因果图作为因果建模的有效和强大的工具，通常被假定为有向的无环图（DAG）。但是，推荐系统通常涉及反馈循环，该反馈循环定义为推荐项目的循环过程，将用户反馈纳入模型更新以及重复该过程。结果，重要的是将循环纳入因果图中，以准确地对推荐系统进行动态和迭代数据生成过程。但是，反馈回路并不总是有益的，因为随着时间的流逝，它们可能会鼓励越来越狭窄的内容暴露，如果无人看管的话，可能会导致回声室。结果，重要的是要了解何时会导致Echo Chambers以及如何减轻回声室而不会损害建议性能。在本文中，我们设计了一个带有循环的因果图，以描述推荐的动态过程。然后，我们采取马尔可夫工艺来分析回声室的数学特性，例如导致回声腔的条件。受理论分析的启发，我们提出了一个动态的因果协作过滤（$ \ partial $ ccf）模型，该模型估算了用户基于后门调整的项目的干预后偏好，并通过反事实推理减轻了Echo Echo Chamber。在现实世界数据集上进行了多个实验，结果表明，我们的框架可以比其他最先进的框架更好地减轻回声室，同时通过基本建议模型实现可比的建议性能。

研究人员对科学发现多年来，研究人员已经实施了观察 - 假设 - 预测 - 实验循环的研究范式。然而，随着MEGA级和毫米科学研究的数据爆炸，有时候很难手动分析数据并提出新的假设来推动科学发现的周期。在本文中，我们介绍了一个可解释的AI辅助范式的科学发现。关键是使用可解释的AI（XAI）来帮助推导数据或模型解释和科学发现。我们展示了如何计算和数据密集型方法 - 以及实验和理论方法 - 可以无缝融合为科学研究。为了展示AI辅助科学发现过程，并为我们历史上一些最伟大的思想付出了尊重，我们展示了Kepler的行星运动和牛顿定律的普遍引力的定律可以通过基于Tycho的（可解释）的AI重新发现Brahe的天文观测数据，其作品在16-17世纪领先科学革命。这项工作还强调了可解释的AI（与黑匣子AI）在科学发现中的重要性，以帮助人类防止或更好地为未来可能发生的技术奇点做好准备。

Neural Radiance Field (NeRF) is a powerful tool to faithfully generate novel views for scenes with only sparse captured images. Despite its strong capability for representing 3D scenes and their appearance, its editing ability is very limited. In this paper, we propose a simple but effective extension of vanilla NeRF, named PaletteNeRF, to enable efficient color editing on NeRF-represented scenes. Motivated by recent palette-based image decomposition works, we approximate each pixel color as a sum of palette colors modulated by additive weights. Instead of predicting pixel colors as in vanilla NeRFs, our method predicts additive weights. The underlying NeRF backbone could also be replaced with more recent NeRF models such as KiloNeRF to achieve real-time editing. Experimental results demonstrate that our method achieves efficient, view-consistent, and artifact-free color editing on a wide range of NeRF-represented scenes.

Sleep stage recognition is crucial for assessing sleep and diagnosing chronic diseases. Deep learning models, such as Convolutional Neural Networks and Recurrent Neural Networks, are trained using grid data as input, making them not capable of learning relationships in non-Euclidean spaces. Graph-based deep models have been developed to address this issue when investigating the external relationship of electrode signals across different brain regions. However, the models cannot solve problems related to the internal relationships between segments of electrode signals within a specific brain region. In this study, we propose a Pearson correlation-based graph attention network, called PearNet, as a solution to this problem. Graph nodes are generated based on the spatial-temporal features extracted by a hierarchical feature extraction method, and then the graph structure is learned adaptively to build node connections. Based on our experiments on the Sleep-EDF-20 and Sleep-EDF-78 datasets, PearNet performs better than the state-of-the-art baselines.

实体对齐（EA）的目的是在不同的知识图（kgs）中找到指代现实世界中同一对象的实体。最近的研究结合了时间信息，以增强KGS的表示。暂时KGS（TKG）之间的EA的现有方法利用时间感知的注意机制将关系和时间信息纳入实体嵌入中。该方法通过使用时间信息优于先前的方法。但是，我们认为，由于大多数TKG具有统一的时间表示，因此不必学习kgs中的时间信息的嵌入。因此，我们提出了一个简单的图形神经网络（GNN）模型，并结合了时间信息匹配机制，该模型以更少的时间和更少的参数实现了更好的性能。此外，由于对齐种子很难在现实世界应用中标记，因此我们还提出了一种通过TKG的时间信息生成无监督比对种子的方法。公共数据集的广泛实验表明，我们的监督方法显着优于先前的方法，而无监督的方法具有竞争性能。

