Graph Neural Networks (GNNs) are deep learning models designed to process attributed graphs. GNNs can compute cluster assignments accounting both for the vertex features and for the graph topology. Existing GNNs for clustering are trained by optimizing an unsupervised minimum cut objective, which is approximated by a Spectral Clustering (SC) relaxation. SC offers a closed-form solution that, however, is not particularly useful for a GNN trained with gradient descent. Additionally, the SC relaxation is loose and yields overly smooth cluster assignments, which do not separate well the samples. We propose a GNN model that optimizes a tighter relaxation of the minimum cut based on graph total variation (GTV). Our model has two core components: i) a message-passing layer that minimizes the $\ell_1$ distance in the features of adjacent vertices, which is key to achieving sharp cluster transitions; ii) a loss function that minimizes the GTV in the cluster assignments while ensuring balanced partitions. By optimizing the proposed loss, our model can be self-trained to perform clustering. In addition, our clustering procedure can be used to implement graph pooling in deep GNN architectures for graph classification. Experiments show that our model outperforms other GNN-based approaches for clustering and graph pooling.
translated by 谷歌翻译
最近,引入了亚图增强图神经网络(SGNN),以增强图形神经网络(GNN)的表达能力,事实证明,该功能不高于一维Weisfeiler-Leman同构测试。新的范式建议使用从输入图中提取的子图提高模型的表现力,但是额外的复杂性加剧了GNNS中本来可以具有挑战性的问题:解释其预测。在这项工作中,我们将PGEXPlainer(GNNS的最新解释者之一)改编为SGNN。拟议的解释器解释了所有不同子图的贡献,并可以产生人类可以解释的有意义的解释。我们在真实和合成数据集上执行的实验表明,我们的框架成功地解释了SGNN在图形分类任务上的决策过程。
translated by 谷歌翻译
时空时间序列的神经预测推动了几个相关应用领域的研究和工业创新。图神经网络(GNN)通常是预测体系结构的核心组成部分。但是,在大多数时空gnns中,计算复杂度比序列时间长度缩放到二次因子,图中链接的数量是图中的链接数,因此阻碍了这些模型在大图和长时间序列中的应用。尽管在静态图的背景下提出了提高可伸缩性的方法,但很少有研究工作专门用于时空情况。为了填补这一空白,我们提出了一个可扩展的体系结构,该体系结构利用了时间和空间动力学的有效编码。特别是,我们使用一个随机的复发神经网络将输入时间序列的历史嵌入到包括多尺度时间动力学的高维状态表示中。然后,使用图形邻接矩阵的不同功率沿空间维度沿空间维度传播,以生成以富含时空特征池的特征的节点嵌入。可以在不监督的方式中有效地预先计算所得的节点嵌入,然后将其馈送到馈送前向解码器,该解码器学会映射多尺度时空表示形式为预测。然后,可以通过对节点的嵌入而无需破坏任何依赖性,从而使训练过程在节点方面并行化,从而可以对大型网络进行可扩展性。相关数据集的经验结果表明,我们的方法可以与最新技术的状态竞争,同时大大减轻了计算负担。
translated by 谷歌翻译
光谱群集中使用的目标函数通常由两个术语组成:i)一个术语最小化群集分配的局部二次变化,并且;ii)一个平衡聚类分区并有助于避免退化解决方案的术语。本文表明,配备合适消息传递层的图形神经网络可以通过仅优化平衡项来生成良好的集群分配。归因图数据集的结果显示了拟议方法在聚类性能和计算时间方面的有效性。
translated by 谷歌翻译
在本文中,我们探讨了通过深度学习来检测C波段SAR图像中极性低的可能性。具体而言,我们介绍了一个新的数据集,该数据集由Sentinel-1图像组成,分为两个类别,分别代表海上中clo子的存在和不存在。该数据集是使用ERE5数据集作为基线构建的,它由2004年注释的图像组成。据我们所知,这是公开发布此类数据集的第一个数据集。该数据集用于训练深度学习模型以对标记的图像进行分类。该模型在独立的测试集上进行了评估,其F-1得分为0.95,表明可以从SAR图像中始终检测到极性低。应用于深度学习模型的可解释性技术表明,大气方面和旋风眼是分类的关键特征。此外,实验结果表明,即使:(i)由于SAR的宽度有限,该模型是正确的:(ii)特征部分被海冰覆盖,(iii)土地覆盖了显着图像的一部分。通过评估多个输入图像分辨率上的模型性能(像素大小为500m,1km和2km),发现较高的分辨率会产生最佳性能。这强调了使用高分辨率传感器(例如SAR来检测极性低)的潜力,与常规使用的传感器(例如散射计)相比。
translated by 谷歌翻译
This paper presents a novel probabilistic forecasting method called ensemble conformalized quantile regression (EnCQR). EnCQR constructs distribution-free and approximately marginally valid prediction intervals (PIs), which are suitable for nonstationary and heteroscedastic time series data. EnCQR can be applied on top of a generic forecasting model, including deep learning architectures. EnCQR exploits a bootstrap ensemble estimator, which enables the use of conformal predictors for time series by removing the requirement of data exchangeability. The ensemble learners are implemented as generic machine learning algorithms performing quantile regression, which allow the length of the PIs to adapt to local variability in the data. In the experiments, we predict time series characterized by a different amount of heteroscedasticity. The results demonstrate that EnCQR outperforms models based only on quantile regression or conformal prediction, and it provides sharper, more informative, and valid PIs.
