可解释的机器学习旨在了解复杂的黑盒系统的推理过程，这些系统因缺乏解释性而臭名昭著。一种不断增长的解释方法是通过反事实解释，这超出了为什么系统做出一定决定，以进一步提供有关用户可以采取哪些方法来改变结果的建议。反事实示例必须能够应对黑框分类器的原始预测，同时还满足实用应用程序的各种约束。这些限制存在于一个和另一个之间的权衡处，对现有作品提出了根本的挑战。为此，我们提出了一个基于随机学习的框架，可以有效地平衡反事实权衡。该框架由具有互补角色的一代和特征选择模块组成：前者的目标是建模有效的反事实的分布，而后者则以允许可区分训练和摊销优化的方式执行其他约束。我们证明了我们方法在产生可行和合理的反事实中的有效性，这些反事实比现有方法更多样化，尤其是比具有相同能力的对应物更有效的方式。

开发了用于解决顺序实验的最佳设计的贝叶斯方法在数学上是优雅的，但在计算上具有挑战性。最近，已经提出了使用摊销的技术来使这些贝叶斯方法实用，通过培训参数化的政策，该政策在部署时有效地设计了设计。但是，这些方法可能无法充分探索设计空间，需要访问可区分的概率模型，并且只能在连续的设计空间上进行优化。在这里，我们通过证明优化政策的问题可以减少到解决马尔可夫决策过程（MDP）来解决这些局限性。我们使用现代深度强化学习技术来解决等效的MDP。我们的实验表明，即使概率模型是黑匣子，我们的方法在部署时间也很有效，并且在连续和离散的设计空间上都表现出最先进的性能。

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.

In this paper, we propose a novel graph kernel, namely the Quantum-based Entropic Subtree Kernel (QESK), for Graph Classification. To this end, we commence by computing the Average Mixing Matrix (AMM) of the Continuous-time Quantum Walk (CTQW) evolved on each graph structure. Moreover, we show how this AMM matrix can be employed to compute a series of entropic subtree representations associated with the classical Weisfeiler-Lehman (WL) algorithm. For a pair of graphs, the QESK kernel is defined by computing the exponentiation of the negative Euclidean distance between their entropic subtree representations, theoretically resulting in a positive definite graph kernel. We show that the proposed QESK kernel not only encapsulates complicated intrinsic quantum-based structural characteristics of graph structures through the CTQW, but also theoretically addresses the shortcoming of ignoring the effects of unshared substructures arising in state-of-the-art R-convolution graph kernels. Moreover, unlike the classical R-convolution kernels, the proposed QESK can discriminate the distinctions of isomorphic subtrees in terms of the global graph structures, theoretically explaining the effectiveness. Experiments indicate that the proposed QESK kernel can significantly outperform state-of-the-art graph kernels and graph deep learning methods for graph classification problems.

The NASA Astrophysics Data System (ADS) is an essential tool for researchers that allows them to explore the astronomy and astrophysics scientific literature, but it has yet to exploit recent advances in natural language processing. At ADASS 2021, we introduced astroBERT, a machine learning language model tailored to the text used in astronomy papers in ADS. In this work we: - announce the first public release of the astroBERT language model; - show how astroBERT improves over existing public language models on astrophysics specific tasks; - and detail how ADS plans to harness the unique structure of scientific papers, the citation graph and citation context, to further improve astroBERT.

Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a policy is trained to maximize a learned value function while constrained by the behavior policy to avoid a significant distributional shift. In this paper, we propose our closed-form policy improvement operators. We make a novel observation that the behavior constraint naturally motivates the use of first-order Taylor approximation, leading to a linear approximation of the policy objective. Additionally, as practical datasets are usually collected by heterogeneous policies, we model the behavior policies as a Gaussian Mixture and overcome the induced optimization difficulties by leveraging the LogSumExp's lower bound and Jensen's Inequality, giving rise to a closed-form policy improvement operator. We instantiate offline RL algorithms with our novel policy improvement operators and empirically demonstrate their effectiveness over state-of-the-art algorithms on the standard D4RL benchmark.

