Weisfeiler-Lehman Neural Machine for Link Prediction

By Muhan Zhang, Yixin Chen. 2017

252 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Urban Studies

How researchers see this paper

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

In Artificial Intelligence

In Statistical and Nonlinear Physics

In Urban Studies

Citations in the corpus

Provably Powerful Graph Networks (2019, methodology): “We follow the standard 10-fold cross validation protocol and splits from Zhang et al. (2018) and report our results according to the protocol described in Xu et al.”
Subgraph-augmented Path Embedding for Semantic User Search on Heterogeneous Social Network (2018, methodology): “Thirdly, graph kernel methods [7], especially Weisfeiler-Lehman graph kernels [29, 41], try to measure the similarity between two (small) graphs w.r.t. their structures.”
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning (2021, background): “To utilize attributed network data to solve practical problems, a wide variety of graph analysis tasks have attracted signiﬁcant research interests in recent years, such as node classiﬁcation [6], [7], graph classiﬁcation [8], [9], and link prediction [10], [11].”
Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs (2017, background): “On the other hand, this simple algorithm is already quite powerful since it can distinguish almost all graphs [6], [8], and has been applied in other areas [9]–[13].”
Link Prediction Based on Graph Neural Networks (2018, methodology): “This poses a question unanswered by [14]: why using a small K can learn high-order graph features? We will answer this question by showing that many high-order features can be well approximated by small enclosing subgraphs, and the approximation error decreases exponentially with the neighborhood si”
Learning Discrete Structures for Graph Neural Networks (2019, methodology): “While a majority of the methods are based on some similarity measure between node pairs, there has been a number of neural network based methods (Zhang & Chen, 2017, 2018).”
Towards Deeper Graph Neural Networks (2020, background): “Great successes have been achieved for many applications, such as node classification [7, 9, 11, 12, 21, 30, 31, 33], graph classification [6, 8, 14, 18, 32, 34, 35, 38] and link prediction [1, 36, 37].”
How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision (2022, methodology): “Our self-supervised task is similar to link prediction (Liben-Nowell & Kleinberg, 2007), which is a well-studied problem and recently tackled by neural networks (Zhang & Chen, 2017; 2018).”
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning (2020, background): “Representations of node sets in a graph can be leveraged for a wide range of applications, such as discovery of functions/roles of nodes based on individual node representations [2–6], link or link type prediction based on node-pair representations [7–10] and graph comparison or molecule classificat”