MetaLearning with Graph Neural Networks

Mandal, Debmalya; Medya, Sourav; Uzzi, Brian; Aggarwal, Charų C.

doi:10.1145/3510374.3510379

Cited by 18 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, research in generating example-level explanations for GNN models has been proposed. , Additionally, graph pretraining and the challenges associated with complex graph structures are also important research directions. Nonetheless, GNNs also have certain limitations such as their performance being limited by their depth and width, their inability to work with insufficient data, and issues related to high computational costs.…”

Section: Methods For Small Molecular Data Challengesmentioning

confidence: 99%

Machine Learning Methods for Small Data Challenges in Molecular Science

et al. 2023

View full text Add to dashboard Cite

Small data are often used in scientific and engineering research due to the presence of various constraints, such as time, cost, ethics, privacy, security, and technical limitations in data acquisition. However, big data have been the focus for the past decade, small data and their challenges have received little attention, even though they are technically more severe in machine learning (ML) and deep learning (DL) studies. Overall, the small data challenge is often compounded by issues, such as data diversity, imputation, noise, imbalance, and high-dimensionality. Fortunately, the current big data era is characterized by technological breakthroughs in ML, DL, and artificial intelligence (AI), which enable data-driven scientific discovery, and many advanced ML and DL technologies developed for big data have inadvertently provided solutions for small data problems. As a result, significant progress has been made in ML and DL for small data challenges in the past decade. In this review, we summarize and analyze several emerging potential solutions to small data challenges in molecular science, including chemical and biological sciences. We review both basic machine learning algorithms, such as linear regression, logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), kernel learning (KL), random forest (RF), and gradient boosting trees (GBT), and more advanced techniques, including artificial neural network (ANN), convolutional neural network (CNN), U-Net, graph neural network (GNN), Generative Adversarial Network (GAN), long short-term memory (LSTM), autoencoder, transformer, transfer learning, active learning, graph-based semi-supervised learning, combining deep learning with traditional machine learning, and physical model-based data augmentation. We also briefly discuss the latest advances in these methods. Finally, we conclude the survey with a discussion of promising trends in small data challenges in molecular science.

show abstract

Section: Methods For Small Molecular Data Challengesmentioning

confidence: 99%

Machine Learning Methods for Small Data Challenges in Molecular Science

et al. 2023

View full text Add to dashboard Cite

show abstract

“…As for graph-level dependencies, they assigned each node to absolute positions on the graph to align different tasks and learn transferable prior knowledge. Moreover, they used central nodes to update representations learned by GNNs [17].…”

Section: Introductionmentioning

confidence: 99%

Graph Relation Networks for Few-shot Node Classification on Attributed Networks

里

刘

张

2023

Preprint

View full text Add to dashboard Cite

Few-shot learning has been solving classification problems with few labels in the image and text domains, which has achieved great success in such Euclidean domains. However, a large amount of data can be represented as attributed networks defined by non-Euclidean domains, and fewer studies have successfully applied few-shot learning to attributed networks. Firstly, they ignore the relationship between nodes, so they can not obtain an adequate and accurate representation of nodes. Secondly, the use of an artificial set distance function to measure the similarity between nodes is defective. Because some special samples can cause perturbation to the classifier. In order to solve the above problems, we propose a new framework based on relation networks - graph relation networks (GRN). Specifically, GRN first sets up an episode training mechanism to simulate a real-world few-shot scenario, then uses graph attention networks to obtain a representation of each node with importance scores, and finally learns to compare the similarity of unclassified and classified nodes through the relation network. We conduct extensive experiments on real-world datasets. The experimental results show that the method improves the performance of graph node classification.

show abstract

“…Second, based on branch exchange theory, we effectively reduce the action space so that the DRL agent can easily meet the radial topology constraint of the OTVR problem. Third, to overcome the limitation of conventional neural network for graph data, graph neural networks (GNN) have been developed rapidly in the past two years [23, 24]. As one of the most popular GNN structures, graph convolution network (GCN) realizes the traditional convolution operation on graph data [25].…”

Section: Introductionmentioning

confidence: 99%

Online topology‐based voltage regulation: A computational performance enhanced algorithm based on deep reinforcement learning

Wang

Zhang

et al. 2022

IET Generation Trans & Dist

View full text Add to dashboard Cite

The increasing use of distributed generation (DG) in power systems can result in frequent online voltage problems. In scenarios in which substantial DG prediction errors occur because of high DG accommodation levels, traditional technical solutions cannot meet the online voltage regulation requirements. Hence, new resources for online voltage regulation are needed. Here, flexible network reconfiguration is proposed to coordinate with the existing resources for severe online voltage deviations. For online topology-based voltage regulation (OTVR), the authors develop a deep reinforcement learning (DRL) algorithm based on the following specially designed modelling to enhance the computational performance. The mechanism of action incorporates the concepts of local research, branch exchange, and action separation, and it effectively simplifies the action dimension and action space. In addition, for the graph data in OTVR, a graph convolution network (GCN) is applied to obtain better feature extraction. Case studies performed on IEEE 14-bus, 33-bus, 141bus systems and a practical system verify that our proposed algorithm can obtain close to optimal solutions in 2 s which can meet the needs of online voltage regulation. Moreover, we verify that the developed OTVR effectively increases DG penetration and decreases the need for investment in additional regulating devices.

show abstract

MetaLearning with Graph Neural Networks

Cited by 18 publications

References 9 publications

Machine Learning Methods for Small Data Challenges in Molecular Science

Machine Learning Methods for Small Data Challenges in Molecular Science

Graph Relation Networks for Few-shot Node Classification on Attributed Networks

Online topology‐based voltage regulation: A computational performance enhanced algorithm based on deep reinforcement learning

Contact Info

Product

Resources

About