Meta-Learning with Graph Neural Networks: Methods and Applications

• URL: http://arxiv.org/abs/2103.00137v1
• Date: Sat, 27 Feb 2021 06:19:11 GMT
• Title: Meta-Learning with Graph Neural Networks: Methods and Applications
• Authors: Debmalya Mandal, Sourav Medya, Brian Uzzi, and Charu Aggarwal
• Abstract summary: Graph Neural Networks (GNNs) are generalizations of deep neural networks on graph data. GNNs are limited when there are few available samples. In recent years, researchers have started to apply meta-learning to GNNs.
• Score: 5.804439462187914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph Neural Networks (GNNs), a generalization of deep neural networks on graph data have been widely used in various domains, ranging from drug discovery to recommender systems. However, GNNs on such applications are limited when there are few available samples. Meta-learning has been an important framework to address the lack of samples in machine learning, and in recent years, the researchers have started to apply meta-learning to GNNs. In this work, we provide a comprehensive survey of different meta-learning approaches involving GNNs on various graph problems showing the power of using these two approaches together. We categorize the literature based on proposed architectures, shared representations, and applications. Finally, we discuss several exciting future research directions and open problems.

Related papers

• Learning Regularization for Graph Inverse Problems [16.062351610520693]
  We introduce a framework leveraging GNNs to solve Graph Inverse Problems (GRIP) The framework is based on a combination of likelihood and prior terms, which are used to find a solution that fits the data. We study our approach on a number of representative problems that demonstrate the effectiveness of the framework.
  arXiv  Detail & Related papers  (2024-08-19T22:03:02Z)
• A Manifold Perspective on the Statistical Generalization of Graph Neural Networks [84.01980526069075]
  Graph Neural Networks (GNNs) combine information from adjacent nodes by successive applications of graph convolutions. We study the generalization gaps of GNNs on both node-level and graph-level tasks. We show that the generalization gaps decrease with the number of nodes in the training graphs.
  arXiv  Detail & Related papers  (2024-06-07T19:25:02Z)
• A Systematic Review of Deep Graph Neural Networks: Challenges, Classification, Architectures, Applications & Potential Utility in Bioinformatics [0.0]
  Graph neural networks (GNNs) employ message transmission between graph nodes to represent graph dependencies. GNNs have the potential to be an excellent tool for solving a wide range of biological challenges in bioinformatics research.
  arXiv  Detail & Related papers  (2023-11-03T10:25:47Z)
• Information Flow in Graph Neural Networks: A Clinical Triage Use Case [49.86931948849343]
  Graph Neural Networks (GNNs) have gained popularity in healthcare and other domains due to their ability to process multi-modal and multi-relational graphs. We investigate how the flow of embedding information within GNNs affects the prediction of links in Knowledge Graphs (KGs) Our results demonstrate that incorporating domain knowledge into the GNN connectivity leads to better performance than using the same connectivity as the KG or allowing unconstrained embedding propagation.
  arXiv  Detail & Related papers  (2023-09-12T09:18:12Z)
• The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey [17.746899445454048]
  Graph Neural Networks (GNNs) are an emerging research field. GNNs can be applied to various domains including recommendation systems, computer vision, natural language processing, biology and chemistry. We aim to fill this gap by summarizing and categorizing important methods and techniques for large-scale GNN solutions.
  arXiv  Detail & Related papers  (2023-05-23T09:22:33Z)
• Graph-level Neural Networks: Current Progress and Future Directions [61.08696673768116]
  Graph-level Neural Networks (GLNNs, deep learning-based graph-level learning methods) have been attractive due to their superiority in modeling high-dimensional data. We propose a systematic taxonomy covering GLNNs upon deep neural networks, graph neural networks, and graph pooling.
  arXiv  Detail & Related papers  (2022-05-31T06:16:55Z)
• Graph Neural Networks for Graphs with Heterophily: A Survey [98.45621222357397]
  We provide a comprehensive review of graph neural networks (GNNs) for heterophilic graphs. Specifically, we propose a systematic taxonomy that essentially governs existing heterophilic GNN models. We discuss the correlation between graph heterophily and various graph research domains, aiming to facilitate the development of more effective GNNs.
  arXiv  Detail & Related papers  (2022-02-14T23:07:47Z)
• Ranking Structured Objects with Graph Neural Networks [0.0]
  RankGNNs are trained with a set of pair-wise preferences between graphs, suggesting that one of them is preferred over the other. One practical application of this problem is drug screening, where an expert wants to find the most promising molecules in a large collection of drug candidates. We empirically demonstrate that our proposed pair-wise RankGNN approach either significantly outperforms or at least matches the ranking performance of the naive point-wise baseline approach.
  arXiv  Detail & Related papers  (2021-04-18T14:40:59Z)
• Computing Graph Neural Networks: A Survey from Algorithms to Accelerators [2.491032752533246]
  Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent years owing to their capability to model and learn from graph-structured data. This paper aims to make two main contributions: a review of the field of GNNs is presented from the perspective of computing. An in-depth analysis of current software and hardware acceleration schemes is provided.
  arXiv  Detail & Related papers  (2020-09-30T22:29:27Z)
• Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks [52.76042362922247]
  Graph neural networks (GNNs) are designed to handle the non-Euclidean graph-structure. Existing GNNs are presented using various techniques, making direct comparison and cross-reference more complex. We organize existing GNNs into spatial and spectral domains, as well as expose the connections within each domain.
  arXiv  Detail & Related papers  (2020-02-27T01:15:10Z)
• Node Masking: Making Graph Neural Networks Generalize and Scale Better [71.51292866945471]
  Graph Neural Networks (GNNs) have received a lot of interest in the recent times. In this paper, we utilize some theoretical tools to better visualize the operations performed by state of the art spatial GNNs. We introduce a simple concept, Node Masking, that allows them to generalize and scale better.
  arXiv  Detail & Related papers  (2020-01-17T06:26:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.