图形上的神经扩散是一类新型的图形神经网络，最近引起了越来越多的关注。图形神经偏微分方程（PDE）的能力在解决图形神经网络（GNN）的常见障碍方面的能力，例如过度平滑和瓶颈的问题，但尚未对其对逆性攻击的稳健性。在这项工作中，我们探讨了图神经PDE的稳健性。我们从经验上证明，与其他GNN相比，图形神经PDE在本质上对拓扑扰动更为强大。我们通过利用在图形拓扑扰动下利用热半群的稳定性来提供对这一现象的见解。我们讨论了各种图扩散操作员，并将它们与现有的图神经PDE相关联。此外，我们提出了一个一般图形神经PDE框架，可以通过该框架来定义新的强大GNN。我们验证了新模型在多个基准数据集上实现了可比的最新性能。

大多数现有的深神经网络都是静态的，这意味着它们只能以固定的复杂性推断。但资源预算可以大幅度不同。即使在一个设备上，实惠预算也可以用不同的场景改变，并且对每个所需预算的反复培训网络是非常昂贵的。因此，在这项工作中，我们提出了一种称为Mutualnet的一般方法，以训练可以以各种资源约束运行的单个网络。我们的方法列举了具有各种网络宽度和输入分辨率的模型配置队列。这种相互学习方案不仅允许模型以不同的宽度分辨率配置运行，而且还可以在这些配置之间传输独特的知识，帮助模型来学习更强大的表示。 Mutualnet是一般的培训方法，可以应用于各种网络结构（例如，2D网络：MobileNets，Reset，3D网络：速度，X3D）和各种任务（例如，图像分类，对象检测，分段和动作识别），并证明了实现各种数据集的一致性改进。由于我们只培训了这一模型，它对独立培训多种型号而言，它也大大降低了培训成本。令人惊讶的是，如果动态资源约束不是一个问题，则可以使用Mutualnet来显着提高单个网络的性能。总之，Mutualnet是静态和自适应，2D和3D网络的统一方法。代码和预先训练的模型可用于\ url {https://github.com/tayang1122/mutualnet}。

In the field of multimodal sentiment analysis (MSA), a few studies have leveraged the inherent modality correlation information stored in samples for self-supervised learning. However, they feed the training pairs in a random order without consideration of difficulty. Without human annotation, the generated training pairs of self-supervised learning often contain noise. If noisy or hard pairs are used for training at the easy stage, the model might be stuck in bad local optimum. In this paper, we inject curriculum learning into weakly supervised modality correlation learning. The weakly supervised correlation learning leverages the label information to generate scores for negative pairs to learn a more discriminative embedding space, where negative pairs are defined as two unimodal embeddings from different samples. To assist the correlation learning, we feed the training pairs to the model according to difficulty by the proposed curriculum learning, which consists of elaborately designed scoring and feeding functions. The scoring function computes the difficulty of pairs using pre-trained and current correlation predictors, where the pairs with large losses are defined as hard pairs. Notably, the hardest pairs are discarded in our algorithm, which are assumed as noisy pairs. Moreover, the feeding function takes the difference of correlation losses as feedback to determine the feeding actions (`stay', `step back', or `step forward'). The proposed method reaches state-of-the-art performance on MSA.

Learning effective joint embedding for cross-modal data has always been a focus in the field of multimodal machine learning. We argue that during multimodal fusion, the generated multimodal embedding may be redundant, and the discriminative unimodal information may be ignored, which often interferes with accurate prediction and leads to a higher risk of overfitting. Moreover, unimodal representations also contain noisy information that negatively influences the learning of cross-modal dynamics. To this end, we introduce the multimodal information bottleneck (MIB), aiming to learn a powerful and sufficient multimodal representation that is free of redundancy and to filter out noisy information in unimodal representations. Specifically, inheriting from the general information bottleneck (IB), MIB aims to learn the minimal sufficient representation for a given task by maximizing the mutual information between the representation and the target and simultaneously constraining the mutual information between the representation and the input data. Different from general IB, our MIB regularizes both the multimodal and unimodal representations, which is a comprehensive and flexible framework that is compatible with any fusion methods. We develop three MIB variants, namely, early-fusion MIB, late-fusion MIB, and complete MIB, to focus on different perspectives of information constraints. Experimental results suggest that the proposed method reaches state-of-the-art performance on the tasks of multimodal sentiment analysis and multimodal emotion recognition across three widely used datasets. The codes are available at \url{https://github.com/TmacMai/Multimodal-Information-Bottleneck}.