translated by 谷歌翻译
我们提出了一种基于图形神经网络(GNN)的端到端框架,以平衡通用网格中的功率流。优化被帧为监督的顶点回归任务,其中GNN培训以预测每个网格分支的电流和功率注入,从而产生功率流量平衡。通过将电网表示为与顶点的分支的线图,我们可以培训一个更准确和强大的GNN来改变底层拓扑。此外,通过使用专门的GNN层,我们能够构建一个非常深的架构,该架构占图表上的大街区,同时仅实现本地化操作。我们执行三个不同的实验来评估:i)使用深入GNN模型时使用本地化而不是全球运营的好处和趋势; ii)图形拓扑中对扰动的弹性;和iii)能力同时在多个网格拓扑上同时培训模型以及新的看不见网格的概括性的改进。拟议的框架是有效的,而且与基于深度学习的其他求解器相比,不仅对网格组件上的物理量而且对拓扑的物理量具有鲁棒性。
translated by 谷歌翻译
In this paper, we address the problem of image splicing localization with a multi-stream network architecture that processes the raw RGB image in parallel with other handcrafted forensic signals. Unlike previous methods that either use only the RGB images or stack several signals in a channel-wise manner, we propose an encoder-decoder architecture that consists of multiple encoder streams. Each stream is fed with either the tampered image or handcrafted signals and processes them separately to capture relevant information from each one independently. Finally, the extracted features from the multiple streams are fused in the bottleneck of the architecture and propagated to the decoder network that generates the output localization map. We experiment with two handcrafted algorithms, i.e., DCT and Splicebuster. Our proposed approach is benchmarked on three public forensics datasets, demonstrating competitive performance against several competing methods and achieving state-of-the-art results, e.g., 0.898 AUC on CASIA.
translated by 谷歌翻译
Binary Neural Networks (BNNs) are showing tremendous success on realistic image classification tasks. Notably, their accuracy is similar to the state-of-the-art accuracy obtained by full-precision models tailored to edge devices. In this regard, BNNs are very amenable to edge devices since they employ 1-bit to store the inputs and weights, and thus, their storage requirements are low. Also, BNNs computations are mainly done using xnor and pop-counts operations which are implemented very efficiently using simple hardware structures. Nonetheless, supporting BNNs efficiently on mobile CPUs is far from trivial since their benefits are hindered by frequent memory accesses to load weights and inputs. In BNNs, a weight or an input is stored using one bit, and aiming to increase storage and computation efficiency, several of them are packed together as a sequence of bits. In this work, we observe that the number of unique sequences representing a set of weights is typically low. Also, we have seen that during the evaluation of a BNN layer, a small group of unique sequences is employed more frequently than others. Accordingly, we propose exploiting this observation by using Huffman Encoding to encode the bit sequences and then using an indirection table to decode them during the BNN evaluation. Also, we propose a clustering scheme to identify the most common sequences of bits and replace the less common ones with some similar common sequences. Hence, we decrease the storage requirements and memory accesses since common sequences are encoded with fewer bits. We extend a mobile CPU by adding a small hardware structure that can efficiently cache and decode the compressed sequence of bits. We evaluate our scheme using the ReAacNet model with the Imagenet dataset. Our experimental results show that our technique can reduce memory requirement by 1.32x and improve performance by 1.35x.
translated by 谷歌翻译
Question Answering (QA) is a growing area of research, often used to facilitate the extraction of information from within documents. State-of-the-art QA models are usually pre-trained on domain-general corpora like Wikipedia and thus tend to struggle on out-of-domain documents without fine-tuning. We demonstrate that synthetic domain-specific datasets can be generated easily using domain-general models, while still providing significant improvements to QA performance. We present two new tools for this task: A flexible pipeline for validating the synthetic QA data and training downstream models on it, and an online interface to facilitate human annotation of this generated data. Using this interface, crowdworkers labelled 1117 synthetic QA pairs, which we then used to fine-tune downstream models and improve domain-specific QA performance by 8.75 F1.
translated by 谷歌翻译