复杂知识库问题回答是过去十年的一个流行的研究领域。最近的公共数据集导致这一领域的令人鼓舞的结果，但主要涉及英语，只涉及少数问题类型和关系，在更现实的环境和英语以外的语言中妨碍研究。此外，很少有最先进的KBQA模型在Wikidata上培训，是最受欢迎的真实知识库之一。我们提出了CLC-Quad，这是Wikidata的第一个大规模复杂的中文语义解析数据集，以解决这些挑战。我们与数据集一起介绍了一个文本到SPARQL基线模型，可以有效地应答多种类型的复杂问题，例如事实上的问题，双重意图问题，布尔问题和计数问题，以及Wikidata作为背景知识。我们终于分析了SOTA KBQA模型在此数据集中的表现，并确定了中国KBQA面临的挑战。

加上各种任务的最新精确度的改进，深度学习模型正在越来越大。但是，实现这些大型模型非常困难，因为有限的GPU内存使得无法将大型型号安装到单个GPU甚至GPU服务器中。此外，要减少大型型号的训练时间非常必要。像Megatron-LM这样的先前方法实现了一种1维分布式方法，以使用GPU来加快培训。但是，这些方法的通信开销很高，大规模集群的缩放效率低。为了解决这些问题，我们提出了Tesseract，这是一种具有新颖设计的高度可扩展的张量并行性。它通过减少通信开销并降低每个GPU所需的内存来提高效率。通过将新颖的尺寸引入张量并行性，Tesseract大大增加了张量并行性的记忆能力。具体而言，这个新的维度进一步增加了张量并行性的程度。与以前的1-D和2-D方法相比，Tesseract设法降低了每一层的通信成本，导致速度分别为1.38倍和1.53倍，并具有强缩放率。在弱缩放实验中，与1-D/2-D方法相比，Tesseract的推理速度最高为4.0/1.7倍和3.4/1.7倍的吞吐量改进。通过引入Tesseract，我们提供了一种更有效，更可扩展的方法，以使用有限的GPU资源实施大型深度学习模型。

Instance segmentation in videos, which aims to segment and track multiple objects in video frames, has garnered a flurry of research attention in recent years. In this paper, we present a novel weakly supervised framework with \textbf{S}patio-\textbf{T}emporal \textbf{C}ollaboration for instance \textbf{Seg}mentation in videos, namely \textbf{STC-Seg}. Concretely, STC-Seg demonstrates four contributions. First, we leverage the complementary representations from unsupervised depth estimation and optical flow to produce effective pseudo-labels for training deep networks and predicting high-quality instance masks. Second, to enhance the mask generation, we devise a puzzle loss, which enables end-to-end training using box-level annotations. Third, our tracking module jointly utilizes bounding-box diagonal points with spatio-temporal discrepancy to model movements, which largely improves the robustness to different object appearances. Finally, our framework is flexible and enables image-level instance segmentation methods to operate the video-level task. We conduct an extensive set of experiments on the KITTI MOTS and YT-VIS datasets. Experimental results demonstrate that our method achieves strong performance and even outperforms fully supervised TrackR-CNN and MaskTrack R-CNN. We believe that STC-Seg can be a valuable addition to the community, as it reflects the tip of an iceberg about the innovative opportunities in the weakly supervised paradigm for instance segmentation in videos.

Federated learning (FL) is an effective technique to directly involve edge devices in machine learning training while preserving client privacy. However, the substantial communication overhead of FL makes training challenging when edge devices have limited network bandwidth. Existing work to optimize FL bandwidth overlooks downstream transmission and does not account for FL client sampling. In this paper we propose GlueFL, a framework that incorporates new client sampling and model compression algorithms to mitigate low download bandwidths of FL clients. GlueFL prioritizes recently used clients and bounds the number of changed positions in compression masks in each round. Across three popular FL datasets and three state-of-the-art strategies, GlueFL reduces downstream client bandwidth by 27% on average and reduces training time by 29% on average.

Predicting personality traits based on online posts has emerged as an important task in many fields such as social network analysis. One of the challenges of this task is assembling information from various posts into an overall profile for each user. While many previous solutions simply concatenate the posts into a long document and then encode the document by sequential or hierarchical models, they introduce unwarranted orders for the posts, which may mislead the models. In this paper, we propose a dynamic deep graph convolutional network (D-DGCN) to overcome the above limitation. Specifically, we design a learn-to-connect approach that adopts a dynamic multi-hop structure instead of a deterministic structure, and combine it with a DGCN module to automatically learn the connections between posts. The modules of post encoder, learn-to-connect, and DGCN are jointly trained in an end-to-end manner. Experimental results on the Kaggle and Pandora datasets show the superior performance of D-DGCN to state-of-the-art baselines. Our code is available at https://github.com/djz233/D-DGCN.

