SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP

• URL: http://arxiv.org/abs/2210.09609v1
• Date: Tue, 18 Oct 2022 05:55:36 GMT
• Title: SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
• Authors: Jie Chen, Shouzhen Chen, Mingyuan Bai, Junbin Gao, Junping Zhang, Jian Pu
• Abstract summary: One promising inference acceleration direction is to distill the GNNs into message-passing-free student multi-layer perceptrons. We introduce a novel structure-mixing knowledge strategy to enhance the learning ability of students for structure information. Our SA-MLP can consistently outperform the teacher GNNs, while maintaining faster inference assitance.
• Score: 46.52398427166938
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The message-passing mechanism helps Graph Neural Networks (GNNs) achieve remarkable results on various node classification tasks. Nevertheless, the recursive nodes fetching and aggregation in message-passing cause inference latency when deploying GNNs to large-scale graphs. One promising inference acceleration direction is to distill the GNNs into message-passing-free student multi-layer perceptrons (MLPs). However, the MLP student cannot fully learn the structure knowledge due to the lack of structure inputs, which causes inferior performance in the heterophily and inductive scenarios. To address this, we intend to inject structure information into MLP-like students in low-latency and interpretable ways. Specifically, we first design a Structure-Aware MLP (SA-MLP) student that encodes both features and structures without message-passing. Then, we introduce a novel structure-mixing knowledge distillation strategy to enhance the learning ability of MLPs for structure information. Furthermore, we design a latent structure embedding approximation technique with two-stage distillation for inductive scenarios. Extensive experiments on eight benchmark datasets under both transductive and inductive settings show that our SA-MLP can consistently outperform the teacher GNNs, while maintaining faster inference as MLPs. The source code of our work can be found in https://github.com/JC-202/SA-MLP.

Related papers

• Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting [50.181824673039436]
  We propose a Graph Structure Self-Contrasting (GSSC) framework that learns graph structural information without message passing. The proposed framework is based purely on Multi-Layer Perceptrons (MLPs), where the structural information is only implicitly incorporated as prior knowledge. It first applies structural sparsification to remove potentially uninformative or noisy edges in the neighborhood, and then performs structural self-contrasting in the sparsified neighborhood to learn robust node representations.
  arXiv  Detail & Related papers  (2024-09-09T12:56:02Z)
• SimMLP: Training MLPs on Graphs without Supervision [38.63554842214315]
  We introduce SimMLP, a Self-supervised framework for learnings on graphs. SimMLP is the first-learning method that can achieve equivalence to GNNs in the optimal case. We provide a comprehensive theoretical analysis, demonstrating the equivalence between SimMLP and GNNs based on mutual information and inductive bias.
  arXiv  Detail & Related papers  (2024-02-14T03:16:13Z)
• MLPs Compass: What is learned when MLPs are combined with PLMs? [20.003022732050994]
  Multilayer-Perceptrons (MLPs) modules achieving robust structural capture capabilities, even outperforming Graph Neural Networks (GNNs) This paper aims to quantify whether simples can further enhance the already potent ability of PLMs to capture linguistic information.
  arXiv  Detail & Related papers  (2024-01-03T11:06:01Z)
• 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)
• Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs [22.541655587228203]
  Distilling high-accuracy Graph Neural Networks(GNNs) to low-latency multilayer perceptrons(MLPs) on graph tasks has become a hot research topic. We propose a Prototype-Guided Knowledge Distillation(PGKD) method, which does not require graph edges(edge-free) yet learns structure-awares.
  arXiv  Detail & Related papers  (2023-03-24T02:28:55Z)
• Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs [71.93227401463199]
  This paper pinpoints the major source of GNNs' performance gain to their intrinsic capability, by introducing an intermediate model class dubbed as P(ropagational)MLP. We observe that PMLPs consistently perform on par with (or even exceed) their GNN counterparts, while being much more efficient in training.
  arXiv  Detail & Related papers  (2022-12-18T08:17:32Z)
• MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization [51.76758674012744]
  Training graph neural networks (GNNs) on large graphs is complex and extremely time consuming. We propose an embarrassingly simple, yet hugely effective method for GNN training acceleration, called PeerInit.
  arXiv  Detail & Related papers  (2022-09-30T21:33:51Z)
• NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs [41.85649409565574]
  Graph Networks (GNNs) have demonstrated their efficacy in dealing with non-Euclidean structural data. Existing methods attempt to address this scalability issue by training multi-layer perceptrons (MLPs) exclusively on node content features. In this paper, we propose to learn NOise-robust Structure-awares On Graphs (NOSMOG) to overcome the challenges.
  arXiv  Detail & Related papers  (2022-08-22T01:47:07Z)

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.