Diabetic Retinopathy (DR) is a significant cause of blindness globally,
highlighting the urgent need for early detection and effective treatment.
Recent advancements in Machine Learning (ML) techniques have shown promise in
DR detection, but the availability of labeled data often limits their
performance. This research proposes a novel Semi-Supervised Graph Learning SSGL
algorithm tailored for DR detection, which capitalizes on the relationships
between labelled and unlabeled data to enhance accuracy. The work begins by
investigating data augmentation and preprocessing techniques to address the
challenges of image quality and feature variations. Techniques such as image
cropping, resizing, contrast adjustment, normalization, and data augmentation
are explored to optimize feature extraction and improve the overall quality of
retinal images. Moreover, apart from detection and diagnosis, this work delves
into applying ML algorithms for predicting the risk of developing DR or the
likelihood of disease progression. Personalized risk scores for individual
patients are generated using comprehensive patient data encompassing
demographic information, medical history, and retinal images. The proposed
Semi-Supervised Graph learning algorithm is rigorously evaluated on two
publicly available datasets and is benchmarked against existing methods.
Results indicate significant improvements in classification accuracy,
specificity, and sensitivity while demonstrating robustness against noise and
outlie rs.Notably, the proposed algorithm addresses the challenge of imbalanced
datasets, common in medical image analysis, further enhancing its practical
applicability.

糖尿病性视网膜病变（DR）是全球致盲的重要原因，早期检测和有效治疗的迫切需求引起了关注。研究中提出了一种针对 DR 检测的新型半监督图学习（SSGL）算法，充分利用标记和未标记数据之间的关系以提高准确性。该研究通过研究数据增强和预处理技术来解决图像质量和特征变化的挑战，并探索了图像裁剪、调整大小、对比度调整、归一化和数据增强等技术来优化特征提取和改善视网膜图像的整体质量。此外，除了检测和诊断，本研究还深入研究了将机器学习算法应用于预测 DR 发展的风险或疾病进展的可能性。使用包含人口信息、病史和视网膜图像的全面患者数据生成个体化风险评分。该提出的半监督图学习算法在两个公开数据集上进行了严格评估，并与现有方法进行了基准测试。结果表明，在分类准确性、特异性和灵敏度方面取得了显著的改进，同时表现出对噪声和异常值的鲁棒性。值得注意的是，该算法解决了医学图像分析中常见的不平衡数据集的挑战，进一步增强了其实际适用性。

利用半监督图学习增强糖尿病视网膜病变检测

Leveraging Semi-Supervised Graph Learning for Enhanced Diabetic  Retinopathy Detection

In recent years, semi-supervised graph learning with data augmentation (DA)
is currently the most commonly used and best-performing method to enhance model
robustness in sparse scenarios with few labeled samples. Differing from
homogeneous graph, DA in heterogeneous graph has greater challenges:
heterogeneity of information requires DA strategies to effectively handle
heterogeneous relations, which considers the information contribution of
different types of neighbors and edges to the target nodes. Furthermore,
over-squashing of information is caused by the negative curvature that formed
by the non-uniformity distribution and strong clustering in complex graph. To
address these challenges, this paper presents a novel method named
Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation
(HG-MDA). For the problem of heterogeneity of information in DA, node and
topology augmentation strategies are proposed for the characteristics of
heterogeneous graph. And meta-relation-based attention is applied as one of the
indexes for selecting augmented nodes and edges. For the problem of
over-squashing of information, triangle based edge adding and removing are
designed to alleviate the negative curvature and bring the gain of topology.
Finally, the loss function consists of the cross-entropy loss for labeled data
and the consistency regularization for unlabeled data. In order to effectively
fuse the prediction results of various DA strategies, the sharpening is used.
Existing experiments on public datasets, i.e., ACM, DBLP, OGB, and industry
dataset MB show that HG-MDA outperforms current SOTA models. Additionly, HG-MDA
is applied to user identification in internet finance scenarios, helping the
business to add 30% key users, and increase loans and balances by 3.6%, 11.1%,
and 9.8%.

该论文提出了一种名为 HG-MDA 的半监督异质图学习方法，通过数据增强、节点和拓扑增强等策略处理稀疏数据场景下异质图的信息异质性问题，采用基于元关系的关注机制和三角形边添加、删除等方式解决了负曲率问题，应用于互联网金融场景下的用户识别任务，取得了比当前 SOTA 模型更好的效果。

半监督异构图学习与多层数据增广

Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation

Inspired by convolutional neural networks on 1D and 2D data, graph
convolutional neural networks (GCNNs) have been developed for various learning
tasks on graph data, and have shown superior performance on real-world
datasets. Despite their success, there is a dearth of theoretical explorations
of GCNN models such as their generalization properties. In this paper, we take
a first step towards developing a deeper theoretical understanding of GCNN
models by analyzing the stability of single-layer GCNN models and deriving
their generalization guarantees in a semi-supervised graph learning setting. In
particular, we show that the algorithmic stability of a GCNN model depends upon
the largest absolute eigenvalue of its graph convolution filter. Moreover, to
ensure the uniform stability needed to provide strong generalization
guarantees, the largest absolute eigenvalue must be independent of the graph
size. Our results shed new insights on the design of new & improved graph
convolution filters with guaranteed algorithmic stability. We evaluate the
generalization gap and stability on various real-world graph datasets and show
that the empirical results indeed support our theoretical findings. To the best
of our knowledge, we are the first to study stability bounds on graph learning
in a semi-supervised setting and derive generalization bounds for GCNN models.

本文研究了图卷积神经网络在半监督学习环境下的算法稳定性及其一阶推论；通过分析单层 GCNN 模型的稳定性，导出其一般化保证，提出稳定性关于其卷积核最大绝对特征值的依赖规律，并说明产生保证所需的卷积核最大特征值与图大小无关，为设计保证的算法稳定性的新型及更好的卷积核提供新思路。最后在多个真实世界的图数据集上评估了实验结果，实验结果支持理论结果。