Unsupervised graph representation learning (UGRL) based on graph neural networks (GNNs), has received increasing attention owing to its efficacy in handling graph-structured data. However, existing UGRL methods ideally assume that the node features are noise-free, which makes them fail to distinguish between useful information and noise when applied to real data with noisy features, thus affecting the quality of learned representations. This urges us to take node noisy features into account in real-world UGRL. With empirical analysis, we reveal that feature propagation, the essential operation in GNNs, acts as a "double-edged sword" in handling noisy features - it can both denoise and diffuse noise, leading to varying feature quality across nodes, even within the same node at different hops. Building on this insight, we propose a novel UGRL method based on Multi-hop feature Quality Estimation (MQE for short). Unlike most UGRL models that directly utilize propagation-based GNNs to generate representations, our approach aims to learn representations through estimating the quality of propagated features at different hops. Specifically, we introduce a Gaussian model that utilizes a learnable "meta-representation" as a condition to estimate the expectation and variance of multi-hop propagated features via neural networks. In this way, the "meta representation" captures the semantic and structural information underlying multiple propagated features but is naturally less susceptible to interference by noise, thereby serving as high-quality node representations beneficial for downstream tasks. Extensive experiments on multiple real-world datasets demonstrate that MQE in learning reliable node representations in scenarios with diverse types of feature noise.
Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head
Meta AI；Cranberry-Lemon University（蔓越莓柠檬大学）；University of the Witwatersrand（威特沃特斯兰德大学）
如果我们希望学习廉价、可靠和可转移的模型，那么代价高昂、嘈杂和过度专业化的标签将被搁置一边，转而支持无监督学习。为此，谱嵌入、自监督学习或生成式建模提供了有竞争力的解决方案。然而，这些方法带来了许多挑战，\textit{e.g.}估计测地线距离，指定投影仪架构和抗崩溃损失，或指定解码器架构和重建损失。相比之下，我们引入了一个简单的可解释的替代方案-创造的\textbf{DIET} -从未标记的数据中学习表示，没有这些挑战。\textbf{DIET}非常简单：采用自己喜欢的分类设置，并使用\textbf{D} atum \textbf{I} nd \textbf{E} x作为其\textbf{T}目标类，\textit{i.e. each sample is its own class}，无需进一步更改。\textbf{DIET}不需要解码器/投影器网络，不基于正对也不基于重构，不引入超参数，并且可以跨数据集和架构进行开箱即用。尽管\textbf{DIET}很简单，但学习到的表示具有高质量，并且通常与最先进的\textit{e.g.}相当，在DIET的学习表示之上使用线性分类器，在CIFAR 100上使用Resnet 101达到$71.4\%$，在TinyImagenet上使用Resnext 50达到$52.5\%$。
Isomorphic-Consistent Variational Graph Auto-Encoders for Multi-Level Graph Representation Learning
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Graph Neural Network and Transformer Integration for Unsupervised System Anomaly Discovery
Georgia Institute of Technology（佐治亚理工学院）；University of Pennsylvania（宾夕法尼亚大学）；Rose-Hulman Institute of Technology（罗斯-霍曼理工学院）；University of California, Berkeley（加利福尼亚大学伯克利分校）
Big Earth Data and Machine Learning for Sustainable and Resilient Agriculture
National Technical University of Athens（雅典国立技术大学）；NOA（国家天文台（注：此处NOA常见全称National Observatory of Athens，即雅典国家天文台））；CERTH（希腊信息技术研究与技术中心（注：CERTH常见全称Center for Research and Technology Hellas，即希腊研究与技术中心））；Wageningen University and Research（瓦赫宁根大学及研究中心）
Voxel-wise classification for porosity investigation of additive manufactured parts with 3D unsupervised and (deeply) supervised neural networks
imec-Vision Lab（imec-Vision实验室）；University of Antwerp（安特卫普大学）；DynXlab: Center for 4D Quantitative X-ray Imaging and Analysis（DynXlab：四维定量X射线成像与分析中心）；Otto von Guericke University（奥托·冯·格里克大学）；Genomics Research Centre, Human Technopole（人类技术研究院基因组学研究中心）；Materialise NV.（Materialise NV.公司）；Flanders Make vzw.（佛兰德制造vzw.机构）
