Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs

By Saurabh Verma, Zhi-Li Zhang. 2017

147 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Graphite: Iterative Generative Modeling of Graphs (2018, background): “An interesting direction of future work is to explore the robustness of Graphite to permutation-invariance across graphs by incorporating robust graph representations [47].”
Provably Powerful Graph Networks (2019, neutral): “7 0.1 > 3 days NA NA NA NA PK (Neumann et al., 2016) 76 2.7 59.5 2.4 73.68 0.7 82.54 0.5 NA NA NA NA WL (Shervashidze et al., 2011) 84.11 1.9 57.97 2.5 74.68 0.5 84.46 0.5 85.12 0.3 NA NA NA FGSD (Verma and Zhang, 2017) 92.12 62.80 73.42 79.80 78.84 80.02 73.62 52.41 AWE-DD (Ivanov and Burnaev, 2”
A simple yet effective baseline for non-attribute graph classification (2018, methodology): “ernel)[KGW16], GK(Graphlet Kernel)[SVP+09], RetGK(Graph Kernels based on Return Probabilities of Random Walks)[ZWX+18], MLG(Multiscale Laplacian Kernel)[KP16], FGSD(family of graph spectral distances)[VZ17]. 3 Although there is an efﬁcient algorithm available to approximate the feature map[RR08], we”
Anonymous Walk Embeddings (2018, unknown): “…on graphs; graph2vec (Narayanan et al., 2017) learns network embeddings by extracting rooted subgraphs and training on skipgram negative sampling model (Mikolov et al., 2013b); FGSD (Verma & Zhang, 2017) that constructs feature vector from the histogram of the multiset of node pairwise distances.”
Invariant and Equivariant Graph Networks (2018, methodology): “We also compare our results to four popular graph kernel methods: Graphlet Kernel (GK) (Shervashidze et al., 2009),Random Walk Kernel (RW) (Vishwanathan et al., 2010), Propagation Kernel (PK) (Neumann et al., 2016), and Weisfeiler-lehman kernels (WL) (Shervashidze et al., 2011) and two recent featur”
Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings (2019, background): “…recent works focus on assignment-based (Johansson & Dubhashi, 2015; Kriege et al., 2016; Nikolentzos et al., 2017), spectral (Kondor & Pan, 2016; Verma & Zhang, 2017), graph decomposition (Nikolentzos et al., 2018), randomized binning approaches (Heimann et al., 2019), and the extension of…”
RetGK: Graph Kernels based on Return Probabilities of Random Walks (2018, methodology): “[24] uses the shortest path distance, and [29] uses the diffusion distance.”
Graph Capsule Convolutional Neural Networks (2018, methodology): “As shown in (Verma & Zhang, 2017) F GSD features capture global information about the graph and can also be computed in fast manner.”
A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021, methodology): “First, graphs in the database are encoded into a shared latent space using graph-level representation techniques, such as Graph2Vec [144], FGSD [145].”
Capsule Graph Neural Network (2018, methodology): “GCAPS-CNN first extract FGSD (Verma & Zhang, 2017) features for nodes that do not have attributes and then generate capsules for each node with higher-order statistical moment value of its neighbor nodes.”
InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization (2019, methodology): “For graph classiﬁcation tasks, we adopt the same procedure of previous works [40, 56, 63, 66] to make a fair comparison and used 10-fold cross validation accuracy to report the classiﬁcation performance.”
Optimal Transport for structured data with application on graphs (2018, background): “Depending on the context, C can either encode the neighborhood information of the nodes, the edge information of the graph or more generally it can model a distance between the nodes such as the shortest path distance or the harmonic distance (Verma & Zhang, 2017).”