Learning from Historical Activations in Graph Neural Networks

• URL: http://arxiv.org/abs/2601.01123v1
• Date: Sat, 03 Jan 2026 08:51:38 GMT
• Title: Learning from Historical Activations in Graph Neural Networks
• Authors: Yaniv Galron, Hadar Sinai, Haggai Maron, Moshe Eliasof,
• Abstract summary: HISTOGRAPH is a novel two-stage attention-based final aggregation layer that first applies a unified layer-wise attention over intermediate activations, followed by node-wise attention.<n> Empirical results on multiple graph classification benchmarks demonstrate that HISTOGRAPH offers strong performance that consistently improves traditional techniques, with particularly strong robustness in deep GNNs.
• Score: 30.897189154307025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A crucial component of GNNs is the pooling procedure, in which the node features calculated by the model are combined to form an informative final descriptor to be used for the downstream task. However, previous graph pooling schemes rely on the last GNN layer features as an input to the pooling or classifier layers, potentially under-utilizing important activations of previous layers produced during the forward pass of the model, which we regard as historical graph activations. This gap is particularly pronounced in cases where a node's representation can shift significantly over the course of many graph neural layers, and worsened by graph-specific challenges such as over-smoothing in deep architectures. To bridge this gap, we introduce HISTOGRAPH, a novel two-stage attention-based final aggregation layer that first applies a unified layer-wise attention over intermediate activations, followed by node-wise attention. By modeling the evolution of node representations across layers, our HISTOGRAPH leverages both the activation history of nodes and the graph structure to refine features used for final prediction. Empirical results on multiple graph classification benchmarks demonstrate that HISTOGRAPH offers strong performance that consistently improves traditional techniques, with particularly strong robustness in deep GNNs.

Related papers

• Hypergraph Neural Network with State Space Models for Node Classification [0.0]
  We propose a novel hypergraph neural network with state space model (HGMN)<n>HGMN effectively integrates role-aware representations into GNNs and the state space model.<n>The model achieves significant performance improvements on node classification tasks compared to state-of-the-art GNN methods.
  arXiv  Detail & Related papers  (2025-08-08T04:54:12Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement [62.91536661584656]
  We propose a dual-module framework, Cell-embedded and Feature-enhanced Graph Neural Network (aka, CeFeGNN) for learning.<n>We embed learnable cell attributions to the common node-edge message passing process, which better captures the spatial dependency of regional features.<n>Experiments on various PDE systems and one real-world dataset demonstrate that CeFeGNN achieves superior performance compared with other baselines.
  arXiv  Detail & Related papers  (2024-09-26T16:22:08Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Efficient Topology-aware Data Augmentation for High-Degree Graph Neural Networks [2.7523980737007414]
  We propose TADA, an efficient and effective front-mounted data augmentation framework for graph neural networks (GNNs) on high-degree graphs (HDGs) Under the hood, TADA includes two key modules: (i) feature expansion with structure embeddings, and (ii) topology- and attribute-aware graph sparsification. TADA considerably improves the predictive performance of mainstream GNN models on 8 real homophilic/heterophilic HDGs in terms of node classification.
  arXiv  Detail & Related papers  (2024-06-08T14:14:19Z)
• Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module [65.81781176362848]
  Graph Neural Networks (GNNs) can learn from graph-structured data through neighborhood information aggregation. As the number of layers increases, node representations become indistinguishable, which is known as over-smoothing. We propose a textbfPosterior-Sampling-based, Node-distinguish Residual module (PSNR).
  arXiv  Detail & Related papers  (2023-05-09T12:03:42Z)
• Deep Manifold Learning with Graph Mining [80.84145791017968]
  We propose a novel graph deep model with a non-gradient decision layer for graph mining. The proposed model has achieved state-of-the-art performance compared to the current models.
  arXiv  Detail & Related papers  (2022-07-18T04:34:08Z)
• Hierarchical graph neural nets can capture long-range interactions [8.067880298298185]
  We study hierarchical message passing models that leverage a multi-resolution representation of a given graph. This facilitates learning of features that span large receptive fields without loss of local information. We introduce Hierarchical Graph Net (HGNet), which for any two connected nodes guarantees existence of message-passing paths of at most logarithmic length.
  arXiv  Detail & Related papers  (2021-07-15T16:24:22Z)
• Improving Graph Neural Networks with Simple Architecture Design [7.057970273958933]
  We introduce several key design strategies for graph neural networks. We present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN) We show that the proposed model outperforms other state of the art GNN models and achieves up to 64% improvements in accuracy on node classification tasks.
  arXiv  Detail & Related papers  (2021-05-17T06:46:01Z)
• CatGCN: Graph Convolutional Networks with Categorical Node Features [99.555850712725]
  CatGCN is tailored for graph learning when the node features are categorical. We train CatGCN in an end-to-end fashion and demonstrate it on semi-supervised node classification.
  arXiv  Detail & Related papers  (2020-09-11T09:25:17Z)
• Hierarchical Message-Passing Graph Neural Networks [12.207978823927386]
  We propose a novel Hierarchical Message-passing Graph Neural Networks framework. Key idea is generating a hierarchical structure that re-organises all nodes in a flat graph into multi-level super graphs. We present the first model to implement this framework, termed Hierarchical Community-aware Graph Neural Network (HC-GNN)
  arXiv  Detail & Related papers  (2020-09-08T13:11:07Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)

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.