Active learning with strong and weak labelers considers a practical setting where we have access to both costly but accurate strong labelers and inaccurate but cheap predictions provided by weak labelers. We study this problem in the streaming setting, where decisions must be taken \textit{online}. We design a novel algorithmic template, Weak Labeler Active Cover (WL-AC), that is able to robustly leverage the lower quality weak labelers to reduce the query complexity while retaining the desired level of accuracy. Prior active learning algorithms with access to weak labelers learn a difference classifier which predicts where the weak labels differ from strong labelers; this requires the strong assumption of realizability of the difference classifier (Zhang and Chaudhuri,2015). WL-AC bypasses this \textit{realizability} assumption and thus is applicable to many real-world scenarios such as random corrupted weak labels and high dimensional family of difference classifiers (\textit{e.g.,} deep neural nets). Moreover, WL-AC cleverly trades off evaluating the quality with full exploitation of weak labelers, which allows to convert any active learning strategy to one that can leverage weak labelers. We provide an instantiation of this template that achieves the optimal query complexity for any given weak labeler, without knowing its accuracy a-priori. Empirically, we propose an instantiation of the WL-AC template that can be efficiently implemented for large-scale models (\textit{e.g}., deep neural nets) and show its effectiveness on the corrupted-MNIST dataset by significantly reducing the number of labels while keeping the same accuracy as in passive learning.

尽管模拟语义通信系统在文献中受到了很大的关注，但在数字语义通信系统上的工作较少。在本文中，我们开发了一个深度学习（DL）启用的矢量量化（VQ）语义通信系统，用于图像传输，名为VQ-Deepsc。具体而言，我们提出了一个基于卷积的神经网络（CNN）的收发器来提取图像的多尺度语义特征，并引入多尺度语义嵌入空间以执行语义特征量化，从而使数据与数字通信系统兼容。此外，我们通过引入Patchgan歧视者来采用对抗训练来提高接收图像的质量。实验结果表明，根据SSIM，所提出的VQ-Deepsc优于传统图像传输方法。

历史互动是推荐模型培训的默认选择，通常表现出高稀疏性，即大多数用户项目对都是未观察到的缺失数据。标准选择是将缺失的数据视为负训练样本，并估计用户项目对之间的相互作用以及观察到的相互作用。通过这种方式，在训练过程中不可避免地会误标记一些潜在的互动，这将损害模型的保真度，阻碍模型回忆起错误标签的项目，尤其是长尾尾。在这项工作中，我们从新的不确定性的新角度研究了标签的问题，该问题描述了缺失数据的固有随机性。随机性促使我们超越了相互作用的可能性，并接受了不确定性建模。为此，我们提出了一个新的不确定性不确定性建议（AUR）框架，该框架由新的不确定性估计器以及正常的推荐模型组成。根据核心不确定性理论，我们得出了一个新的建议目标来学习估计量。由于错误标签的机会反映了一对的潜力，因此AUR根据不确定性提出了建议，该建议被证明是为了改善较不受欢迎的项目的建议性能而不会牺牲整体性能。我们在三个代表性推荐模型上实例化AUR：来自主流模型体系结构的矩阵分解（MF），LightGCN和VAE。两个现实世界数据集的广泛结果验证了AUR W.R.T.的有效性。更好的建议结果，尤其是在长尾项目上。

面向任务的对话框（TOD）系统通常需要与外部知识库的互动，以检索必要的实体（例如餐厅）信息以支持响应生成。大多数当前的端到端TOD系统要么明确检索KB信息，要么将其嵌入模型参数中以进行隐式访问。后一种方法显示出更高的灵活性和效率。在这两种方法中，系统都可以通过冲突的实体信息产生响应。为了解决此问题，我们建议先生成实体自动加压，并利用它来指导端到端系统中的响应生成。为了确保实体的一致性，我们对实体生成强加了三位一体的约束。我们还引入了logit串联策略，以促进梯度反向传播进行端到端培训。 Multiwoz 2.1单一和CAMREST的实验表明，我们的系统可以产生更多的高质量和实体一致的响应。

预训练的语言模型（PLM）在自然语言理解中的许多下游任务中取得了显着的性能增长。已提出了各种中文PLM，以学习更好的中文表示。但是，大多数当前模型都使用中文字符作为输入，并且无法编码中文单词中包含的语义信息。虽然最近的预训练模型同时融合了单词和字符，但它们通常会遭受不足的语义互动，并且无法捕获单词和字符之间的语义关系。为了解决上述问题，我们提出了一个简单而有效的PLM小扣手，该小扣子采用了对单词和性格表示的对比度学习。特别是，Clower通过对多透明信息的对比学习将粗粒的信息（即单词）隐式编码为细粒度表示（即字符）。在现实的情况下，小电动器具有很大的价值，因为它可以轻松地将其纳入任何现有的基于细粒的PLM中而无需修改生产管道。在一系列下游任务上进行的扩展实验表明，小动物的卓越性能超过了几个最先进的实验 - 艺术基线。