E-CGL: An Efficient Continual Graph Learner

• URL: http://arxiv.org/abs/2408.09350v1
• Date: Sun, 18 Aug 2024 04:10:30 GMT
• Title: E-CGL: An Efficient Continual Graph Learner
• Authors: Jianhao Guo, Zixuan Ni, Yun Zhu, Siliang Tang,
• Abstract summary: In continual graph learning, graphs evolve based on streaming graph data. Continual graph learning presents unique challenges that require adaptive and efficient graph learning methods. We produce an Efficient Continual Graph Learner (E-CGL) in this paper.
• Score: 30.757231591601997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning has emerged as a crucial paradigm for learning from sequential data while preserving previous knowledge. In the realm of continual graph learning, where graphs continuously evolve based on streaming graph data, continual graph learning presents unique challenges that require adaptive and efficient graph learning methods in addition to the problem of catastrophic forgetting. The first challenge arises from the interdependencies between different graph data, where previous graphs can influence new data distributions. The second challenge lies in the efficiency concern when dealing with large graphs. To addresses these two problems, we produce an Efficient Continual Graph Learner (E-CGL) in this paper. We tackle the interdependencies issue by demonstrating the effectiveness of replay strategies and introducing a combined sampling strategy that considers both node importance and diversity. To overcome the limitation of efficiency, E-CGL leverages a simple yet effective MLP model that shares weights with a GCN during training, achieving acceleration by circumventing the computationally expensive message passing process. Our method comprehensively surpasses nine baselines on four graph continual learning datasets under two settings, meanwhile E-CGL largely reduces the catastrophic forgetting problem down to an average of -1.1%. Additionally, E-CGL achieves an average of 15.83x training time acceleration and 4.89x inference time acceleration across the four datasets. These results indicate that E-CGL not only effectively manages the correlation between different graph data during continual training but also enhances the efficiency of continual learning on large graphs. The code is publicly available at https://github.com/aubreygjh/E-CGL.

Related papers

• Continual Learning on Graphs: Challenges, Solutions, and Opportunities [72.7886669278433]
  We provide a comprehensive review of existing continual graph learning (CGL) algorithms. We compare methods with traditional continual learning techniques and analyze the applicability of the traditional continual learning techniques to forgetting tasks. We will maintain an up-to-date repository featuring a comprehensive list of accessible algorithms.
  arXiv  Detail & Related papers  (2024-02-18T12:24:45Z)
• PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation [49.00940417190911]
  Existing graph representation learning models encounter a catastrophic problem when learning with newly incoming graphs. In this paper, we propose a PUdo-label guided Memory bAnkrogation (PUMA) framework to enhance its efficiency and effectiveness.
  arXiv  Detail & Related papers  (2023-12-22T05:09:58Z)
• GIF: A General Graph Unlearning Strategy via Influence Function [63.52038638220563]
  Graph Influence Function (GIF) is a model-agnostic unlearning method that can efficiently and accurately estimate parameter changes in response to a $epsilon$-mass perturbation in deleted data. We conduct extensive experiments on four representative GNN models and three benchmark datasets to justify GIF's superiority in terms of unlearning efficacy, model utility, and unlearning efficiency.
  arXiv  Detail & Related papers  (2023-04-06T03:02:54Z)
• Continual Graph Learning: A Survey [4.618696834991205]
  Research on continual learning (CL) mainly focuses on data represented in the Euclidean space. Most graph learning models are tailored for static graphs. Catastrophic forgetting also emerges in graph learning models when being trained incrementally.
  arXiv  Detail & Related papers  (2023-01-28T15:42:49Z)
• Localized Contrastive Learning on Graphs [110.54606263711385]
  We introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL) In spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
  arXiv  Detail & Related papers  (2022-12-08T23:36:00Z)
• Data Augmentation for Deep Graph Learning: A Survey [66.04015540536027]
  We first propose a taxonomy for graph data augmentation and then provide a structured review by categorizing the related work based on the augmented information modalities. Focusing on the two challenging problems in DGL (i.e., optimal graph learning and low-resource graph learning), we also discuss and review the existing learning paradigms which are based on graph data augmentation.
  arXiv  Detail & Related papers  (2022-02-16T18:30:33Z)
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings [53.58077686470096]
  We propose an end-to-end graph learning framework, namely Iterative Deep Graph Learning (IDGL) for jointly and iteratively learning graph structure and graph embedding. Our experiments show that our proposed IDGL models can consistently outperform or match the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-06-21T19:49:15Z)

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.