Graph Kernels: A Survey

Nikolentzos, Giannis; Siglidis, Giannis; Vazirgiannis, Michalis

doi:10.1613/jair.1.13225

Cited by 61 publications

(44 citation statements)

References 136 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A simple unlabeled graph is usually represented through an adjacency matrix A(G X ) ∈ R N,N , whose elements A ij are set to one if two different nodes i and j are linked by an edge or to zero otherwise 45,47 . However, the same graph would correspond to an infinite number of conformations through this definition: by changing the interatomic distances, as long as the edges are preserved (i.e.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids

Casier¹,

Silva²,

Badawi³

et al. 2020

Preprint

View full text Add to dashboard Cite

Nowadays, the coupling of electronic structure and machine learning techniques serves as a powerful tool to predict chemical and physical properties of a broad range of systems. With the aim of improving the accuracy of predictions, a large number of representations for molecules and solids for machine learning applications has been developed. In this work we propose a novel descriptor based on the notion of molecular graph. While graphs are largely employed in classification problems in cheminformatics or bioinformatics, they are not often used in regression problem, especially of energy-related properties. Our method is based on a local decomposition of atomic environments and on the hybridization of two kernel functions: a graph kernel contribution that describes the chemical pattern and a Coulomb label contribution that

show abstract

Section: Methodsmentioning

confidence: 99%

“…which is commonly used also in other graphs application [45][46][47]52 . This normalization can be seen as a Jaccard's distance -i.e.…”

Section: 3mentioning

confidence: 99%

Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids

Casier¹,

Silva²,

Badawi³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…1. graph representation learning [73], such as message passing neural networks (MPNNs) [74,75] that learn task-specific vector representations of molecular graphs for prediction tasks in an end-to-end manner 2. graph kernels [76][77][78][79][80][81], which (loosely speaking) measure the similarity between any two input graphs, allowing for the use of kernel methods [82], such as support vector machines [83], kernel regression/classification [82], and Gaussian processes [84], for prediction tasks.…”

Section: Representing Molecules For Supervised Machine Learning Tasksmentioning

confidence: 99%

Classifying the toxicity of pesticides to honey bees via support vector machines with random walk graph kernels

Yang

Henle

Simon

et al. 2022

Preprint

View full text Add to dashboard Cite

Pesticides benefit agriculture by increasing crop yield, quality, and security. However, pesticides may inadvertently harm bees, which are agriculturally and ecologically vital as pollinators. The development of new pesticides---driven by pest resistance to and demands to reduce negative environmental impacts of incumbent pesticides---necessitates assessments of pesticide toxicity to bees. We leverage a data set of 382 molecules labeled from honey bee toxicity experiments to train a classifier that predicts the toxicity of a new pesticide molecule to honey bees. Traditionally, the first step of a molecular machine learning task is to explicitly convert molecules into feature vector representations for input to the classifier. Instead, we (i) adopt the fixed-length random walk graph kernel to express the similarity between any two molecular graphs and (ii) use the kernel trick to train a support vector machine (SVM) to classify the bee toxicity of pesticides represented as molecular graphs. We assess the performance of the graph-kernel-SVM classifier under different walk lengths used to describe the molecular graphs. The optimal classifier, with walk length 5, achieves an (mean over 100 runs) accuracy, precision, and recall of 0.83, 0.71, and 0.72 on a test data set.

show abstract

“…This is unlike the modular approach of GraphDCA which measures similarity in terms of different node representations. For a recent overview of graph kernels, see (Nikolentzos et al, 2021).…”

Section: Graph Comparisonmentioning

confidence: 99%

GraphDCA -- a Framework for Node Distribution Comparison in Real and Synthetic Graphs

Ceylan¹,

Poklukar²,

Hultin³

et al. 2022

Preprint

View full text Add to dashboard Cite

We argue that when comparing two graphs, the distribution of node structural features is more informative than global graph statistics which are often used in practice, especially to evaluate graph generative models. Thus, we present GraphDCA -a framework for evaluating similarity between graphs based on the alignment of their respective node representation sets. The sets are compared using a recently proposed method for comparing representation spaces, called Delaunay Component Analysis (DCA), which we extend to graph data. To evaluate our framework, we generate a benchmark dataset of graphs exhibiting different structural patterns and show, using three node structure feature extractors, that GraphDCA recognizes graphs with both similar and dissimilar local structure. We then apply our framework to evaluate three publicly available real-world graph datasets and demonstrate, using gradual edge perturbations, that GraphDCA satisfyingly captures gradually decreasing similarity, unlike global statistics. Finally, we use GraphDCA to evaluate two state-of-the-art graph generative models, NetGAN and CELL, and conclude that further improvements are needed for these models to adequately reproduce local structural features.

show abstract

Graph Kernels: A Survey

Cited by 61 publications

References 136 publications

Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids

Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids

Classifying the toxicity of pesticides to honey bees via support vector machines with random walk graph kernels

GraphDCA -- a Framework for Node Distribution Comparison in Real and Synthetic Graphs

Contact Info

Product

Resources

About