FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning

• URL: http://arxiv.org/abs/2407.19429v3
• Date: Thu, 8 Aug 2024 07:56:48 GMT
• Title: FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning
• Abstract summary: We propose a novel method called Feature-Topology Fusion-based Experience Replay (FTF-ER) to mitigate the catastrophic forgetting issue with enhanced efficiency. FTF-ER includes both feature and global topological information, which can significantly improve the effectiveness of the sampled nodes. It achieves a significant improvement of 3.6% in AA and 7.1% in AF on the OGB-Arxiv dataset, demonstrating its superior performance in the class-incremental learning setting.
• Score: 12.050104684013622
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual graph learning (CGL) is an important and challenging task that aims to extend static GNNs to dynamic task flow scenarios. As one of the mainstream CGL methods, the experience replay (ER) method receives widespread attention due to its superior performance. However, existing ER methods focus on identifying samples by feature significance or topological relevance, which limits their utilization of comprehensive graph data. In addition, the topology-based ER methods only consider local topological information and add neighboring nodes to the buffer, which ignores the global topological information and increases memory overhead. To bridge these gaps, we propose a novel method called Feature-Topology Fusion-based Experience Replay (FTF-ER) to effectively mitigate the catastrophic forgetting issue with enhanced efficiency. Specifically, from an overall perspective to maximize the utilization of the entire graph data, we propose a highly complementary approach including both feature and global topological information, which can significantly improve the effectiveness of the sampled nodes. Moreover, to further utilize global topological information, we propose Hodge Potential Score (HPS) as a novel module to calculate the topological importance of nodes. HPS derives a global node ranking via Hodge decomposition on graphs, providing more accurate global topological information compared to neighbor sampling. By excluding neighbor sampling, HPS significantly reduces buffer storage costs for acquiring topological information and simultaneously decreases training time. Compared with state-of-the-art methods, FTF-ER achieves a significant improvement of 3.6% in AA and 7.1% in AF on the OGB-Arxiv dataset, demonstrating its superior performance in the class-incremental learning setting.

Related papers

• Global to Local: Topology-Preserving Adaptive Graph Pooling via Granular-Ball [18.207001863893083]
  We propose a novel Topology-Preserving Adaptive Graph Pooling (TPAGP) method.<n>TPAGP partitions graphs into granular balls by integrating node features and topological information.<n>We design a multi-granularity graph network model that facilitates feature interaction and optimization across different granularities.
  arXiv  Detail & Related papers  (2026-09-04T10:32:20Z)
• LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification [1.0094533804829493]
  We introduce LightTopoGAT, a lightweight graph attention network that enhances node features through topological augmentation.<n>We show that LightTopoGAT achieves superior performance compared to established baselines including GCN, GraphSAGE, and standard GAT.
  arXiv  Detail & Related papers  (2025-12-15T18:09:59Z)
• ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion [73.85920403511706]
  We propose ScaleGNN, a novel framework that adaptively fuses multi-hop node features for scalable and effective graph learning.<n>We show that ScaleGNN consistently outperforms state-of-the-art GNNs in both predictive accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-04-22T14:05:11Z)
• Using Subgraph GNNs for Node Classification:an Overlooked Potential Approach [13.947915030994851]
  SubGND (Subgraph GNN for NoDe) is a new subgraph-based classification framework for node classification. We show that SubGND achieves performance comparable to or surpassing global message-passing GNNs.
  arXiv  Detail & Related papers  (2025-03-09T13:37:38Z)
• Amplify Graph Learning for Recommendation via Sparsity Completion [16.32861024767423]
  Graph learning models have been widely deployed in collaborative filtering (CF) based recommendation systems. Due to the issue of data sparsity, the graph structure of the original input lacks potential positive preference edges. We propose an Amplify Graph Learning framework based on Sparsity Completion (called AGL-SC)
  arXiv  Detail & Related papers  (2024-06-27T08:26:20Z)
• Representation Learning on Heterophilic Graph with Directional Neighborhood Attention [8.493802098034255]
  Graph Attention Network (GAT) is one of the most popular Graph Neural Network (GNN) architecture. GAT lacks the ability to capture long-range and global graph information, leading to unsatisfactory performance on some datasets. We propose Directional Graph Attention Network (DGAT) to combine the feature-based attention with the global directional information extracted from the graph topology.
  arXiv  Detail & Related papers  (2024-03-03T10:59:16Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• GFlowCausal: Generative Flow Networks for Causal Discovery [27.51595081346858]
  We propose a novel approach to learning a Directed Acyclic Graph (DAG) from observational data called GFlowCausal. GFlowCausal aims to learn the best policy to generate high-reward DAGs by sequential actions with probabilities proportional to predefined rewards. We conduct extensive experiments on both synthetic and real datasets, and results show the proposed approach to be superior and also performs well in a large-scale setting.
  arXiv  Detail & Related papers  (2022-10-15T04:07:39Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• Local Augmentation for Graph Neural Networks [78.48812244668017]
  We introduce the local augmentation, which enhances node features by its local subgraph structures. Based on the local augmentation, we further design a novel framework: LA-GNN, which can apply to any GNN models in a plug-and-play manner.
  arXiv  Detail & Related papers  (2021-09-08T18:10:08Z)
• Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
  We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
  arXiv  Detail & Related papers  (2020-10-19T21:51:47Z)
• Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification [63.56018768401328]
  We propose a Multi-level Graph Convolutional Network (GCN) with Automatic Graph Learning method (MGCN-AGL) for HSI classification. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions. Our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level.
  arXiv  Detail & Related papers  (2020-09-19T09:26:20Z)
• Global Context-Aware Progressive Aggregation Network for Salient Object Detection [117.943116761278]
  We propose a novel network named GCPANet to integrate low-level appearance features, high-level semantic features, and global context features. We show that the proposed approach outperforms the state-of-the-art methods both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2020-03-02T04:26:10Z)

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.