Reliable and Compact Graph Fine-tuning via GraphSparse Prompting

• URL: http://arxiv.org/abs/2410.21749v1
• Date: Tue, 29 Oct 2024 05:31:14 GMT
• Title: Reliable and Compact Graph Fine-tuning via GraphSparse Prompting
• Abstract summary: We propose exploiting sparse representation theory for graph prompting and present Graph Sparse Prompting (GSP) GSP aims to adaptively and sparsely select the optimal elements to achieve compact prompting for downstream tasks. A simple yet effective algorithm has been designed for solving GSFP and GSmFP models.
• Score: 24.381392096420402
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, graph prompt learning has garnered increasing attention in adapting pre-trained GNN models for downstream graph learning tasks. However, existing works generally conduct prompting over all graph elements (e.g., nodes, edges, node attributes, etc.), which is suboptimal and obviously redundant. To address this issue, we propose exploiting sparse representation theory for graph prompting and present Graph Sparse Prompting (GSP). GSP aims to adaptively and sparsely select the optimal elements (e.g., certain node attributes) to achieve compact prompting for downstream tasks. Specifically, we propose two kinds of GSP models, termed Graph Sparse Feature Prompting (GSFP) and Graph Sparse multi-Feature Prompting (GSmFP). Both GSFP and GSmFP provide a general scheme for tuning any specific pre-trained GNNs that can achieve attribute selection and compact prompt learning simultaneously. A simple yet effective algorithm has been designed for solving GSFP and GSmFP models. Experiments on 16 widely-used benchmark datasets validate the effectiveness and advantages of the proposed GSFPs.

Related papers

• Unified Graph Prompt Learning via Low-Rank Graph Message Prompting [19.25560625766155]
  Graph Data Prompt (GDP) introduces specific prompts in graph data for efficiently adapting pre-trained GNNs.<n>GDPs have been respectively designed for distinct graph component (e.g., node features, edge features, edge weights) and thus operate within limited prompt spaces for graph data.<n>We propose Low-Rank GMP (LR-GMP) which leverages low-rank prompt representation to achieve an effective and compact graph prompt learning.
  arXiv  Detail & Related papers  (2026-04-13T10:07:12Z)
• A Cross-graph Tuning-free GNN Prompting Framework [22.062254916602637]
  We introduce a Cross-graph Tuning-free Prompting Framework (CTP), which supports both homogeneous and heterogeneous graphs.<n>CTP can be directly deployed to unseen graphs without further parameter tuning, and thus enables a plug-and-play GNN inference engine.<n>Experiments on few-shot prediction tasks show that, compared to SOTAs, achieves an average accuracy gain of 30.8% and a maximum gain of 54%.
  arXiv  Detail & Related papers  (2026-04-01T02:34:23Z)
• When Prompting Meets Spiking: Graph Sparse Prompting via Spiking Graph Prompt Learning [16.952691538775877]
  Graph Prompt Feature (GPF) learning has been widely used in adapting pre-trained GNN model on the downstream task.<n>This paper proposes learning sparse graph prompts by leveraging the spiking neuron mechanism, Spiking Graph Prompt Feature (SpikingGPF)<n>Our approach is motivated by the observation that spiking neuron can perform inexpensive information processing and produce sparse outputs which naturally fits the task of our graph sparse prompting.
  arXiv  Detail & Related papers  (2026-01-06T02:22:04Z)
• GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks [66.07512871031163]
  "Pre-training, adaptation" scheme pre-trains powerful Graph Neural Networks (GNNs) over unlabeled graph data.<n>In the adaptation phase, graph prompting modifies input graph data with learnable prompts while keeping pre-trained GNN models frozen.<n>We propose the first **Graph** **T**opology-**O**riented **P**rompting (GraphTOP) framework to effectively adapt pre-trained GNN models for downstream tasks.
  arXiv  Detail & Related papers  (2025-10-25T22:50:12Z)
• DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach [36.29151413055608]
  Graph prompting methods struggle with complex graphs like heterophily graphs. This paper identifies two key challenges in adapting graph prompting methods for complex graphs. We propose Distribution-aware Graph Prompt Tuning (DAGPrompT) to overcome these challenges.
  arXiv  Detail & Related papers  (2025-01-25T08:53:42Z)
• 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) This framework provides a standardized setting to evaluate GNNs across diverse datasets. We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks [13.655670509818144]
  We propose a novel Graph structure Prompt Learning method (GPL) to enhance the training of Graph networks (GNNs) GPL employs task-independent graph structure losses to encourage GNNs to learn intrinsic graph characteristics while simultaneously solving downstream tasks. In experiments on eleven real-world datasets, after being trained by neural prediction, GNNs significantly outperform their original performance on node classification, graph classification, and edge tasks.
  arXiv  Detail & Related papers  (2024-07-16T03:59:18Z)
• Efficient Graph Similarity Computation with Alignment Regularization [7.143879014059894]
  Graph similarity computation (GSC) is a learning-based prediction task using Graph Neural Networks (GNNs) We show that high-quality learning can be attained with a simple yet powerful regularization technique, which we call the Alignment Regularization (AReg) In the inference stage, the graph-level representations learned by the GNN encoder are directly used to compute the similarity score without using AReg again to speed up inference.
  arXiv  Detail & Related papers  (2024-06-21T07:37:28Z)
• 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)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• 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)
• Training Free Graph Neural Networks for Graph Matching [103.45755859119035]
  TFGM is a framework to boost the performance of Graph Neural Networks (GNNs) based graph matching without training. Applying TFGM on various GNNs shows promising improvements over baselines.
  arXiv  Detail & Related papers  (2022-01-14T09:04:46Z)
• Scalable Graph Neural Networks for Heterogeneous Graphs [12.44278942365518]
  Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities.
  arXiv  Detail & Related papers  (2020-11-19T06:03:35Z)
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning [63.97983530843762]
  Graph Neural Networks (GNNs) have achieved great success in graph representation learning. GNNs generate identical representations for graph substructures that may in fact be very different. More powerful GNNs, proposed recently by mimicking higher-order tests, are inefficient as they cannot sparsity of underlying graph structure. We propose Distance Depiction (DE) as a new class of graph representation learning.
  arXiv  Detail & Related papers  (2020-08-31T23:15:40Z)
• Scaling Graph Neural Networks with Approximate PageRank [64.92311737049054]
  We present the PPRGo model which utilizes an efficient approximation of information diffusion in GNNs. In addition to being faster, PPRGo is inherently scalable, and can be trivially parallelized for large datasets like those found in industry settings. We show that training PPRGo and predicting labels for all nodes in this graph takes under 2 minutes on a single machine, far outpacing other baselines on the same graph.
  arXiv  Detail & Related papers  (2020-07-03T09:30:07Z)
• Pointer Graph Networks [48.44209547013781]
  Graph neural networks (GNNs) are typically applied to static graphs that are assumed to be known upfront. Pointer Graph Networks (PGNs) augment sets or graphs with additional inferred edges for improved model generalisation ability. PGNs allow each node to dynamically point to another node, followed by message passing over these pointers.
  arXiv  Detail & Related papers  (2020-06-11T12:52:31Z)

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.