CSI反馈是大规模多输入多输出（MIMO）技术的重要问题，因为反馈开销与亚渠道的数量和天线数量成正比，这两种数量均与大型MIMO系统的大​​小相规。基于深度学习的CSI反馈方法由于其出色的性能而被广泛采用。尽管取得了成功，但目前的方法并未完全利用CSI数据的特征与深度学习框架之间的关系。在本文中，我们提出了一种拼图拼图帮助培训策略（JPTS），以通过最大程度地提高原始CSI和压缩CSI之间的相互信息来增强基于深度学习的大型MIMO CSI反馈方法。我们将JPT应用于现有的最新方法。实验结果表明，通过采用这种训练策略，在室内和室外环境中，精度平均可以提高12.07％和7.01％。提出的方法准备采用大量MIMO CSI反馈的现有深度学习框架。 JPT的代码可在GitHub上获得可重现性。

代码生成旨在从自然语言描述中自动生成代码段。通常，主流代码生成方法依赖大量的配对培训数据，包括自然语言描述和代码。但是，在某些特定领域的情况下，很难为代码生成建立如此大的配对语料库，因为没有直接可用的配对数据，并且需要大量精力来手动编写代码说明来构建高质量的培训数据集。由于培训数据有限，生成模型不能经过良好的训练，并且可能过于拟合，从而使该模型对现实世界的使用不满意。为此，在本文中，我们提出了一种任务增强方法，该方法通过扩展原始的Tranx模型来支持suptoken级代码生成，将域知识通过辅助任务和亚键入tranx模型纳入代码生成模型。为了验证我们提出的方法，我们收集了一个真实的代码生成数据集并在其上进行实验。我们的实验结果表明，亚句级Tranx模型在我们的数据集中优于原始Tranx模型和变压器模型，并且在我们的任务增强方法的帮助下，Subtoken-Tranx的确切匹配精度可显着提高12.75 \％。多个代码类别的模型性能满足了工业系统应用程序的要求。我们提出的方法已由阿里巴巴的\ emph {bizcook}平台采用。据我们所知，这是在工业开发环境中采用的第一个领域代码生成系统。

创建什么故事需要推理关于先前陈述以及变更条件的可能结果。人们可以在新条件下轻松生成连贯的结局，但目前系统会对原始故事进行最小的变化来挑战。因此，一个主要挑战是生成逻辑故事和用最小编辑重写之间的权衡。在本文中，我们提出了教育，这是一种基于编辑的无预测方法，用于反复重写。教育包括基于估计在线条件的因果效果的目标位置检测策略，这使故事的因果不变部分。 Bowat然后在流畅，一致性和最小编辑约束下生成故事。我们还提出了一种新的指标来缓解当前自动指标的缺点，更好地评估权衡。我们评估公共反事故事重写基准的教育。实验表明，教育根据自动和人类评估，达到了无监督的SOTA方法的最佳权衡。教育资源可用于：https：//github.com/jiangjiechen/educat。

今天的数据往往散布数十亿资源受限的边缘设备，具有安全性和隐私约束。联合学习（FL）已成为在保持数据私有的同时学习全球模型的可行解决方案，但FL的模型复杂性被边缘节点的计算资源阻碍。在这项工作中，我们调查了一种新的范例来利用强大的服务器模型来突破FL中的模型容量。通过选择性地从多个教师客户和本身学习，服务器模型开发深入的知识，并将其知识传输回客户端，以恢复它们各自的性能。我们所提出的框架在服务器和客户端模型上实现了卓越的性能，并在统一的框架中提供了几个优势，包括异构客户端架构的灵活性，对各种图像分类任务的客户端和服务器之间的通信效率。

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed implicitly, by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. CMT obtains 73.0% NDS on nuScenes benchmark. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code will be released at https://github.com/junjie18/CMT.