A gentle introduction to deep learning for graphs
From MaRDI portal
Publication:2055049
DOI10.1016/J.NEUNET.2020.06.006zbMATH Open1475.68310arXiv1912.12693OpenAlexW2997785591WikidataQ96591611 ScholiaQ96591611MaRDI QIDQ2055049FDOQ2055049
Authors: Davide Bacciu, Federico Errica, Alessio Micheli, Marco Podda 
Publication date: 3 December 2021
Published in: Neural Networks (Search for Journal in Brave)
Abstract: The adaptive processing of graph data is a long-standing research topic which has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is designed as a tutorial introduction to the field of deep learning for graphs. It favours a consistent and progressive introduction of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view to the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. It introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. The methodological exposition is complemented by a discussion of interesting research challenges and applications in the field.
Full work available at URL: https://arxiv.org/abs/1912.12693
Recommendations
Artificial neural networks and deep learning (68T07) Graph theory (including graph drawing) in computer science (68R10)
Cites Work
- kLog: a language for logical and relational learning with kernels
- The elements of statistical learning. Data mining, inference, and prediction
- Support-vector networks
- Wavelets on graphs via spectral graph theory
- Random Graphs
- Graph kernels
- Title not available (Why is that?)
- Weisfeiler-Lehman graph kernels
- Graph theory with applications
- Approximation by superpositions of a sigmoidal function
- Mixed memory Markov models: Decomposing complex stochastic processes as mixtures of simpler ones
- The self-organizing map
- Title not available (Why is that?)
- Recursive self-organizing network models
- Universal Approximation Capability of Cascade Correlation for Structures
- An Introduction to Variational Autoencoders
Cited In (23)
- Probabilistic learning on graphs via contextual architectures
- Graph neural networks: foundations, frontiers, and applications
- Representation learning for dynamic graphs: a survey
- Locality preserving dense graph convolutional networks with graph context-aware node representations
- Investigation into the application of graph neural networks to large-scale recommender systems
- Deep graph similarity learning: a survey
- Deep learning on graphs
- Challenges for machine learning in RNA-protein interaction prediction
- Polynomial-based graph convolutional neural networks for graph classification
- Graph deconvolutional networks
- Title not available (Why is that?)
- Learning the structural vocabulary of a network
- \(k\)-hop graph neural networks
- Some open questions on morphological operators and representations in the deep learning era. A personal vision
- Graph kernels: a survey
- \texttt{GIST}: distributed training for large-scale graph convolutional networks
- Graph Neural Networks for Natural Language Processing: A Survey
- Towards data augmentation in graph neural network: an overview and evaluation
- Correlation-driven framework based on graph convolutional network for clinical disease classification
- Local2global: a distributed approach for scaling representation learning on graphs
- Graph neural network
- GSM: inductive learning on dynamic graph embeddings
- K-plex cover pooling for graph neural networks
Uses Software
This page was built for publication: A gentle introduction to deep learning for graphs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2055049)
