Unitary convolutions for learning on graphs and groups

• URL: http://arxiv.org/abs/2410.05499v1
• Date: Mon, 7 Oct 2024 21:09:14 GMT
• Title: Unitary convolutions for learning on graphs and groups
• Authors: Bobak T. Kiani, Lukas Fesser, Melanie Weber,
• Abstract summary: We study unitary group convolutions, which allow for deeper networks that are more stable during training. The main focus of the paper are graph neural networks, where we show that unitary graph convolutions provably avoid over-smoothing. Our experimental results confirm that unitary graph convolutional networks achieve competitive performance on benchmark datasets.
• Score: 0.9899763598214121
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data with geometric structure is ubiquitous in machine learning often arising from fundamental symmetries in a domain, such as permutation-invariance in graphs and translation-invariance in images. Group-convolutional architectures, which encode symmetries as inductive bias, have shown great success in applications, but can suffer from instabilities as their depth increases and often struggle to learn long range dependencies in data. For instance, graph neural networks experience instability due to the convergence of node representations (over-smoothing), which can occur after only a few iterations of message-passing, reducing their effectiveness in downstream tasks. Here, we propose and study unitary group convolutions, which allow for deeper networks that are more stable during training. The main focus of the paper are graph neural networks, where we show that unitary graph convolutions provably avoid over-smoothing. Our experimental results confirm that unitary graph convolutional networks achieve competitive performance on benchmark datasets compared to state-of-the-art graph neural networks. We complement our analysis of the graph domain with the study of general unitary convolutions and analyze their role in enhancing stability in general group convolutional architectures.

Related papers

• What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding [67.59552859593985]
  Graph Transformers, which incorporate self-attention and positional encoding, have emerged as a powerful architecture for various graph learning tasks. This paper introduces first theoretical investigation of a shallow Graph Transformer for semi-supervised classification.
  arXiv  Detail & Related papers  (2024-06-04T05:30:16Z)
• Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structure [7.133681867718039]
  Graph neural networks are becoming increasingly popular in the field of machine learning. They have been applied in safety-critical environments where perturbations inherently occur. This research addresses the non-passing gap by preserving the dependencies of all elements in the underlying computations.
  arXiv  Detail & Related papers  (2024-04-23T14:12:48Z)
• Homophily modulates double descent generalization in graph convolution networks [33.703222768801574]
  We show how risk is shaped by the interplay between the graph noise, feature noise, and the number of training labels. We use our analytic insights to improve performance of state-of-the-art graph convolution networks on heterophilic datasets.
  arXiv  Detail & Related papers  (2022-12-26T09:57:09Z)
• Towards Relation-centered Pooling and Convolution for Heterogeneous Graph Learning Networks [11.421162988355146]
  Heterogeneous graph neural network has unleashed great potential on graph representation learning. We design a relation-centered Pooling and Convolution for Heterogeneous Graph learning Network, namely PC-HGN, to enable relation-specific sampling and cross-relation convolutions. We evaluate the performance of the proposed model by comparing with state-of-the-art graph learning models on three different real-world datasets.
  arXiv  Detail & Related papers  (2022-10-31T08:43:32Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)
• Graph Kernel Neural Networks [53.91024360329517]
  We propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability.
  arXiv  Detail & Related papers  (2021-12-14T14:48:08Z)
• Multilayer Clustered Graph Learning [66.94201299553336]
  We use contrastive loss as a data fidelity term, in order to properly aggregate the observed layers into a representative graph. Experiments show that our method leads to a clustered clusters w.r.t. We learn a clustering algorithm for solving clustering problems.
  arXiv  Detail & Related papers  (2020-10-29T09:58:02Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)
• Geometrically Principled Connections in Graph Neural Networks [66.51286736506658]
  We argue geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning. We relate graph neural networks to widely successful computer graphics and data approximation models: radial basis functions (RBFs) We introduce affine skip connections, a novel building block formed by combining a fully connected layer with any graph convolution operator.
  arXiv  Detail & Related papers  (2020-04-06T13:25:46Z)

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.