Domain generalization (DG) aims to train a model to perform well in unseen domains under different distributions. This paper considers a more realistic yet more challenging scenario,namely Single Domain Generalization (Single-DG), where only a single source domain is available for training. To tackle this challenge, we first try to understand when neural networks fail to generalize? We empirically ascertain a property of a model that correlates strongly with its generalization that we coin as "model sensitivity". Based on our analysis, we propose a novel strategy of Spectral Adversarial Data Augmentation (SADA) to generate augmented images targeted at the highly sensitive frequencies. Models trained with these hard-to-learn samples can effectively suppress the sensitivity in the frequency space, which leads to improved generalization performance. Extensive experiments on multiple public datasets demonstrate the superiority of our approach, which surpasses the state-of-the-art single-DG methods.

本文解决了解释黑框回归模型异常预测的任务。当使用黑框模型（例如从许多传感器测量值中预测能源消耗的一个模型）时，我们通常会有某些观察到的样品可能会显着偏离其预测的情况。这可能是由于亚最佳黑盒模型，或仅仅​​是因为这些样品是异常值。无论哪种情况，理想情况下都希望计算``责任分数''，以指示输入变量负责异常输出的程度。在这项工作中，我们将此任务形式化为一个统计逆问题：给定模型偏离预期值，推断每个输入变量的责任分数。我们提出了一种称为似然补偿（LC）的新方法，该方法基于可能性原理，并计算对每个输入变量的校正。据我们所知，这是第一个计算实际有价值异常模型偏差的责任分数的原则性框架。我们将方法应用于现实世界中的建筑能源预测任务，并根据专家反馈确认其实用性。

为了回应对新的基于AI的技术的社会，法律和道德影响的认识，AI和ML少校会议和期刊现在鼓励或要求提交的论文包括道德影响声明并接受道德审查。这一举动引发了关于伦理在AI和数据科学研究中的作用的激烈辩论，有时会变成适得其反的名称和“取消”的威胁。我们认为，更加关注数据科学家的道德教育可能有助于弥合分离数据科学界的意识形态鸿沟。我们将这种深厚的意识形态冲突诊断为原子主义者和整体者之间的一项冲突。除其他事项外，原子主义者认为，事实是并且应该与价值观分开的想法，而整体者认为事实和价值观是并且应该彼此之间的不可分割。我们的目标是鼓励跨学科和减少学科两极分化的目标，我们借鉴了从哲学和法律到社会理论和人文心理学等各种历史来源，以描述每个意识形态的信仰和假设。最后，我们呼吁数据科学界内的原子主义者和整体者在道德分歧期间表现出更大的同理心，并提出四种有针对性的策略，以确保数据科学研究受益社会。

近年来，人们对可解释的AI（XAI）领域的兴趣激增，文献中提出了很多算法。但是，关于如何评估XAI的共识缺乏共识阻碍了该领域的发展。我们强调说，XAI并不是一组整体技术 - 研究人员和从业人员已经开始利用XAI算法来构建服务于不同使用环境的XAI系统，例如模型调试和决策支持。然而，对XAI的算法研究通常不会考虑到这些多样化的下游使用环境，从而对实际用户产生有限的有效性甚至意想不到的后果，以及从业者做出技术选择的困难。我们认为，缩小差距的一种方法是开发评估方法，这些方法在这些用法上下文中说明了不同的用户需求。为了实现这一目标，我们通过考虑XAI评估标准对XAI的原型用法上下文的相对重要性，介绍了情境化XAI评估的观点。为了探索XAI评估标准的上下文依赖性，我们进行了两项调查研究，一项与XAI主题专家，另一项与人群工人进行。我们的结果敦促通过使用使用的评估实践进行负责任的AI研究，并在不同使用环境中对XAI的用户需求有细微的了解。

Many works in explainable AI have focused on explaining black-box classification models. Explaining deep reinforcement learning (RL) policies in a manner that could be understood by domain users has received much less attention. In this paper, we propose a novel perspective to understanding RL policies based on identifying important states from automatically learned meta-states. The key conceptual difference between our approach and many previous ones is that we form meta-states based on locality governed by the expert policy dynamics rather than based on similarity of actions, and that we do not assume any particular knowledge of the underlying topology of the state space. Theoretically, we show that our algorithm to find meta-states converges and the objective that selects important states from each meta-state is submodular leading to efficient high quality greedy selection. Experiments on four domains (four rooms, door-key, minipacman, and pong) and a carefully conducted user study illustrate that our perspective leads to better understanding of the policy. We conjecture that this is a result of our meta-states being more intuitive in that the corresponding important states are strong indicators of tractable intermediate goals that are easier for humans to interpret and follow.

