Sparsifying the Update Step in Graph Neural Networks

• URL: http://arxiv.org/abs/2109.00909v1
• Date: Thu, 2 Sep 2021 13:06:34 GMT
• Title: Sparsifying the Update Step in Graph Neural Networks
• Authors: Johannes F. Lutzeyer, Changmin Wu, Michalis Vazirgiannis
• Abstract summary: We study the effect of sparsification on the trainable part of MPNNs known as the Update step. Specifically, we propose the ExpanderGNN model with a tuneable sparsification rate and the Activation-Only GNN, which has no linear transform in the Update step. Our novel benchmark models enable a better understanding of the influence of the Update step on model performance.
• Score: 15.446125349239534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Message-Passing Neural Networks (MPNNs), the most prominent Graph Neural Network (GNN) framework, celebrate much success in the analysis of graph-structured data. Concurrently, the sparsification of Neural Network models attracts a great amount of academic and industrial interest. In this paper, we conduct a structured study of the effect of sparsification on the trainable part of MPNNs known as the Update step. To this end, we design a series of models to successively sparsify the linear transform in the Update step. Specifically, we propose the ExpanderGNN model with a tuneable sparsification rate and the Activation-Only GNN, which has no linear transform in the Update step. In agreement with a growing trend in the literature, the sparsification paradigm is changed by initialising sparse neural network architectures rather than expensively sparsifying already trained architectures. Our novel benchmark models enable a better understanding of the influence of the Update step on model performance and outperform existing simplified benchmark models such as the Simple Graph Convolution. The ExpanderGNNs, and in some cases the Activation-Only models, achieve performance on par with their vanilla counterparts on several downstream tasks while containing significantly fewer trainable parameters. In experiments with matching parameter numbers, our benchmark models outperform the state-of-the-art GNN models. Our code is publicly available at: https://github.com/ChangminWu/ExpanderGNN.

Related papers

• DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning [38.53424185696828]
  The representation learning of Discrete-Time Dynamic Graphs (DTDGs) has been extensively applied to model the dynamics of temporally changing entities and their evolving connections. This paper introduces a novel representation learning method DTFormer for DTDGs, pivoting from the traditional GNN+RNN framework to a Transformer-based architecture.
  arXiv  Detail & Related papers  (2024-07-26T05:46:23Z)
• Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias [75.44877675117749]
  We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph datasets Benchmark.
  arXiv  Detail & Related papers  (2023-09-26T13:09:43Z)
• Simple yet Effective Gradient-Free Graph Convolutional Networks [20.448409424929604]
  Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning. In this paper, we relate over-smoothing with the vanishing gradient phenomenon and craft a gradient-free training framework. Our methods achieve better and more stable performances on node classification tasks with varying depths and cost much less training time.
  arXiv  Detail & Related papers  (2023-02-01T11:00:24Z)
• Bag of Tricks of Semi-Supervised Classification with Graph Neural Networks [0.0]
  In this paper, we first summarize a collection of existing refinements, and then propose several novel techniques regarding these model designs and label usage. We empirically evaluate their impacts on the final model accuracy through ablation studies, and show that we are able to significantly improve various GNN models to the extent that they outweigh the gains from model architecture improvement.
  arXiv  Detail & Related papers  (2021-03-24T17:24:26Z)
• Overcoming Catastrophic Forgetting in Graph Neural Networks [50.900153089330175]
  Catastrophic forgetting refers to the tendency that a neural network "forgets" the previous learned knowledge upon learning new tasks. We propose a novel scheme dedicated to overcoming this problem and hence strengthen continual learning in graph neural networks (GNNs) At the heart of our approach is a generic module, termed as topology-aware weight preserving(TWP)
  arXiv  Detail & Related papers  (2020-12-10T22:30:25Z)
• Data-Driven Learning of Geometric Scattering Networks [74.3283600072357]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2020-10-06T01:20:27Z)
• A Unified View on Graph Neural Networks as Graph Signal Denoising [49.980783124401555]
  Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models can be regarded as solving a graph denoising problem. We instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes.
  arXiv  Detail & Related papers  (2020-10-05T04:57:18Z)
• Streaming Graph Neural Networks via Continual Learning [31.810308087441445]
  Graph neural networks (GNNs) have achieved strong performance in various applications. In this paper, we propose a streaming GNN model based on continual learning. We show that our model can efficiently update model parameters and achieve comparable performance to model retraining.
  arXiv  Detail & Related papers  (2020-09-23T06:52:30Z)
• Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequence [24.594587557319837]
  We develop a graph filter framework for approximating the modelling of hidden states in Recurrent Neural Networks (RNNs) The proposed framework is validated through several multi-way sequence modelling tasks and benchmarked against traditional RNNs. We show that the proposed RGTN is capable of not only out-performing standard RNNs, but also mitigating the Curse of Dimensionality associated with traditional RNNs.
  arXiv  Detail & Related papers  (2020-09-18T10:13:36Z)
• 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)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

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.