A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation

• URL: http://arxiv.org/abs/2403.03483v1
• Date: Wed, 6 Mar 2024 05:52:13 GMT
• Title: A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation
• Authors: Lirong Wu, Haitao Lin, Zhangyang Gao, Guojiang Zhao, Stan Z. Li
• Abstract summary: We propose a Teacher-Free Graph Self-Distillation (TGS) framework that does not require any teacher model or GNNs during both training and inference. TGS enjoys the benefits of graph topology awareness in training but is free from data dependency in inference.
• Score: 58.813991312803246
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial applications. One reason for such an academic-industry gap is the neighborhood-fetching latency incurred by data dependency in GNNs. To reduce their gaps, Graph Knowledge Distillation (GKD) is proposed, usually based on a standard teacher-student architecture, to distill knowledge from a large teacher GNN into a lightweight student GNN or MLP. However, we found in this paper that neither teachers nor GNNs are necessary for graph knowledge distillation. We propose a Teacher-Free Graph Self-Distillation (TGS) framework that does not require any teacher model or GNNs during both training and inference. More importantly, the proposed TGS framework is purely based on MLPs, where structural information is only implicitly used to guide dual knowledge self-distillation between the target node and its neighborhood. As a result, TGS enjoys the benefits of graph topology awareness in training but is free from data dependency in inference. Extensive experiments have shown that the performance of vanilla MLPs can be greatly improved with dual self-distillation, e.g., TGS improves over vanilla MLPs by 15.54% on average and outperforms state-of-the-art GKD algorithms on six real-world datasets. In terms of inference speed, TGS infers 75X-89X faster than existing GNNs and 16X-25X faster than classical inference acceleration methods.

Related papers

• Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation [56.912354708167534]
  Graph Neural Networks (GNNs) and lightweight Multi-Layer Perceptron (MLPs) GNNto-MLP Knowledge Distillation (KD) proposes to distill knowledge from a well-trained teacher GNN into a student. This paper proposes a simple yet effective Hardness-aware GNN-to-MLP Distillation (HGMD) framework.
  arXiv  Detail & Related papers  (2024-07-20T06:13:00Z)
• VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs [97.63412451659826]
  VQGraph learns a structure-aware tokenizer on graph data that can encode each node's local substructure as a discrete code. VQGraph achieves new state-of-the-art performance on GNN-to-MLP distillation in both transductive and inductive settings.
  arXiv  Detail & Related papers  (2023-08-04T02:58:08Z)
• Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework [36.160251860788314]
  We propose an efficient Full-Frequency GNN-to-MLP (FFG2M) distillation framework. We factorize the knowledge learned by GNNs into low- and high-frequency components in the spectral domain. We identify a potential information drowning problem for existing GNN-to-MLP distillation.
  arXiv  Detail & Related papers  (2023-05-18T06:57:06Z)
• RELIANT: Fair Knowledge Distillation for Graph Neural Networks [39.22568244059485]
  Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. Knowledge Distillation (KD) is a common solution to compress GNNs. We propose a principled framework named RELIANT to mitigate the bias exhibited by the student model.
  arXiv  Detail & Related papers  (2023-01-03T15:21:24Z)
• Teaching Yourself: Graph Self-Distillation on Neighborhood for Node Classification [42.840122801915996]
  We propose a Graph Self-Distillation on Neighborhood (GSDN) framework to reduce the gap between GNNs and Neurals. GSDN infers 75XX faster than existing GNNs and 16X-25X faster than other inference acceleration methods.
  arXiv  Detail & Related papers  (2022-10-05T08:35:34Z)
• Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation [34.676755383361005]
  Graph-less Neural Networks (GLNNs) have no inference graph dependency. We show that GLNNs with competitive performance infer faster than GNNs by 146X-273X and faster than other acceleration methods by 14X-27X. A comprehensive analysis of GLNN shows when and why GLNN can achieve competitive results to Gs and suggests GLNN as a handy choice for latency-constrained applications.
  arXiv  Detail & Related papers  (2021-10-17T05:16:58Z)
• Graph-Free Knowledge Distillation for Graph Neural Networks [30.38128029453977]
  We propose the first dedicated approach to distilling knowledge from a graph neural network without graph data. The proposed graph-free KD (GFKD) learns graph topology structures for knowledge transfer by modeling them with multinomial distribution. We provide the strategies for handling different types of prior knowledge in the graph data or the GNNs.
  arXiv  Detail & Related papers  (2021-05-16T21:38:24Z)
• On Self-Distilling Graph Neural Network [64.00508355508106]
  We propose the first teacher-free knowledge distillation method for GNNs, termed GNN Self-Distillation (GNN-SD) The method is built upon the proposed neighborhood discrepancy rate (NDR), which quantifies the non-smoothness of the embedded graph in an efficient way. We also summarize a generic GNN-SD framework that could be exploited to induce other distillation strategies.
  arXiv  Detail & Related papers  (2020-11-04T12:29:33Z)
• GPT-GNN: Generative Pre-Training of Graph Neural Networks [93.35945182085948]
  Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data. We present the GPT-GNN framework to initialize GNNs by generative pre-training. We show that GPT-GNN significantly outperforms state-of-the-art GNN models without pre-training by up to 9.1% across various downstream tasks.
  arXiv  Detail & Related papers  (2020-06-27T20:12:33Z)

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.