Preference-driven Knowledge Distillation for Few-shot Node Classification

• URL: http://arxiv.org/abs/2510.10116v3
• Date: Fri, 24 Oct 2025 02:51:28 GMT
• Title: Preference-driven Knowledge Distillation for Few-shot Node Classification
• Authors: Xing Wei, Chunchun Chen, Rui Fan, Xiaofeng Cao, Sourav Medya, Wei Ye,
• Abstract summary: Graph neural networks (GNNs) can efficiently process text-attributed graphs (TAGs)<n>LLMs perform well in zero-/few-shot learning on TAGs but suffer from a scalability challenge.<n>We propose a preference-driven knowledge distillation (PKD) framework to synergize the complementary strengths of LLMs and various GNNs for few-shot node classification.
• Score: 27.21434758196304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs) can efficiently process text-attributed graphs (TAGs) due to their message-passing mechanisms, but their training heavily relies on the human-annotated labels. Moreover, the complex and diverse local topologies of nodes of real-world TAGs make it challenging for a single mechanism to handle. Large language models (LLMs) perform well in zero-/few-shot learning on TAGs but suffer from a scalability challenge. Therefore, we propose a preference-driven knowledge distillation (PKD) framework to synergize the complementary strengths of LLMs and various GNNs for few-shot node classification. Specifically, we develop a GNN-preference-driven node selector that effectively promotes prediction distillation from LLMs to teacher GNNs. To further tackle nodes' intricate local topologies, we develop a node-preference-driven GNN selector that identifies the most suitable teacher GNN for each node, thereby facilitating tailored knowledge distillation from teacher GNNs to the student GNN. Extensive experiments validate the efficacy of our proposed framework in few-shot node classification on real-world TAGs. Our code is be available.

Related papers

• Few-Shot Graph Out-of-Distribution Detection with LLMs [34.42512005781724]
  We propose a framework that combines the strengths of large language models (LLMs) and graph neural networks (GNNs) to enhance data efficiency in graph out-of-distribution (OOD) detection.<n>We show that LLM-GOOD significantly reduces human annotation costs and outperforms state-of-the-art baselines in terms of both ID classification accuracy and OOD detection performance.
  arXiv  Detail & Related papers  (2025-03-28T02:37:18Z)
• IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks [68.6374698896505]
  Graph Neural Networks (GNNs) have been increasingly deployed in a plethora of applications. Privacy leakage may happen when the trained GNNs are deployed and exposed to potential attackers. We propose a principled framework named IDEA to achieve flexible and certified unlearning for GNNs.
  arXiv  Detail & Related papers  (2024-07-28T04:59:59Z)
• LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework [30.54068909225463]
  We aim to streamline the GNN design process and leverage the advantages of Large Language Models (LLMs) to improve the performance of GNNs on downstream tasks. We formulate a new paradigm, coined "LLMs-as-Consultants," which integrates LLMs with GNNs in an interactive manner. We empirically evaluate the effectiveness of LOGIN on node classification tasks across both homophilic and heterophilic graphs.
  arXiv  Detail & Related papers  (2024-05-22T18:17:20Z)
• Large Language Model Meets Graph Neural Network in Knowledge Distillation [7.686812700685084]
  We propose a temporal-aware framework for predicting Quality of Service (QoS) in service-oriented architectures. Our proposed TOGCL framework significantly outperforms state-of-the-art methods across multiple metrics, achieving improvements of up to 38.80%.
  arXiv  Detail & Related papers  (2024-02-08T18:33:21Z)
• Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias [72.33336385797944]
  We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias.<n>We show that LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2023-09-26T13:09:43Z)
• Contrastive Meta-Learning for Few-shot Node Classification [54.36506013228169]
  Few-shot node classification aims to predict labels for nodes on graphs with only limited labeled nodes as references. We create a novel contrastive meta-learning framework on graphs, named COSMIC, with two key designs.
  arXiv  Detail & Related papers  (2023-06-27T02:22:45Z)
• Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification [9.539495585692007]
  We propose novel objective terms for the training of GNNs for node classification. Our first term seeks to maximize the mutual information between node and label features. Our second term promotes anisotropic smoothness in the prediction maps.
  arXiv  Detail & Related papers  (2022-11-29T23:25:14Z)
• Efficient and effective training of language and graph neural network models [36.00479096375565]
  We put forth an efficient and effective framework termed language model GNN (LM-GNN) to jointly train large-scale language models and graph neural networks. The effectiveness in our framework is achieved by applying stage-wise fine-tuning of the BERT model first with heterogenous graph information and then with a GNN model. We evaluate the LM-GNN framework in different datasets performance and showcase the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2022-06-22T00:23:37Z)
• A Variational Edge Partition Model for Supervised Graph Representation Learning [51.30365677476971]
  This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities. We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
  arXiv  Detail & Related papers  (2022-02-07T14:37:50Z)
• Identity-aware Graph Neural Networks [63.6952975763946]
  We develop a class of message passing Graph Neural Networks (ID-GNNs) with greater expressive power than the 1-WL test. ID-GNN extends existing GNN architectures by inductively considering nodes' identities during message passing. We show that transforming existing GNNs to ID-GNNs yields on average 40% accuracy improvement on challenging node, edge, and graph property prediction tasks.
  arXiv  Detail & Related papers  (2021-01-25T18:59:01Z)
• 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)
• A Collective Learning Framework to Boost GNN Expressiveness [25.394456460032625]
  We consider the task of inductive node classification using Graph Neural Networks (GNNs) in supervised and semi-supervised settings. We propose a general collective learning approach to increase the representation power of any existing GNN. We evaluate performance on five real-world network datasets and demonstrate consistent, significant improvement in node classification accuracy.
  arXiv  Detail & Related papers  (2020-03-26T22:07:28Z)

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.