由于准备点云的标记数据用于训练语义分割网络是一个耗时的过程，因此已经引入了弱监督的方法，以从一小部分数据中学习。这些方法通常是基于对比损失的学习，同时自动从一组稀疏的用户注销标签中得出每个点伪标签。在本文中，我们的关键观察是，选择要注释的样品的选择与这些样品的使用方式一样重要。因此，我们介绍了一种对3D场景进行弱监督分割的方法，该方法将自我训练与主动学习结合在一起。主动学习选择注释点可能会导致训练有素的模型的性能改进，而自我培训则可以有效利用用户提供的标签来学习模型。我们证明我们的方法会导致一种有效的方法，该方法可改善场景细分对以前的作品和基线，同时仅需要少量的用户注释。

To apply federated learning to drug discovery we developed a novel platform in the context of European Innovative Medicines Initiative (IMI) project MELLODDY (grant n{\deg}831472), which was comprised of 10 pharmaceutical companies, academic research labs, large industrial companies and startups. The MELLODDY platform was the first industry-scale platform to enable the creation of a global federated model for drug discovery without sharing the confidential data sets of the individual partners. The federated model was trained on the platform by aggregating the gradients of all contributing partners in a cryptographic, secure way following each training iteration. The platform was deployed on an Amazon Web Services (AWS) multi-account architecture running Kubernetes clusters in private subnets. Organisationally, the roles of the different partners were codified as different rights and permissions on the platform and administrated in a decentralized way. The MELLODDY platform generated new scientific discoveries which are described in a companion paper.

在具有可再生生成的大量份额的网格中，由于负载和发电的波动性增加，运营商将需要其他工具来评估运营风险。正向不确定性传播问题的计算要求必须解决众多安全受限的经济调度（SCED）优化，是这种实时风险评估的主要障碍。本文提出了一个即时风险评估学习框架（Jitralf）作为替代方案。 Jitralf训练风险代理，每天每小时一个，使用机器学习（ML）来预测估计风险所需的数量，而无需明确解决SCED问题。这大大减轻了正向不确定性传播的计算负担，并允许快速，实时的风险估计。本文还提出了一种新颖的，不对称的损失函数，并表明使用不对称损失训练的模型的性能优于使用对称损耗函数的模型。在法国传输系统上评估了Jitralf，以评估运营储量不足的风险，减轻负载的风险和预期的运营成本。

在监视机器学习系统时，均匀性的两样本测试构成了现有的漂移检测构建方法的基础。它们用于测试证据表明，最近部署数据的分布与历史参考数据的基础数据不同。但是，通常，诸如时间诱导的相关性等各种因素意味着，预计最近的部署数据不会形成I.I.D.来自历史数据分布的样本。取而代之的是，我们可能希望测试允许更改的\ textit {Context}条件上的分布差异。为了促进这一点，我们从因果推理域借用机械，以开发出更通用的漂移检测框架，建立在有条件分布治疗效果的两样本测试基础上。我们建议根据最大条件平均差异对框架进行特定的实例化。然后，我们提供了一项实证研究，证明了其对实践感兴趣的各种漂移检测问题的有效性，例如以对其各自的流行率不敏感的方式检测数据基础分布的漂移。该研究还证明了对成像网尺度视力问题的适用性。

Reading comprehension of legal text can be a particularly challenging task due to the length and complexity of legal clauses and a shortage of expert-annotated datasets. To address this challenge, we introduce the Merger Agreement Understanding Dataset (MAUD), an expert-annotated reading comprehension dataset based on the American Bar Association's 2021 Public Target Deal Points Study, with over 39,000 examples and over 47,000 total annotations. Our fine-tuned Transformer baselines show promising results, with models performing well above random on most questions. However, on a large subset of questions, there is still room for significant improvement. As the only expert-annotated merger agreement dataset, MAUD is valuable as a benchmark for both the legal profession and the NLP community.

We demonstrate how efficient autonomous drone swarms can be in detecting and tracking occluded targets in densely forested areas, such as lost people during search and rescue missions. Exploration and optimization of local viewing conditions, such as occlusion density and target view obliqueness, provide much faster and much more reliable results than previous, blind sampling strategies that are based on pre-defined waypoints. An adapted real-time particle swarm optimization and a new objective function are presented that are able to deal with dynamic and highly random through-foliage conditions. Synthetic aperture sensing is our fundamental sampling principle, and drone swarms are employed to approximate the optical signals of extremely wide and adaptable airborne lenses.

Many problems involve the use of models which learn probability distributions or incorporate randomness in some way. In such problems, because computing the true expected gradient may be intractable, a gradient estimator is used to update the model parameters. When the model parameters directly affect a probability distribution, the gradient estimator will involve score function terms. This paper studies baselines, a variance reduction technique for score functions. Motivated primarily by reinforcement learning, we derive for the first time an expression for the optimal state-dependent baseline, the baseline which results in a gradient estimator with minimum variance. Although we show that there exist examples where the optimal baseline may be arbitrarily better than a value function baseline, we find that the value function baseline usually performs similarly to an optimal baseline in terms of variance reduction. Moreover, the value function can also be used for bootstrapping estimators of the return, leading to additional variance reduction. Our results give new insight and justification for why value function baselines and the generalized advantage estimator (GAE) work well in practice.

We propose a fairness-aware learning framework that mitigates intersectional subgroup bias associated with protected attributes. Prior research has primarily focused on mitigating one kind of bias by incorporating complex fairness-driven constraints into optimization objectives or designing additional layers that focus on specific protected attributes. We introduce a simple and generic bias mitigation approach that prevents models from learning relationships between protected attributes and output variable by reducing mutual information between them. We demonstrate that our approach is effective in reducing bias with little or no drop in accuracy. We also show that the models trained with our learning framework become causally fair and insensitive to the values of protected attributes. Finally, we validate our approach by studying feature interactions between protected and non-protected attributes. We demonstrate that these interactions are significantly reduced when applying our bias mitigation.

Automatic segmentation is essential for the brain tumor diagnosis, disease prognosis, and follow-up therapy of patients with gliomas. Still, accurate detection of gliomas and their sub-regions in multimodal MRI is very challenging due to the variety of scanners and imaging protocols. Over the last years, the BraTS Challenge has provided a large number of multi-institutional MRI scans as a benchmark for glioma segmentation algorithms. This paper describes our contribution to the BraTS 2022 Continuous Evaluation challenge. We propose a new ensemble of multiple deep learning frameworks namely, DeepSeg, nnU-Net, and DeepSCAN for automatic glioma boundaries detection in pre-operative MRI. It is worth noting that our ensemble models took first place in the final evaluation on the BraTS testing dataset with Dice scores of 0.9294, 0.8788, and 0.8803, and Hausdorf distance of 5.23, 13.54, and 12.05, for the whole tumor, tumor core, and enhancing tumor, respectively. Furthermore, the proposed ensemble method ranked first in the final ranking on another unseen test dataset, namely Sub-Saharan Africa dataset, achieving mean Dice scores of 0.9737, 0.9593, and 0.9022, and HD95 of 2.66, 1.72, 3.32 for the whole tumor, tumor core, and enhancing tumor, respectively. The docker image for the winning submission is publicly available at (https://hub.docker.com/r/razeineldin/camed22).

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.