A lot of theoretical and empirical evidence shows that the flatter local minima tend to improve generalization. Adversarial Weight Perturbation (AWP) is an emerging technique to efficiently and effectively find such minima. In AWP we minimize the loss w.r.t. a bounded worst-case perturbation of the model parameters thereby favoring local minima with a small loss in a neighborhood around them. The benefits of AWP, and more generally the connections between flatness and generalization, have been extensively studied for i.i.d. data such as images. In this paper, we extensively study this phenomenon for graph data. Along the way, we first derive a generalization bound for non-i.i.d. node classification tasks. Then we identify a vanishing-gradient issue with all existing formulations of AWP and we propose a new Weighted Truncated AWP (WT-AWP) to alleviate this issue. We show that regularizing graph neural networks with WT-AWP consistently improves both natural and robust generalization across many different graph learning tasks and models.

Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex distributed problem, the federated learning in practice still faces numerous challenges, such as the large training iterations to converge since the sizes of models and datasets keep increasing, and the lack of adaptivity by SGD-based model updates. Meanwhile, the study of adaptive methods in federated learning is scarce and existing works either lack a complete theoretical convergence guarantee or have slow sample complexity. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on the momentum-based variance reduced technique in cross-silo FL. We first explore how to design the adaptive algorithm in the FL setting. By providing a counter-example, we prove that a simple combination of FL and adaptive methods could lead to divergence. More importantly, we provide a convergence analysis for our method and prove that our algorithm is the first adaptive FL algorithm to reach the best-known samples $O(\epsilon^{-3})$ and $O(\epsilon^{-2})$ communication rounds to find an $\epsilon$-stationary point without large batches. The experimental results on the language modeling task and image classification task with heterogeneous data demonstrate the efficiency of our algorithms.

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

在过去的十年中，AI AID毒品发现（AIDD）的计算方法和数据集策划的繁荣发展。但是，现实世界中的药物数据集经常表现出高度不平衡的分布，这在很大程度上被当前的文献忽略了，但可能会严重损害机器学习应用程序的公平性和概括。在这一观察结果的激励下，我们介绍了Imdrug，这是一个全面的基准标准，其开源python库由4个不平衡设置，11个AI-Ready数据集，54个学习任务和16种为不平衡学习量身定制的基线算法。它为涵盖广泛的药物发现管道（例如分子建模，药物靶标相互作用和逆合合成）的问题和解决方案提供了可访问且可定制的测试床。我们通过新的评估指标进行广泛的实证研究，以证明现有算法在数据不平衡情况下无法解决药物和药物挑战。我们认为，Imdrug为未来的研究和发展开辟了途径，在AIDD和深度不平衡学习的交集中对现实世界中的挑战开辟了道路。

大规模数据集上的视觉语言预训练（VLP）在各种下游任务上表现出了首要性能。对于VLP来说，完整且公平的基准（即包括大规模的预训练数据集和各种下游任务）是必不可少的。尽管有很多具有英语语料库的基准，但使用其他语言（例如中文）为VLP建立丰富的基准是一个关键问题。为此，我们为研究界建立了一个称为零的中国跨模式基准，以比较VLP模型。我们发布两个用于下游任务的预训练数据集和五个微调数据集。旁边，我们提出了一个新的预训练前训练框架，用于跨模式学习。具体而言，我们应用全局对比度预级分别学习图像和文本的各个表示。然后，我们通过图像文本交叉编码器和文本图像交叉编码器以细粒度的排名方式融合表示形式。为了进一步增强模型的能力，我们提出了一种由目标引导的蒸馏和特征引导的蒸馏组成的双向蒸馏策略。对于简洁起见，我们将型号r2d2命名。我们在四个公共跨模式数据集和拟议的五个下游数据集上实现最先进的性能。在Flickr30k-CN，可可-CN和Muge进行零射击任务时，与最平均召回的R2D2进行了2.5亿个数据集的R2D2，在2.5亿个数据集中进行了4.7％，5.4％和6.3％的均值改善，而与最新的召回相比艺术。数据集，模型和代码可在https://github.com/yuxie11/r2d2上找到

本文研究了一个新的在线学习问题，其中包含双流式数据，其中数据流是通过不断发展的特征空间来描述的，新的功能出现了，旧功能逐渐消失。这个问题的挑战是两个折叠：1）随着时间的推移，数据样本不断流动，可能会随着时间的推移而随着时间的流逝而携带移动的模式，因此学习者可以随时更新。 2）很少的样本描述了新出现的特征，从而导致较弱的学习者倾向于做出错误预测。克服挑战的一个合理的想法是在前进的特征空间之间建立关系，以便在线学习者可以利用从旧功能中学到的知识来改善新功能的学习性能。不幸的是，这个想法并没有扩展到具有复杂功能相互作用的高维媒体流，这在善于跨性（偏见的浅学习者）和表现力（需要深度学习者）之间的权衡受到了折衷。在此激励的情况下，我们提出了一种新颖的旧^3S范式，其中发现了一个共享的潜在子空间来总结旧功能空间中的信息，从而构建了中间功能映射关系。旧^3S的关键特征是将模型容量视为可学习的语义，根据在线方式以输入数据流的复杂性和非线性，共同产生最佳模型深度和参数。理论分析和实证研究都证实了我们提议的生存能力和有效性。

