• Home
  • Search
  • Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
  • Open Access IconOpen Access
  • Cite Icon13
  • https://doi.org/10.1109/icdm50108.2020.00052Copy DOI Icon

Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning

  • Nov 1, 2020
  • Ziyue Qiao +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

While Graph Neural Network (GNN) has shown superiority in learning node representations of homogeneous graphs, leveraging GNN on heterogeneous graphs remains a challenging problem. The dominating reason is that GNN learns node representations by aggregating neighbors' information regardless of node types. Some work is proposed to alleviate such issue by exploiting relations or meta-path to sample neighbors with distinct categories, then use attention mechanism to learn different importance for different categories. However, one limitation is that the learned representations for different types of nodes should own different feature spaces, while all the above work still project node representations into one feature space. Moreover, after exploring massive heterogeneous graphs, we identify a fact that multiple nodes with the same type always connect to a node with another type, which reveals the many-to-one schema, a.k.a. the hierarchical tree structure. But all the above work cannot preserve such tree structure, since the exact multi-hop path correlation from neighbors to the target node would be erased through aggregation. Therefore, to overcome the limitations of the literature, we propose T-GNN, a tree structure-aware graph neural network model for graph representation learning. Specifically, the proposed T-GNN consists of two modules: (1) the integrated hierarchical aggregation module and (2) the relational metric learning module. The integrated hierarchical aggregation module aims to preserve the tree structure by combining GNN with gated recurrent unit to integrate the hierarchical and sequential neighborhood information on the tree structure to node representations. The relational metric learning module aims to preserve the heterogeneity by embedding each type of nodes into a type-specific space with distinct distribution based on similarity metrics. In this way, our proposed T-GNN is capable of simultaneously preserving the heterogeneity and the tree structure inherent in heterogeneous graphs. Finally, we conduct extensive experiments to show the outstanding performance of T-GNN in tasks of node clustering and classification, inductive node clustering and classification, and link prediction.

Similar Papers
  • Conference Article

Discovering Localized Information for Heterogeneous Graph Node Representation Learning

  • Dec 01, 2020
  • Lin Meng +3
  • Conference Article
  • Citations2

A Graph Neural Network with Type-Feature Attention for Node Classification on Heterogeneous Graphs

  • Dec 16, 2022
  • Kang Chen +3
  • PDF
  • Research Article
  • Citations13

MBHAN: Motif-Based Heterogeneous Graph Attention Network

  • Jun 10, 2022
  • Applied Sciences
  • Qian Hu +3
  • Conference Article
  • Citations4

PHGNN: Position-aware Graph Neural Network for Heterogeneous Graph Embedding

  • Jul 18, 2021
  • Hangjun Yang +4
  • Conference Article
  • Citations6

Hyperdimensional Representation Learning for Node Classification and Link Prediction

  • Mar 10, 2025
  • Abhishek Dalvi +1
  • Research Article
  • Citations1

Dual-Path Graph Neural Network with Adaptive Auxiliary Module for Link Prediction.

  • Mar 25, 2024
  • Big data
  • Zhenzhen Yang +3
  • Research Article
  • Citations30

MuxGNN: Multiplex Graph Neural Network for Heterogeneous Graphs.

  • Sep 01, 2023
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Joshua Melton +1
  • Research Article
  • Citations9

DynHEN: A heterogeneous network model for dynamic bipartite graph representation learning

  • Aug 11, 2022
  • Neurocomputing
  • Zhezhe Xing +3
  • Conference Article
  • Citations373

Graph Convolutional Networks with EigenPooling

  • Jul 25, 2019
  • Yao Ma +3
  • Conference Article
  • Citations34

MANDO: Multi-Level Heterogeneous Graph Embeddings for Fine-Grained Detection of Smart Contract Vulnerabilities

  • Oct 13, 2022
  • Hoang H Nguyen +6
  • Research Article
  • Citations17

Heterogeneous graph neural networks with denoising for graph embeddings

  • Dec 10, 2021
  • Knowledge-Based Systems
  • Xinrui Dong +4
  • Conference Article
  • Citations2

Multi-View Heterogeneous Graph Attention Network

  • May 24, 2023
  • Mingxia Zhao +1
  • Conference Article
  • Citations5

Heterogeneous Graph Embedding Based on Edge-aware Neighborhood Convolution

  • Jul 18, 2021
  • Hui Chen +3
  • PDF
  • Research Article
  • Citations1

Unsupervised Heterogeneous Graph Neural Networks for One-Class Tasks: Exploring Early Fusion Operators

  • May 29, 2024
  • Journal on Interactive Systems
  • Marcos Paulo Silva Gôlo +3
  • Research Article
  • Citations5

Heterogeneous Graph Transformer for Meta-structure Learning with Application in Text Classification

  • May 22, 2023
  • ACM Transactions on the Web
  • Shuhai Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.