Node-level Contrastive Unlearning on Graph Neural Networks

• URL: http://arxiv.org/abs/2503.02959v1
• Date: Tue, 04 Mar 2025 19:34:19 GMT
• Title: Node-level Contrastive Unlearning on Graph Neural Networks
• Authors: Hong kyu Lee, Qiuchen Zhang, Carl Yang, Li Xiong,
• Abstract summary: Graph unlearning aims to remove a subset of graph entities (i.e. nodes and edges) from a graph neural network (GNN) trained on the graph.<n>Existing works utilize graph partitioning, influence function, or additional layers to achieve graph unlearning.<n>In this paper, we achieve more effective graph unlearning by utilizing the embedding space.
• Score: 27.60189451838526
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Graph unlearning aims to remove a subset of graph entities (i.e. nodes and edges) from a graph neural network (GNN) trained on the graph. Unlike machine unlearning for models trained on Euclidean-structured data, effectively unlearning a model trained on non-Euclidean-structured data, such as graphs, is challenging because graph entities exhibit mutual dependencies. Existing works utilize graph partitioning, influence function, or additional layers to achieve graph unlearning. However, none of them can achieve high scalability and effectiveness without additional constraints. In this paper, we achieve more effective graph unlearning by utilizing the embedding space. The primary training objective of a GNN is to generate proper embeddings for each node that encapsulates both structural information and node feature representations. Thus, directly optimizing the embedding space can effectively remove the target nodes' information from the model. Based on this intuition, we propose node-level contrastive unlearning (Node-CUL). It removes the influence of the target nodes (unlearning nodes) by contrasting the embeddings of remaining nodes and neighbors of unlearning nodes. Through iterative updates, the embeddings of unlearning nodes gradually become similar to those of unseen nodes, effectively removing the learned information without directly incorporating unseen data. In addition, we introduce a neighborhood reconstruction method that optimizes the embeddings of the neighbors in order to remove influence of unlearning nodes to maintain the utility of the GNN model. Experiments on various graph data and models show that our Node-CUL achieves the best unlearn efficacy and enhanced model utility with requiring comparable computing resources with existing frameworks.

Related papers

• Contrastive Graph Representation Learning with Adversarial Cross-view Reconstruction and Information Bottleneck [5.707725771108279]
  We propose an effective Contrastive Graph Representation Learning with Adversarial Cross-view Reconstruction and Information Bottleneck (CGRL) for node classification. Our method significantly outperforms existing state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-08-01T05:45:21Z)
• GraphEdit: Large Language Models for Graph Structure Learning [62.618818029177355]
  Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data. Existing GSL methods heavily depend on explicit graph structural information as supervision signals. We propose GraphEdit, an approach that leverages large language models (LLMs) to learn complex node relationships in graph-structured data.
  arXiv  Detail & Related papers  (2024-02-23T08:29:42Z)
• Degree-based stratification of nodes in Graph Neural Networks [66.17149106033126]
  We modify the Graph Neural Network (GNN) architecture so that the weight matrices are learned, separately, for the nodes in each group. This simple-to-implement modification seems to improve performance across datasets and GNN methods.
  arXiv  Detail & Related papers  (2023-12-16T14:09:23Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection [19.57394670843742]
  We study the unlearning problem in linear-GNNs, and then introduce its extension to non-linear structures. Given a set of nodes to unlearn, we propose PROJECTOR that unlearns by projecting the weight parameters of the pre-trained model onto a subspace that is irrelevant to features of the nodes to be forgotten.
  arXiv  Detail & Related papers  (2023-02-17T16:49:10Z)
• A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features [61.92791503017341]
  Graph Neural Networks (GNNs) with numerical node features and graph structure as inputs have demonstrated superior performance on various supervised learning tasks with graph data. The best models for such data types in most standard supervised learning settings with IID (non-graph) data are not easily incorporated into a GNN. Here we propose a robust stacking framework that fuses graph-aware propagation with arbitrary models intended for IID data.
  arXiv  Detail & Related papers  (2022-06-16T22:46:33Z)
• EIGNN: Efficient Infinite-Depth Graph Neural Networks [51.97361378423152]
  Graph neural networks (GNNs) are widely used for modelling graph-structured data in numerous applications. Motivated by this limitation, we propose a GNN model with infinite depth, which we call Efficient Infinite-Depth Graph Neural Networks (EIGNN) We show that EIGNN has a better ability to capture long-range dependencies than recent baselines, and consistently achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-02-22T08:16:58Z)
• Graph Neural Network with Curriculum Learning for Imbalanced Node Classification [21.085314408929058]
  Graph Neural Network (GNN) is an emerging technique for graph-based learning tasks such as node classification. In this work, we reveal the vulnerability of GNN to the imbalance of node labels. We propose a novel graph neural network framework with curriculum learning (GNN-CL) consisting of two modules.
  arXiv  Detail & Related papers  (2022-02-05T10:46:11Z)
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [68.97378785686723]
  graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. A majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs. We propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
  arXiv  Detail & Related papers  (2021-04-04T23:31:39Z)
• Node2Seq: Towards Trainable Convolutions in Graph Neural Networks [59.378148590027735]
  We propose a graph network layer, known as Node2Seq, to learn node embeddings with explicitly trainable weights for different neighboring nodes. For a target node, our method sorts its neighboring nodes via attention mechanism and then employs 1D convolutional neural networks (CNNs) to enable explicit weights for information aggregation. In addition, we propose to incorporate non-local information for feature learning in an adaptive manner based on the attention scores.
  arXiv  Detail & Related papers  (2021-01-06T03:05:37Z)

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.