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is especially important for semantic segmentation tasks involving 3D datasets that are often significantly smaller and more challenging to annotate than their image-based counterparts. Self-supervised pre-training on large unlabelled datasets is one way to reduce the amount of manual annotations needed. Previous work has focused on pre-training with point cloud data exclusively; this approach often requires two or more registered views. In the present work, we combine image and point cloud modalities, by first learning self-supervised image features and then using these features to train a 3D model. By incorporating image data, which is often included in many 3D datasets, our pre-training method only requires a single scan of a scene. We demonstrate that our pre-training approach, despite using single scans, achieves comparable performance to other multi-scan, point cloud-only methods.

In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs. Different from most existing classical graph kernels, the proposed HAQJSK kernels can incorporate hierarchical aligned structure information between graphs and transform graphs of random sizes into fixed-sized aligned graph structures, i.e., the Hierarchical Transitive Aligned Adjacency Matrix of vertices and the Hierarchical Transitive Aligned Density Matrix of the Continuous-Time Quantum Walk (CTQW). For a pair of graphs to hand, the resulting HAQJSK kernels are defined by measuring the Quantum Jensen-Shannon Divergence (QJSD) between their transitive aligned graph structures. We show that the proposed HAQJSK kernels not only reflect richer intrinsic global graph characteristics in terms of the CTQW, but also address the drawback of neglecting structural correspondence information arising in most existing R-convolution kernels. Furthermore, unlike the previous Quantum Jensen-Shannon Kernels associated with the QJSD and the CTQW, the proposed HAQJSK kernels can simultaneously guarantee the properties of permutation invariant and positive definiteness, explaining the theoretical advantages of the HAQJSK kernels. Experiments indicate the effectiveness of the proposed kernels.

Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on most skills relevant to the task at hand. Empirical work on this problem is not straightforward, since we do not yet have systems that broadly exceed our abilities. This paper discusses one of the major ways we think about this problem, with a focus on how to turn it into one that can be productively studied empirically. We first present an experimental design centered on choosing tasks for which human specialists succeed but unaided humans and current general AI systems fail. We then present a proof-of-concept experiment following meant to demonstrate a key feature of this experimental design and show its viability with two question-answering tasks: MMLU and time-limited QuALITY. On these tasks, we find that human participants who interact with an unreliable large-language-model dialog assistant through chat -- a trivial baseline strategy for scalable oversight -- substantially outperform both the model alone and their own unaided performance. These results are an encouraging sign that scalable oversight will be tractable to study with present models and bolster recent findings that large language models can productively assist humans with difficult tasks.

行星漫游者任务必须利用基于机器学习的感知来继续发生地球外探索，几乎没有人类的存在。火星地形细分对于漫游车导航和避免危害至关重要，以执行进一步的探索性任务，例如土壤样品收集和寻找有机化合物。当前的火星地形细分模型需要大量标记的数据才能实现可接受的性能，还需要重新培训以在不同域中的部署，即不同的漫游者任务或不同的任务，即地质识别和导航。这项研究提出了一种半监督的学习方法，该方法利用了骨干的无监督对比度预处理，用于对火星表面的多效率语义分割。该模型将通过使用混合域训练套件来确保具有多样性的混合域训练套件，从而扩展到当前的火星分割能力，以便在不同的火星漫游者任务中部署以进行地形导航。使用平均像素精度的评估结果表明，与单个领域训练和监督培训相比，半监督的混合域方法通过达到火星科学实验室的好奇心漫游者的精度为97％，MARS 2020 Perseverance Perseverance Rover提高了精度。 。此外，使用召回度量与标准的跨透镜损失相比，使用召回度量的损失功能提供不同的权重方法将对少数族裔或稀有类别的模型提高了30％以上。这些结果可以以数据效率的方式为Rover任务提供未来的多任务和多任务语义细分。