在胸部计算机断层扫描（CT）扫描中，自动分割地面玻璃的不透明和固结可以在高资源利用时期减轻放射科医生的负担。但是，由于分布（OOD）数据默默失败，深度学习模型在临床常规中不受信任。我们提出了一种轻巧的OOD检测方法，该方法利用特征空间中的Mahalanobis距离，并无缝集成到最新的分割管道中。简单的方法甚至可以增加具有临床相关的不确定性定量的预训练模型。我们在四个胸部CT分布偏移和两个磁共振成像应用中验证我们的方法，即海马和前列腺的分割。我们的结果表明，所提出的方法在所有探索场景中有效地检测到遥远和近型样品。

大多数持续学习方法都在明确定义任务边界并在培训和测试过程中可用的任务标识信息的设置中进行了验证。我们探讨了这种方法在任务不足的环境中的性能，该环境更像动态临床环境，并逐渐变化。我们提出了Odex，这是一种整体解决方案，将分布外检测与持续学习技术相结合。在海马分割的两种情况下进行验证表明，我们提出的方法可靠地维持早期任务的性能而不会失去可塑性。

联邦学习是培训强大的深度学习模型的最有希望的胸廓CTS中Covid-19相关发现的细分。通过以分散的方式学习，异构数据可以从各种来源和采集协议中利用，同时确保患者隐私。然而，连续监测模型的性能是至关重要的。然而，当涉及弥漫性肺病变的分割时，快速的目视检查是不足以评估专家放射科医师对所有网络输出的质量，并且无法彻底监测。在这项工作中，我们呈现了一系列轻量级度量，可以在每个医院本地计算，然后聚合用于联合系统的中央监控。我们的线性模型检测到分布外数据集上超过70％的低质量分段，从而可靠地发出模型性能下降。

Convolutional neural networks (CNNs) are currently among the most widely-used neural networks available and achieve state-of-the-art performance for many problems. While originally applied to computer vision tasks, CNNs work well with any data with a spatial relationship, besides images, and have been applied to different fields. However, recent works have highlighted how CNNs, like other deep learning models, are sensitive to noise injection which can jeopardise their performance. This paper quantifies the numerical uncertainty of the floating point arithmetic inaccuracies of the inference stage of DeepGOPlus, a CNN that predicts protein function, in order to determine its numerical stability. In addition, this paper investigates the possibility to use reduced-precision floating point formats for DeepGOPlus inference to reduce memory consumption and latency. This is achieved with Monte Carlo Arithmetic, a technique that experimentally quantifies floating point operation errors and VPREC, a tool that emulates results with customizable floating point precision formats. Focus is placed on the inference stage as it is the main deliverable of the DeepGOPlus model that will be used across environments and therefore most likely be subjected to the most amount of noise. Furthermore, studies have shown that the inference stage is the part of the model which is most disposed to being scaled down in terms of reduced precision. All in all, it has been found that the numerical uncertainty of the DeepGOPlus CNN is very low at its current numerical precision format, but the model cannot currently be reduced to a lower precision that might render it more lightweight.

With the increasing use of Graph Neural Networks (GNNs) in critical real-world applications, several post hoc explanation methods have been proposed to understand their predictions. However, there has been no work in generating explanations on the fly during model training and utilizing them to improve the expressive power of the underlying GNN models. In this work, we introduce a novel explanation-directed neural message passing framework for GNNs, EXPASS (EXplainable message PASSing), which aggregates only embeddings from nodes and edges identified as important by a GNN explanation method. EXPASS can be used with any existing GNN architecture and subgraph-optimizing explainer to learn accurate graph embeddings. We theoretically show that EXPASS alleviates the oversmoothing problem in GNNs by slowing the layer wise loss of Dirichlet energy and that the embedding difference between the vanilla message passing and EXPASS framework can be upper bounded by the difference of their respective model weights. Our empirical results show that graph embeddings learned using EXPASS improve the predictive performance and alleviate the oversmoothing problems of GNNs, opening up new frontiers in graph machine learning to develop explanation-based training frameworks.

Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing approaches usually consider learning prompt vectors for each task independently from scratch, thereby failing to exploit the rich shareable knowledge across different vision-language tasks. In this paper, we propose multitask vision-language prompt tuning (MVLPT), which incorporates cross-task knowledge into prompt tuning for vision-language models. Specifically, (i) we demonstrate the effectiveness of learning a single transferable prompt from multiple source tasks to initialize the prompt for each target task; (ii) we show many target tasks can benefit each other from sharing prompt vectors and thus can be jointly learned via multitask prompt tuning. We benchmark the proposed MVLPT using three representative prompt tuning methods, namely text prompt tuning, visual prompt tuning, and the unified vision-language prompt tuning. Results in 20 vision tasks demonstrate that the proposed approach outperforms all single-task baseline prompt tuning methods, setting the new state-of-the-art on the few-shot ELEVATER benchmarks and cross-task generalization benchmarks. To understand where the cross-task knowledge is most effective, we also conduct a large-scale study on task transferability with 20 vision tasks in 400 combinations for each prompt tuning method. It shows that the most performant MVLPT for each prompt tuning method prefers different task combinations and many tasks can benefit each other, depending on their visual similarity and label similarity. Code is available at https://github.com/sIncerass/MVLPT.

