The instrumental variable (IV) approach is a widely used way to estimate the causal effects of a treatment on an outcome of interest from observational data with latent confounders. A standard IV is expected to be related to the treatment variable and independent of all other variables in the system. However, it is challenging to search for a standard IV from data directly due to the strict conditions. The conditional IV (CIV) method has been proposed to allow a variable to be an instrument conditioning on a set of variables, allowing a wider choice of possible IVs and enabling broader practical applications of the IV approach. Nevertheless, there is not a data-driven method to discover a CIV and its conditioning set directly from data. To fill this gap, in this paper, we propose to learn the representations of the information of a CIV and its conditioning set from data with latent confounders for average causal effect estimation. By taking advantage of deep generative models, we develop a novel data-driven approach for simultaneously learning the representation of a CIV from measured variables and generating the representation of its conditioning set given measured variables. Extensive experiments on synthetic and real-world datasets show that our method outperforms the existing IV methods.

在科学研究和现实世界应用的许多领域中，非实验数据的因果效应的无偏估计对于理解数据的基础机制以及对有效响应或干预措施的决策至关重要。从不同角度对这个具有挑战性的问题进行了大量研究。对于数据中的因果效应估计，始终做出诸如马尔可夫财产，忠诚和因果关系之类的假设。在假设下，仍然需要一组协变量或基本因果图之类的全部知识。一个实用的挑战是，在许多应用程序中，没有这样的全部知识或只有某些部分知识。近年来，研究已经出现了基于图形因果模型的搜索策略，以从数据中发现有用的知识，以进行因果效应估计，并具有一些温和的假设，并在应对实际挑战方面表现出了诺言。在这项调查中，我们回顾了方法，并关注数据驱动方法所面临的挑战。我们讨论数据驱动方法的假设，优势和局限性。我们希望这篇综述将激励更多的研究人员根据图形因果建模设计更好的数据驱动方法，以解决因果效应估计的具有挑战性的问题。

许多研究都致力于学习公平代表的问题。但是，它们并未明确表示潜在表示之间的关系。在许多实际应用中，潜在表示之间可能存在因果关系。此外，大多数公平的表示学习方法都集中在群体级别的公平性上，并基于相关性，忽略了数据基础的因果关系。在这项工作中，我们从理论上证明，使用结构化表示可以使下游预测模型实现反事实公平，然后我们提出了反事实公平性变异自动编码器（CF-VAE）以获得有关领域知识的结构化表示。实验结果表明，所提出的方法比基准公平方法获得了更好的公平性和准确性性能。

本文研究了通过机器学习模型估计特征对特定实例预测的贡献的问题，以及功能对模型的总体贡献。特征（变量）对预测结果的因果效应反映了该特征对预测的贡献。一个挑战是，如果没有已知的因果图，就无法从数据中估算大多数现有的因果效应。在本文中，我们根据假设的理想实验定义了解释性因果效应。该定义给不可知论的解释带来了一些好处。首先，解释是透明的，具有因果关系。其次，解释性因果效应估计可以数据驱动。第三，因果效应既提供了特定预测的局部解释，又提供了一个全局解释，显示了一个特征在预测模型中的总体重要性。我们进一步提出了一种基于解释性因果效应来解释的方法和组合变量的方法。我们显示了对某些现实世界数据集的实验的定义和方法。

不观察到的混淆是观测数据的因果效应估计的主要障碍。仪器变量（IVS）广泛用于存在潜在混淆时的因果效应估计。利用标准IV方法，当给定的IV有效时，可以获得无偏估计，但标准IV的有效性要求是严格和不可能的。已经提出了通过调节一组观察变量（称为条件IV的调节装置）来放松标准IV的要求。然而，用于查找条件IV的调节集的标准需要完整的因果结构知识或指向的非循环图（DAG），其代表观察到和未观察的变量的因果关系。这使得无法发现直接从数据设置的调节。在本文中，通过利用潜在变量的因果推断中的最大祖先图（MAGS），我们提出了一种新型的MAG中的IV，祖先IV，并开发了支持给定祖传的调节装置的数据驱动的发现iv在mag。基于该理论，我们在MAG和观测数据中开发了一种与祖先IV的非偏见因果效应估计的算法。与现有IV方法相比，对合成和实际数据集的广泛实验表明了算法的性能。

本地到全球学习方法在贝叶斯网络（BN）结构学习中起着重要作用。现有的本地到全局学习算法首先通过在数据集中学习每个变量的MB（马尔可夫毯子）或PC（家长和儿童）来构建DAG（Markov毯子）或PC（父母和儿童），然后在骨架中定向边缘。然而，现有的MB或PC学习方法通​​常是昂贵的昂贵昂贵，特别是具有大型BN，导致局部到全局学习算法效率低下。为了解决问题，在本文中，我们使用特征选择开发了一个有效的本地到全局学习方法。具体地，我们首先分析众所周知的最小冗余和最大相关性（MRMR）特征选择方法的基本原理，用于学习变量的PC集。基于分析，我们提出了一种高效的F2SL（基于特征选择的结构学习）方法，以局部 - 全局BN结构学习。 F2SL方法首先采用MRMR方法来学习DAG骨架，然后在骨架中的边缘。采用独立测试或进行定向边缘的分数函数，我们将F2SL方法实例化为两个新算法，F2SL-C（使用独立测试）和F2SL-S（使用得分函数）。与最先进的本地到全局BN学习算法相比，实验验证了本文中所提出的算法比比较算法更有效，提供竞争性结构学习质量。

在个性化决策中，需要证据来确定诉讼（治疗）是否适合个人。可以通过对亚组中的治疗效应异质性进行建模来获得此类证据。现有的可解释的建模方法采用自上而下的方法来寻找具有异质治疗效果的亚组，它们可能会错过个人最具体和最相关的环境。在本文中，我们设计了\ emph {治疗效果模式（TEP）}来表示数据中的治疗效果异质性。为了实现TEP的可解释呈现，我们使用围绕结果的局部因果结构，以明确说明如何在建模中使用这些重要变量。我们还得出了一个公正估计\ emph {条件平均因果效应（CATE）}的公式，它使用我们的问题设置中的局部结构进行了估计。在发现过程中，我们旨在最大程度地减少以模式表示的每个子组中的异质性。我们提出了一种自下而上的搜索算法，以发现适合个性化决策的最具体情况的最特定模式。实验表明，所提出的方法模型治疗效果的异质性比合成和现实世界数据集中的其他三种基于树的方法更好。

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.

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset. However, the existing dataset distillation techniques mainly aim at achieving the best trade-off between resource usage efficiency and model utility. The security risks stemming from them have not been explored. This study performs the first backdoor attack against the models trained on the data distilled by dataset distillation models in the image domain. Concretely, we inject triggers into the synthetic data during the distillation procedure rather than during the model training stage, where all previous attacks are performed. We propose two types of backdoor attacks, namely NAIVEATTACK and DOORPING. NAIVEATTACK simply adds triggers to the raw data at the initial distillation phase, while DOORPING iteratively updates the triggers during the entire distillation procedure. We conduct extensive evaluations on multiple datasets, architectures, and dataset distillation techniques. Empirical evaluation shows that NAIVEATTACK achieves decent attack success rate (ASR) scores in some cases, while DOORPING reaches higher ASR scores (close to 1.0) in all cases. Furthermore, we conduct a comprehensive ablation study to analyze the factors that may affect the attack performance. Finally, we evaluate multiple defense mechanisms against our backdoor attacks and show that our attacks can practically circumvent these defense mechanisms.

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.