在过去几年中，知识转移从复杂的高性能模型转移到更简单且潜在的低性能以提高其性能，这引起了人们的极大兴趣从小数据中构建和学习。该问题的已知方法（即知识蒸馏，模型压缩，profewight等）通常通过修改目标或重量训练的方案直接将信息（即单个/单跳）从复杂模型转移到所选的简单模型训练简单模型的示例。在本文中，我们通过动态选择和/或构建一系列降低复杂性的中间模型的序列，在其中将信息从复杂模型传输到简单模型，而比原始复杂模型不那么复杂。我们的方法可以使用前面提到的任何方法以及以1-HOP方式进行序列的连续模型之间传输信息，从而推广这些方法。在实际数据的实验中，我们观察到，对于1跳上的模型选择，我们将获得一致的收益，该模型平均超过2 \％，在特定情况下最多达到8 \％。我们还经验分析了多跳方法可能对传统的1跳方法有益的条件，并报告其他有趣的见解。据我们所知，这是第一份提出这种多跳的方法来执行知识转移的工作，鉴于我们认为这是一个重要的方法论贡献，这是一个高表现的复杂模型。

最近，提出了不变的风险最小化（IRM）作为解决分布外（OOD）概括的有前途的解决方案。但是，目前尚不清楚何时应优先于广泛的经验风险最小化（ERM）框架。在这项工作中，我们从样本复杂性的角度分析了这两个框架，从而迈出了一个坚定的一步，以回答这个重要问题。我们发现，根据数据生成机制的类型，这两种方法可能具有有限样本和渐近行为。例如，在协变量偏移设置中，我们看到两种方法不仅达到了相同的渐近解决方案，而且具有相似的有限样本行为，没有明显的赢家。但是，对于其他分布变化，例如涉及混杂因素或反毒物变量的变化，两种方法到达不同的渐近解决方案，在这些方法中，保证IRM可以接近有限样品状态中所需的OOD溶液，而ERM甚至偶然地偏向于渐近。我们进一步研究了不同因素（环境的数量，模型的复杂性和IRM惩罚权重）如何影响IRM的样本复杂性与其距离OOD溶液的距离有关

In this paper we propose a novel method that provides contrastive explanations justifying the classification of an input by a black box classifier such as a deep neural network. Given an input we find what should be minimally and sufficiently present (viz. important object pixels in an image) to justify its classification and analogously what should be minimally and necessarily absent (viz. certain background pixels). We argue that such explanations are natural for humans and are used commonly in domains such as health care and criminology. What is minimally but critically absent is an important part of an explanation, which to the best of our knowledge, has not been explicitly identified by current explanation methods that explain predictions of neural networks. We validate our approach on three real datasets obtained from diverse domains; namely, a handwritten digits dataset MNIST, a large procurement fraud dataset and a brain activity strength dataset. In all three cases, we witness the power of our approach in generating precise explanations that are also easy for human experts to understand and evaluate.

Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at least few task-relevant target domain training data are available for adaptation from the source to the target domain. However, this requires laborious model-tuning by the end-user who may prefer to have a system that works ``out-of-the-box." To address such practical scenarios, we identify a novel target domain (inference-time) VAD task where no target domain training data are available. To this end, we propose a new `Zero-shot Cross-domain Video Anomaly Detection (zxvad)' framework that includes a future-frame prediction generative model setup. Different from prior future-frame prediction models, our model uses a novel Normalcy Classifier module to learn the features of normal event videos by learning how such features are different ``relatively" to features in pseudo-abnormal examples. A novel Untrained Convolutional Neural Network based Anomaly Synthesis module crafts these pseudo-abnormal examples by adding foreign objects in normal video frames with no extra training cost. With our novel relative normalcy feature learning strategy, zxvad generalizes and learns to distinguish between normal and abnormal frames in a new target domain without adaptation during inference. Through evaluations on common datasets, we show that zxvad outperforms the state-of-the-art (SOTA), regardless of whether task-relevant (i.e., VAD) source training data are available or not. Lastly, zxvad also beats the SOTA methods in inference-time efficiency metrics including the model size, total parameters, GPU energy consumption, and GMACs.

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections to avoid the problem of vanishing gradients, they can be viewed as the numerical integration of a differential equation. In this extended abstract, we build upon this connection and propose a modification of the internal architecture of a transformer layer. The proposed model places the multi-head attention sublayer and the MLP sublayer parallel to each other. Our experiments show that this simple modification improves the performance of transformer networks in multiple tasks. Moreover, for the image classification task, we show that using neural ODE solvers with a sophisticated integration scheme further improves performance.