用于检测CT肺血管造影（CTPA）图像上的肺栓塞（PES）的自动化方法是高需求。现有方法通常采用单独的步骤进行PE候选检测和假阳性去除，而不考虑另一步骤的能力。结果，大多数现有方法通常遭受高误率，以达到可接受的敏感性。本研究介绍了一个端到端的培训卷积神经网络（CNN），其中两个步骤共同优化。所提出的CNN由三个连接子网组成：1）一种用于检测包含可疑PES的多维数据集的新型3D候选提案网络，2）用于生成用于候选的固定血管对齐图像表示的3D空间转换子网，以及3）2D分类网络将转换立方体的三个横截面作为输入，消除了误报。我们使用PE挑战的20个CTPA测试数据集评估了我们的方法，在0mm，2mm和5mm定位误差下，实现了78.9％，80.7％和80.7％的灵敏度，2mm和5mm定位误差，其优于状态 - 最新方法。我们进一步在我们自己的数据集中进一步评估了我们的系统，该数据集由129个CTPA数据组成，共269个栓子。我们的系统在0mm，2mm和5mm定位误差下每卷的2个假阳性达到63.2％，78.9％和86.8％的灵敏度。

Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. We propose a highly effective unsupervised generative adversarial network, dubbed Enlight-enGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Instead of supervising the learning using ground truth data, we propose to regularize the unpaired training using the information extracted from the input itself, and benchmark a series of innovations for the low-light image enhancement problem, including a global-local discriminator structure, a selfregularized perceptual loss fusion, and the attention mechanism. Through extensive experiments, our proposed approach outperforms recent methods under a variety of metrics in terms of visual quality and subjective user study. Thanks to the great flexibility brought by unpaired training, EnlightenGAN is demonstrated to be easily adaptable to enhancing real-world images from various domains. Our codes and pre-trained models are available at: https://github.com/VITA-Group/EnlightenGAN.

Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency. We believe the insufficient utilization of training signals should be responsible. To alleviate this issue, we introduce a conceptually simple yet learning-efficient MIM training scheme, termed Disjoint Masking with Joint Distillation (DMJD). For disjoint masking (DM), we sequentially sample multiple masked views per image in a mini-batch with the disjoint regulation to raise the usage of tokens for reconstruction in each image while keeping the masking rate of each view. For joint distillation (JD), we adopt a dual branch architecture to respectively predict invisible (masked) and visible (unmasked) tokens with superior learning targets. Rooting in orthogonal perspectives for training efficiency improvement, DM and JD cooperatively accelerate the training convergence yet not sacrificing the model generalization ability. Concretely, DM can train ViT with half of the effective training epochs (3.7 times less time-consuming) to report competitive performance. With JD, our DMJD clearly improves the linear probing classification accuracy over ConvMAE by 5.8%. On fine-grained downstream tasks like semantic segmentation, object detection, etc., our DMJD also presents superior generalization compared with state-of-the-art SSL methods. The code and model will be made public at https://github.com/mx-mark/DMJD.

Cohn and Umans proposed a framework for developing fast matrix multiplication algorithms based on the embedding computation in certain groups algebras. In subsequent work with Kleinberg and Szegedy, they connected this to the search for combinatorial objects called strong uniquely solvable puzzles (strong USPs). We begin a systematic computer-aided search for these objects. We develop and implement constraint-based algorithms build on reductions to $\mathrm{SAT}$ and $\mathrm{IP}$ to verify that puzzles are strong USPs, and to search for large strong USPs. We produce tight bounds on the maximum size of a strong USP for width $k \le 5$, construct puzzles of small width that are larger than previous work, and improve the upper bounds on strong USP size for $k \le 12$. Although our work only deals with puzzles of small-constant width, the strong USPs we find imply matrix multiplication algorithms that run in $O(n^\omega)$ time with exponent $\omega \le 2.66$. While our algorithms do not beat the fastest algorithms, our work provides evidence and, perhaps, a path to finding families of strong USPs that imply matrix multiplication algorithms that are more efficient than those currently known.

This paper presents a practical global optimization algorithm for the K-center clustering problem, which aims to select K samples as the cluster centers to minimize the maximum within-cluster distance. This algorithm is based on a reduced-space branch and bound scheme and guarantees convergence to the global optimum in a finite number of steps by only branching on the regions of centers. To improve efficiency, we have designed a two-stage decomposable lower bound, the solution of which can be derived in a closed form. In addition, we also propose several acceleration techniques to narrow down the region of centers, including bounds tightening, sample reduction, and parallelization. Extensive studies on synthetic and real-world datasets have demonstrated that our algorithm can solve the K-center problems to global optimal within 4 hours for ten million samples in the serial mode and one billion samples in the parallel mode. Moreover, compared with the state-of-the-art heuristic methods, the global optimum obtained by our algorithm can averagely reduce the objective function by 25.8% on all the synthetic and real-world datasets.