Rethinking pooling in graph neural networks

• URL: http://arxiv.org/abs/2010.11418v1
• Date: Thu, 22 Oct 2020 03:48:56 GMT
• Title: Rethinking pooling in graph neural networks
• Authors: Diego Mesquita, Amauri H. Souza, Samuel Kaski
• Abstract summary: We study the interplay between convolutional layers and the subsequent pooling ones. In contrast to the common belief, local pooling is not responsible for the success of GNNs on relevant and widely-used benchmarks.
• Score: 12.168949038217889
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph pooling is a central component of a myriad of graph neural network (GNN) architectures. As an inheritance from traditional CNNs, most approaches formulate graph pooling as a cluster assignment problem, extending the idea of local patches in regular grids to graphs. Despite the wide adherence to this design choice, no work has rigorously evaluated its influence on the success of GNNs. In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph. Strikingly, our experiments demonstrate that using these variants does not result in any decrease in performance. To understand this phenomenon, we study the interplay between convolutional layers and the subsequent pooling ones. We show that the convolutions play a leading role in the learned representations. In contrast to the common belief, local pooling is not responsible for the success of GNNs on relevant and widely-used benchmarks.

Related papers

• Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach [1.4854797901022863]
  We propose a novel and flexible truss-based graph sparsification model that prunes edges from dense regions of the graph. We then utilize our sparsification model in the state-of-the-art baseline GNNs and pooling models, such as GIN, SAGPool, GMT, DiffPool, MinCutPool, HGP-SL, DMonPool, and AdamGNN.
  arXiv  Detail & Related papers  (2024-07-16T17:21:36Z)
• A Manifold Perspective on the Statistical Generalization of Graph Neural Networks [84.01980526069075]
  Graph Neural Networks (GNNs) combine information from adjacent nodes by successive applications of graph convolutions. We study the generalization gaps of GNNs on both node-level and graph-level tasks. We show that the generalization gaps decrease with the number of nodes in the training graphs.
  arXiv  Detail & Related papers  (2024-06-07T19:25:02Z)
• Learning to Reweight for Graph Neural Network [63.978102332612906]
  Graph Neural Networks (GNNs) show promising results for graph tasks. Existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability.
  arXiv  Detail & Related papers  (2023-12-19T12:25:10Z)
• Degree-based stratification of nodes in Graph Neural Networks [66.17149106033126]
  We modify the Graph Neural Network (GNN) architecture so that the weight matrices are learned, separately, for the nodes in each group. This simple-to-implement modification seems to improve performance across datasets and GNN methods.
  arXiv  Detail & Related papers  (2023-12-16T14:09:23Z)
• Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals [7.6435511285856865]
  Graph neural networks (GNNs) are widely used in domains like social networks and biological systems. locality assumption of GNNs hampers their ability to capture long-range dependencies and global patterns in graphs. We propose a new inductive bias based on variational analysis, drawing inspiration from the Brachchronistoe problem.
  arXiv  Detail & Related papers  (2023-07-01T04:44:43Z)
• Deep Ensembles for Graphs with Higher-order Dependencies [13.164412455321907]
  Graph neural networks (GNNs) continue to achieve state-of-the-art performance on many graph learning tasks. We show that the tendency of traditional graph representations to underfit each node's neighborhood causes existing GNNs to generalize poorly. We propose a novel Deep Graph Ensemble (DGE) which captures neighborhood variance by training an ensemble of GNNs on different neighborhood subspaces of the same node.
  arXiv  Detail & Related papers  (2022-05-27T14:01:08Z)
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs [51.33152272781324]
  Graph Neural Networks (GNNs) are proposed without considering the distribution shifts between training and testing graphs. In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation. We propose a general causal representation framework, called StableGNN, to eliminate the impact of spurious correlations.
  arXiv  Detail & Related papers  (2021-11-20T18:57:18Z)
• Graph Neural Networks: Architectures, Stability and Transferability [176.3960927323358]
  Graph Neural Networks (GNNs) are information processing architectures for signals supported on graphs. They are generalizations of convolutional neural networks (CNNs) in which individual layers contain banks of graph convolutional filters.
  arXiv  Detail & Related papers  (2020-08-04T18:57:36Z)
• Graph Clustering with Graph Neural Networks [5.305362965553278]
  Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph analysis tasks. Unsupervised problems on graphs, such as graph clustering, have proved more resistant to advances in GNNs. We introduce Deep Modularity Networks (DMoN), an unsupervised pooling method inspired by the modularity measure of clustering quality.
  arXiv  Detail & Related papers  (2020-06-30T15:30:49Z)
• Stochastic Graph Neural Networks [123.39024384275054]
  Graph neural networks (GNNs) model nonlinear representations in graph data with applications in distributed agent coordination, control, and planning. Current GNN architectures assume ideal scenarios and ignore link fluctuations that occur due to environment, human factors, or external attacks. In these situations, the GNN fails to address its distributed task if the topological randomness is not considered accordingly.
  arXiv  Detail & Related papers  (2020-06-04T08:00:00Z)

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.