VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

• URL: http://arxiv.org/abs/2308.02117v3
• Date: Wed, 6 Mar 2024 15:06:27 GMT
• Title: VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
• Authors: Ling Yang, Ye Tian, Minkai Xu, Zhongyi Liu, Shenda Hong, Wei Qu, Wentao Zhang, Bin Cui, Muhan Zhang, Jure Leskovec
• Abstract summary: 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.
• Score: 97.63412451659826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output representations of teacher GNN. Existing methods mainly make the MLP to mimic the GNN predictions over a few class labels. However, the class space may not be expressive enough for covering numerous diverse local graph structures, thus limiting the performance of knowledge transfer from GNN to MLP. To address this issue, we propose to learn a new powerful graph representation space by directly labeling nodes' diverse local structures for GNN-to-MLP distillation. Specifically, we propose a variant of VQ-VAE to learn a structure-aware tokenizer on graph data that can encode each node's local substructure as a discrete code. The discrete codes constitute a codebook as a new graph representation space that is able to identify different local graph structures of nodes with the corresponding code indices. Then, based on the learned codebook, we propose a new distillation target, namely soft code assignments, to directly transfer the structural knowledge of each node from GNN to MLP. The resulting framework VQGraph achieves new state-of-the-art performance on GNN-to-MLP distillation in both transductive and inductive settings across seven graph datasets. We show that VQGraph with better performance infers faster than GNNs by 828x, and also achieves accuracy improvement over GNNs and stand-alone MLPs by 3.90% and 28.05% on average, respectively. Code: https://github.com/YangLing0818/VQGraph.

Related papers

• 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)
• KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning [27.638009679134523]
  Graph Neural Networks (GNNs) have become the de facto tool for learning node and graph representations. In this work, we compare the performance of Kolmogorov-Arnold Networks (KANs) against that of theorems in graph learning tasks.
  arXiv  Detail & Related papers  (2024-06-26T14:21:21Z)
• A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation [58.813991312803246]
  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.
  arXiv  Detail & Related papers  (2024-03-06T05:52:13Z)
• 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)
• 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)
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction [123.20238648121445]
  We propose a new self-supervised learning framework, Graph Information Aided Node feature exTraction (GIANT) GIANT makes use of the eXtreme Multi-label Classification (XMC) formalism, which is crucial for fine-tuning the language model based on graph information. We demonstrate the superior performance of GIANT over the standard GNN pipeline on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-29T19:55:12Z)
• 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 Neural Networks with Learnable Structural and Positional Representations [83.24058411666483]
  A major issue with arbitrary graphs is the absence of canonical positional information of nodes. We introduce Positional nodes (PE) of nodes, and inject it into the input layer, like in Transformers. We observe a performance increase for molecular datasets, from 2.87% up to 64.14% when considering learnable PE for both GNN classes.
  arXiv  Detail & Related papers  (2021-10-15T05:59:15Z)
• On Graph Neural Networks versus Graph-Augmented MLPs [51.23890789522705]
  Graph-Augmented Multi-Layer Perceptrons (GA-MLPs) first augments node features with certain multi-hop operators on the graph. We prove a separation in expressive power between GA-MLPs and GNNs that grows exponentially in depth.
  arXiv  Detail & Related papers  (2020-10-28T17:59:59Z)

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.