We study a novel and important communication pattern in large-scale model-parallel deep learning (DL), which we call cross-mesh resharding. This pattern emerges when the two paradigms of model parallelism - intra-operator and inter-operator parallelism - are combined to support large models on large clusters. In cross-mesh resharding, a sharded tensor needs to be sent from a source device mesh to a destination device mesh, on which the tensor may be distributed with the same or different layouts. We formalize this as a many-to-many multicast communication problem, and show that existing approaches either are sub-optimal or do not generalize to different network topologies or tensor layouts, which result from different model architectures and parallelism strategies. We then propose two contributions to address cross-mesh resharding: an efficient broadcast-based communication system, and an "overlapping-friendly" pipeline schedule. On microbenchmarks, our overall system outperforms existing ones by up to 10x across various tensor and mesh layouts. On end-to-end training of two large models, GPT-3 and U-Transformer, we improve throughput by 10% and 50%, respectively.

大多数经典的大满贯系统都依赖于静态场景假设，这限制了其在现实世界中的适用性。最近提出了最近的SLAM框架来同时跟踪相机和移动对象。但是，他们通常无法估计物体的规范姿势并表现出低对象跟踪精度。为了解决这个问题，我们提出了Twistslam ++，这是一种语义，动态的，全动态的，可融合立体声图像和LiDAR信息。使用语义信息，我们跟踪可能移动对象，并将它们与LIDAR扫描中的3D对象检测相关联，以获得其姿势和尺寸。然后，我们对连续对象扫描进行注册以完善对象姿势估计。最后，使用对象扫描来估计对象的形状，并约束MAP点位于BA内的估计表面上。我们在经典的基准上表明，基于多模式信息的这种融合方法提高了对象跟踪的准确性。

从随机实验获得的数据培训模型是做出良好决策的理想选择。但是，随机实验通常是耗时的，昂贵的，冒险的，不可行的或不道德的，决策者别无选择，只能依靠培训模型时在历史策略下收集的观察数据。这不仅为实践中的决策政策发挥了最佳作用，还为不同的数据收集协议对数据培训的各种政策的绩效的影响，或者在问题上的稳健性方面的稳健性，对问题的绩效提出了疑问诸如观察结果中的动作或奖励 - 特定延迟之类的特征。我们的目的是为了在LinkedIn优化销售渠道分配的问题回答此类问题，其中销售帐户（线索）需要分配给三个渠道之一，目的是在一段时间内最大程度地提高成功转换的数量。关键问题特征构成了观察分配结果的随机延迟，其分布既是通道和结果依赖性的。我们构建了一个离散的时间模拟，可以处理我们的问题功能并将其用于评估：a）基于历史规则的策略； b）有监督的机器学习政策（XGBOOST）； c）多臂强盗（MAB）策略，在涉及的不同情况下：i）用于培训的数据收集（观察性与随机分组）； ii）铅转换方案； iii）延迟分布。我们的仿真结果表明，Linucb是一种简单的mAB策略，始终优于其他策略，相对于基于规则的策略，实现了18-47％的提升

ICECUBE是一种用于检测1 GEV和1 PEV之间大气和天体中微子的光学传感器的立方公斤阵列，该阵列已部署1.45 km至2.45 km的南极的冰盖表面以下1.45 km至2.45 km。来自ICE探测器的事件的分类和重建在ICeCube数据分析中起着核心作用。重建和分类事件是一个挑战，这是由于探测器的几何形状，不均匀的散射和冰中光的吸收，并且低于100 GEV的光，每个事件产生的信号光子数量相对较少。为了应对这一挑战，可以将ICECUBE事件表示为点云图形，并将图形神经网络（GNN）作为分类和重建方法。 GNN能够将中微子事件与宇宙射线背景区分开，对不同的中微子事件类型进行分类，并重建沉积的能量，方向和相互作用顶点。基于仿真，我们提供了1-100 GEV能量范围的比较与当前ICECUBE分析中使用的当前最新最大似然技术，包括已知系统不确定性的影响。对于中微子事件分类，与当前的IceCube方法相比，GNN以固定的假阳性速率（FPR）提高了信号效率的18％。另外，GNN在固定信号效率下将FPR的降低超过8（低于半百分比）。对于能源，方向和相互作用顶点的重建，与当前最大似然技术相比，分辨率平均提高了13％-20％。当在GPU上运行时，GNN能够以几乎是2.7 kHz的中位数ICECUBE触发速率的速率处理ICECUBE事件，这打开了在在线搜索瞬态事件中使用低能量中微子的可能性。