mlsanityData to 7 Oct 2026

IMPA-HGAE:Intra-Meta-Path Augmented Heterogeneous Graph Autoencoder

arXiv 2506.06809 ↗First posted 7 Jun 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning (SSL) methods have been increasingly applied to diverse downstream tasks due to their superior generalization capabilities and low annotation costs. However, most existing heterogeneous graph SSL models convert heterogeneous graphs into homogeneous ones via meta-paths for training, which only leverage information from nodes at both ends of meta-paths while underutilizing the heterogeneous node information along the meta-paths. To address this limitation, this paper proposes a novel framework named IMPA-HGAE to enhance target node embeddings by fully exploiting internal node information along meta-paths. Experimental results validate that IMPA-HGAE achieves superior performance on heterogeneous datasets. Furthermore, this paper introduce innovative masking strategies to strengthen the representational capacity of generative SSL models on heterogeneous graph data. Additionally, this paper discuss the interpretability of the proposed method and potential future directions for generative self-supervised learning in heterogeneous graphs. This work provides insights into leveraging meta-path-guided structural semantics for robust representation learning in complex graph scenarios.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 24 references that are in the map. First posted on arXiv 7 Jun 2025.

Builds on

19 of 24 references.

References · 19

  1. 2016Variational Graph Auto-Encoderscited by 1,373
  2. 2019Heterogeneous Graph Attention Networkcited by 732
  3. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  4. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  5. 2020Heterogeneous Graph Transformercited by 581
  6. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  7. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  8. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  9. 2021Graph Contrastive Learning Automatedcited by 287
  10. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  11. 2019Unsupervised Attributed Multiplex Network Embeddingcited by 95
  12. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
7 more
  1. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  2. 2020GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphscited by 64
  3. 2022Heterogeneous Graph Masked Autoencoderscited by 47
  4. 2019Heterogeneous Deep Graph Infomaxcited by 42
  5. 2023SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Maskingcited by 23
  6. 2024Rethinking Graph Masked Autoencoders through Alignment and Uniformitycited by 22
  7. 2022Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learningcited by 13

Built on by

Not cited yet.