Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning

• URL: http://arxiv.org/abs/2511.11081v1
• Date: Fri, 14 Nov 2025 08:53:39 GMT
• Title: Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning
• Authors: Jun Hu, Shangheng Chen, Yufei He, Yuan Li, Bryan Hooi, Bingsheng He,
• Abstract summary: Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs.<n>HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs.<n>We propose pre-computation-based HGNNs that only perform message passing once during preprocessing.
• Score: 70.73716819236627
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs. Typical end-to-end HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs. Pre-computation-based HGNNs address this by performing message passing only once during preprocessing, collecting neighbor information into regular-shaped tensors, which enables efficient mini-batch training. Label-based pre-computation methods collect neighbors' label information but suffer from training label leakage, where a node's own label information propagates back to itself during multi-hop message passing - the echo effect. Existing mitigation strategies are memory-inefficient on large graphs or suffer from compatibility issues with advanced message passing methods. We propose Echoless Label-based Pre-computation (Echoless-LP), which eliminates training label leakage with Partition-Focused Echoless Propagation (PFEP). PFEP partitions target nodes and performs echoless propagation, where nodes in each partition collect label information only from neighbors in other partitions, avoiding echo while remaining memory-efficient and compatible with any message passing method. We also introduce an Asymmetric Partitioning Scheme (APS) and a PostAdjust mechanism to address information loss from partitioning and distributional shifts across partitions. Experiments on public datasets demonstrate that Echoless-LP achieves superior performance and maintains memory efficiency compared to baselines.

Related papers

• Graph Parsing Networks [64.5041886737007]
  We propose an efficient graph parsing algorithm to infer the pooling structure, which then drives graph pooling. The resulting Graph Parsing Network (GPN) adaptively learns personalized pooling structure for each individual graph.
  arXiv  Detail & Related papers  (2024-02-22T09:08:36Z)
• ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance [53.73316938815873]
  We propose a method called ERASE (Error-Resilient representation learning on graphs for lAbel noiSe tolerancE) to learn representations with error tolerance. ERASE combines prototype pseudo-labels with propagated denoised labels and updates representations with error resilience. Our method can outperform multiple baselines with clear margins in broad noise levels and enjoy great scalability.
  arXiv  Detail & Related papers  (2023-12-13T17:59:07Z)
• Efficient Heterogeneous Graph Learning via Random Projection [58.4138636866903]
  Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors. We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN)
  arXiv  Detail & Related papers  (2023-10-23T01:25:44Z)
• All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation [67.30502812804271]
  Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. We propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
  arXiv  Detail & Related papers  (2023-05-25T08:19:31Z)
• Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification [36.3733132520186]
  We propose a graph-based pseudo label correction network (GLC) to refine the pseudo labels in the manner of supervised clustering. GLC learns to rectify the initial noisy labels by means of the relationship constraints between samples on the k Nearest Neighbor graph. Our method is widely compatible with various clustering-based methods and promotes the state-of-the-art performance consistently.
  arXiv  Detail & Related papers  (2022-06-14T05:59:37Z)
• Memory-based Message Passing: Decoupling the Message for Propogation from Discrimination [6.7605701314795095]
  Message passing is a fundamental procedure for graph neural networks (GNNs) We propose a Memory-based Message Passing (MMP) method to decouple the message of each node into a self-embedding part for discrimination and a memory part for propagation. Our MMP is a general skill that can work as an additional layer to help improve traditional GNNs performance.
  arXiv  Detail & Related papers  (2022-02-01T14:15:32Z)
• Adaptive Label Smoothing To Regularize Large-Scale Graph Training [46.00927775402987]
  We propose the adaptive label smoothing (ALS) method to replace the one-hot hard labels with smoothed ones. ALS propagates node labels to aggregate the neighborhood label distribution in a pre-processing step, and then updates the optimal smoothed labels online to adapt to specific graph structure.
  arXiv  Detail & Related papers  (2021-08-30T23:51:31Z)
• On the Equivalence of Decoupled Graph Convolution Network and Label Propagation [60.34028546202372]
  Some work shows that coupling is inferior to decoupling, which supports deep graph propagation better. Despite effectiveness, the working mechanisms of the decoupled GCN are not well understood. We propose a new label propagation method named propagation then training Adaptively (PTA), which overcomes the flaws of the decoupled GCN.
  arXiv  Detail & Related papers  (2020-10-23T13:57:39Z)
• Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification [25.064700425166176]
  We propose a novel Unified Message Passaging Model (UniMP) that can incorporate feature and label propagation at both training and inference time. UniMP conceptually unifies feature propagation and label propagation and is empirically powerful. It obtains new state-of-the-art semi-supervised classification results in Open Graph Benchmark (OGB)
  arXiv  Detail & Related papers  (2020-09-08T04:04:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.