目的：在手术规划之前，CT图像中肝血管的分割是必不可少的，并引起了医学图像分析界的广泛兴趣。由于结构复杂，对比度背景下，自动肝脏血管分割仍然特别具有挑战性。大多数相关的研究采用FCN，U-Net和V-Net变体作为骨干。然而，这些方法主要集中在捕获多尺度局部特征，这可能导致由于卷积运营商有限的地区接收领域而产生错误分类的体素。方法：我们提出了一种强大的端到端血管分割网络，通过将SWIN变压器扩展到3D并采用卷积和自我关注的有效组合，提出了一种被称为电感偏置的多头注意船网（IBIMHAV-NET）的稳健端到端血管分割网络。在实践中，我们介绍了Voxel-Wise嵌入而不是修补程序嵌入，以定位精确的肝脏血管素，并采用多尺度卷积运营商来获得局部空间信息。另一方面，我们提出了感应偏置的多头自我关注，其学习从初始化的绝对位置嵌入的归纳偏置相对位置嵌入嵌入。基于此，我们可以获得更可靠的查询和键矩阵。为了验证我们模型的泛化，我们测试具有不同结构复杂性的样本。结果：我们对3Dircadb数据集进行了实验。四种测试病例的平均骰子和敏感性为74.8％和77.5％，超过现有深度学习方法的结果和改进的图形切割方法。结论：拟议模型IBIMHAV-Net提供一种具有交错架构的自动，精确的3D肝血管分割，可更好地利用CT卷中的全局和局部空间特征。它可以进一步扩展到其他临床数据。

由于介导的介入X射线和未定义的预介入计算机断层扫描（CT）之间的映射关系是不确定的，辅助定位装置或身体标记，例如医疗植入物，通常用于确定这种关系。然而，由于复杂的现实，这种方法不能广泛用于临床上。为了确定映射关系，并实现没有辅助设备或标记的人体的初始化估计，所提出的方法应用图像分割和深度匹配，以直接匹配X射线和CT图像。结果，训练有素的网络可以直接预测任意X射线和CT之间的空间对应。实验结果表明，当与传统方法相结合的方法时，实现的准确性和速度可以满足基本的临床干预需求，并为介入内注册提供了新的方向。

使用X光片级注释（是或否疾病）和细粒病变级注释（病变边界框）开发了两个DL模型，分别为Chexnet和ChexDet。在测试集（n = 2,922）中比较了模型的内部分类性能和病变定位性能，在NIH-Google（n = 4,376）和Padchest（n = 24,536）数据集上比较了外部分类性能，以及外部病变的本地化性能性能在NIH-Chestx-Ray14数据集（n = 880）上进行了比较。还将模型与内部测试集子集的放射学家进行了比较（n = 496）。鉴于足够的训练数据，这两个模型都与放射科医生相当。 CHEXDET对外部分类有了显着改善，例如在NIH-Google上分类（ROC曲线下的ChexDet区域[AUC]：0.67：Chexnet AUC：0.51; P <.001）和PadChest（ChexDet AUC：0.78，Chexnet AUC，Chexnet AUC，Chexnet AUC，Chexnet auc：chexnet auc auc：chexnet auc auc auc：0.78，chexnet auc auc： ：0.55; p <.001）。对于所有数据集的大多数异常，例如在内部集合中检测气胸（Chexdet Jacknife替代自由响应ROC的功绩[JAFROC-FOM]：0.87，0.87，CHEXNET JAFROC-FOM：0.113） ; p <.001）和NIH-Chestx-Ray14（Chexdet Jafroc-fom：0.55，Chexnet Jafroc-fom：0.04; p <.001）。总结，细粒的注释克服了快捷方式学习并启用了DL模型，以识别正确的病变模式，从而改善模型的概括性。

Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning. However, they neglect the relationship between multiple granularities and different features in alignment, degrading detection. Addressing this, we introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning. The key is to encode the dependencies across different granularities including pixel-, instance-, and category-levels simultaneously to align two domains. Specifically, based on pixel-level features, we first develop an omni-scale gated fusion (OSGF) module to aggregate discriminative representations of instances with scale-aware convolutions, leading to robust multi-scale detection. Besides, we introduce multi-granularity discriminators to identify where, either source or target domains, different granularities of samples come from. Note that, MGA not only leverages instance discriminability in different categories but also exploits category consistency between two domains for detection. Furthermore, we present an adaptive exponential moving average (AEMA) strategy that explores model assessments for model update to improve pseudo labels and alleviate local misalignment problem, boosting detection robustness. Extensive experiments on multiple domain adaption scenarios validate the superiority of MGA over other approaches on FCOS and Faster R-CNN detectors. Code will be released at https://github.com/tiankongzhang/MGA.