Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning

• URL: http://arxiv.org/abs/2507.09132v1
• Date: Sat, 12 Jul 2025 04:12:24 GMT
• Title: Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning
• Authors: Chu-Yuan Wei, Shun-Yao Liu, Sheng-Da Zhuo, Chang-Dong Wang, Shu-Qiang Huang, Mohsen Guizani,
• Abstract summary: Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based tasks (e.g., node classification or link prediction)<n>Despite their triumphs, GNNs still face challenges such as long training and inference times, difficulty in capturing complex relationships, and insufficient feature extraction.<n>We propose a novel framework combining graph prompts with weight pruning, called GPAWP, which aims to enhance the performance and efficiency of graph prompts by using fewer of them.
• Score: 37.735384483052044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based tasks (e.g., node classification or link prediction). Despite their triumphs, GNNs still face challenges such as long training and inference times, difficulty in capturing complex relationships, and insufficient feature extraction. To tackle these issues, graph pre-training and graph prompt methods have garnered increasing attention for their ability to leverage large-scale datasets for initial learning and task-specific adaptation, offering potential improvements in GNN performance. However, previous research has overlooked the potential of graph prompts in optimizing models, as well as the impact of both positive and negative graph prompts on model stability and efficiency. To bridge this gap, we propose a novel framework combining graph prompts with weight pruning, called GPAWP, which aims to enhance the performance and efficiency of graph prompts by using fewer of them. We evaluate the importance of graph prompts using an importance assessment function to determine positive and negative weights at different granularities. Through hierarchically structured pruning, we eliminate negative prompt labels, resulting in more parameter-efficient and competitively performing prompts. Extensive experiments on three benchmark datasets demonstrate the superiority of GPAWP, leading to a significant reduction in parameters in node classification tasks.

Related papers

• 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)
• A Unified Graph Selective Prompt Learning for Graph Neural Networks [20.595782116049428]
  Graph Prompt Feature (GPF) has achieved remarkable success in adapting pre-trained models for Graph Neural Networks (GNNs) We propose a new unified Graph Selective Prompt Feature learning (GSPF) for GNN fine-tuning.
  arXiv  Detail & Related papers  (2024-06-15T04:36:40Z)
• Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification [25.831508778029097]
  We introduce AMUD, which quantifies the relationship between node profiles and topology from a statistical perspective. We also propose ADPA as a new directed graph learning paradigm for AMUD.
  arXiv  Detail & Related papers  (2023-12-07T07:54:11Z)
• HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks [22.775933880072294]
  HetGPT is a post-training prompting framework for graph neural networks.<n>It improves the performance of state-of-the-art HGNNs on semi-supervised node classification.
  arXiv  Detail & Related papers  (2023-10-23T19:35:57Z)
• Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning [38.5372139056485]
  Graph Active Learning (GAL) aims to find the most informative nodes in graphs for annotation to maximize the Graph Neural Networks (GNNs) performance. Gal strategies may introduce semantic confusion to the selected training set, particularly when graphs are noisy. We present Semantic-aware Active learning framework for Graphs (SAG) to mitigate the semantic confusion problem.
  arXiv  Detail & Related papers  (2023-08-17T07:06:54Z)
• 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)
• MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
  We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs. We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
  arXiv  Detail & Related papers  (2022-08-21T15:12:08Z)
• Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks [52.566735716983956]
  We propose a graph gradual pruning framework termed CGP to dynamically prune GNNs. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.
  arXiv  Detail & Related papers  (2022-07-18T14:23:31Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• 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)

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.