. Then, we derive a differentiable rectification loss to force OC pixels to shift to the IC group. Incorporating our OCR with seminal baselines (e.g., AffinityNet, SEAM, MCTformer), we can achieve remarkable performance gains on both Pascal VOC (+3.2%, +3.3%, +0.8% mIoU) and MS COCO (+1.0%, +1.3%, +0.5% mIoU) datasets with negligible extra training overhead, which justifies the effectiveness and generality of our OCR.
translated by 谷歌翻译
联合学习(FL)是一个分布式的机器学习框架,可以减轻数据孤岛,在该筒仓中,分散的客户在不共享其私人数据的情况下协作学习全球模型。但是,客户的非独立且相同分布的(非IID)数据对训练有素的模型产生了负面影响,并且具有不同本地更新的客户可能会在每个通信回合中对本地梯度造成巨大差距。在本文中,我们提出了一种联合矢量平均(FedVeca)方法来解决上述非IID数据问题。具体而言,我们为与本地梯度相关的全球模型设定了一个新的目标。局部梯度定义为具有步长和方向的双向向量,其中步长为局部更新的数量,并且根据我们的定义将方向分为正和负。在FedVeca中,方向受步尺的影响,因此我们平均双向向量,以降低不同步骤尺寸的效果。然后,我们理论上分析了步骤大小与全球目标之间的关系,并在每个通信循环的步骤大小上获得上限。基于上限,我们为服务器和客户端设计了一种算法,以自适应调整使目标接近最佳的步骤大小。最后,我们通过构建原型系统对不同数据集,模型和场景进行实验,实验结果证明了FedVeca方法的有效性和效率。
translated by 谷歌翻译
有机搜索包括电子商务公司总流量的很大一部分。扩大公司在有机搜索渠道上接触的一种方法是创建对客户意图的覆盖范围更广泛的着陆页。在本文中,我们提出了一个基于变压器语言模型的有机渠道页面管理系统,旨在提高公司对渠道的总体点击的突出性。我们的系统成功地处理了数百万个新登陆页面的创建和部署过程。我们展示并讨论了最先进的语言表示方法的现实表现,并揭示了我们如何将它们视为最佳的解决方案。
translated by 谷歌翻译
安全与其他交通参与者的互动是自动驾驶的核心要求之一,尤其是在交叉点和遮挡中。大多数现有的方法都是为特定场景设计的,需要大量的人工劳动参数调整,以应用于不同情况。为了解决这个问题,我们首先提出了一个基于学习的交互点模型(IPM),该模型描述了代理与保护时间和交互优先级之间的相互作用以统一的方式。我们将提出的IPM进一步整合到一个新颖的计划框架中,通过在高度动态的环境中的全面模拟来证明其有效性和鲁棒性。
translated by 谷歌翻译
尽管变形金刚及其变体构象体在语音识别方面表现出了有希望的表现,但参数化的属性在训练和推理过程中导致了很大的记忆成本。一些作品使用跨层重量分享来减少模型的参数。但是,不可避免的能力损失会损害模型性能。为了解决这个问题,本文提出了通过共享稀疏门控专家的参数效率构象异构体。具体而言,我们使用稀疏门控的专家(MOE)来扩展构型块的容量而不增加计算。然后,共享分组构象块的参数,以减少参数的数量。接下来,为了确保具有不同级别适应表示的灵活性的共享块,我们会单独设计MOE路由器和标准化。此外,我们使用知识蒸馏来进一步提高性能。实验结果表明,与全参数模型相比,所提出的模型用编码器的1/3来实现竞争性能。
translated by 谷歌翻译
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
translated by 谷歌翻译
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。
translated by 谷歌翻译
只有单个目标扬声器的语音供参考的单发语音转换(VC)已成为一个热门研究主题。现有作品通常会散布音色,而有关音高,节奏和内容的信息仍然混合在一起。为了进一步删除这些语音组件,有效地执行一声VC,我们采用随机重新采样用于音高和内容编码器,并使用互信息的各种对比对数比率上限和基于梯度反向层的对抗性相互信息学习来确保不同部分在训练过程中仅包含所需的分离表示的潜在空间。 VCTK数据集的实验显示该模型就自然性和智能性方面实现了一声VC的最新性能。此外,我们可以通过语音表示分离分别传递音色,音调和节奏的单发VC的特征。我们的代码,预训练的模型和演示可在https://im1eon.github.io/is2022-Srdvc/上获得。
translated by 谷歌翻译