Representation Learning on Heterostructures via Heterogeneous Anonymous Walks

  title={Representation Learning on Heterostructures via Heterogeneous Anonymous Walks},
  author={X. Guo and Pengfei Jiao and Ting Pan and Wang Zhang and Mengyu Jia and Danyang Shi and Wenjun Wang},
Capturing structural similarity has been a hot topic in the field of network embedding recently due to its great help in understanding the node functions and behaviors. However, existing works have paid very much attention to learning structures on homogeneous networks while the related study on heterogeneous networks is still a void. In this paper, we try to take the first step for representation learning on heterostructures, which is very challenging due to their highly diverse combinations… 

Figures and Tables from this paper



GraLSP: Graph Neural Networks with Local Structural Patterns

This paper proposes GraLSP, a GNN framework which explicitly incorporates local structural patterns into the neighborhood aggregation through random anonymous walks, and designs objectives that capture similarities between structures and are optimized jointly with node proximity objectives.

Heterogeneous Network Representation Learning: A Unified Framework With Survey and Benchmark

This work aims to provide a unified framework to deeply summarize and evaluate existing research on heterogeneous network embedding (HNE), and provides a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms.

Learning Structural Node Embeddings via Diffusion Wavelets

GraphWave is developed, a method that represents each node's network neighborhood via a low-dimensional embedding by leveraging heat wavelet diffusion patterns and mathematically proves that nodes with similar network neighborhoods will have similar GraphWave embeddings even though these nodes may reside in very different parts of the network, and the method scales linearly with the number of edges.

A Structural Graph Representation Learning Framework

This work formulate higher-order network representation learning and describes a general framework called HONE for learning such structural node embeddings from networks via the subgraph patterns (network motifs, graphlet orbits/positions) in a nodes neighborhood.

Role-Based Graph Embeddings

The Role2Vec framework is introduced, based on the proposed notion of attributed random walks to learn structural role-based embeddings, which enables these methods to be more widely applicable by learning inductive functions that capture the structural roles in the graph.

Learning Stochastic Equivalence based on Discrete Ricci Curvature

This work constructs a framework called Curvature-based Network Embedding with Stochastic Equivalence (CNESE) to embed stochastic equivalence and estimates the role distribution of nodes based on discrete Ricci curvature for its excellent ability to concisely representing local topology.

AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks

This work proposes a novel embedding learning framework-ASPEM-to preserve the semantic information in HINs based on multiple aspects, where the aspects can be selected from the given HIN in an unsupervised manner.

Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels

This paper proposes GSKN1, a GNN model with a theoretically stronger ability to distinguish graph structures, based on anonymous walks, flexible substructure units, and derive it upon feature mappings of graph kernels (GKs).

RiWalk: Fast Structural Node Embedding via Role Identification

RiWalk is a flexible paradigm for learning structural node representations as it decouples the structural embedding problem into a role identification procedure and a network embedding procedure and shows potential of structural embeddings in transfer learning.

Learning Structural Node Representations Using Graph Kernels

This paper proposes SEGK, a powerful framework for computing structural node representations that compares the neighborhood subgraphs of increasing size of two nodes using graph kernels, and evaluates its performance on several synthetic and real-world datasets.