Learnable Graph Convolutional Attention Networks
- URL: http://arxiv.org/abs/2211.11853v1
- Date: Mon, 21 Nov 2022 21:08:58 GMT
- Title: Learnable Graph Convolutional Attention Networks
- Authors: Adri\'an Javaloy, Pablo Sanchez-Martin, Amit Levi and Isabel Valera
- Abstract summary: Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by applying a non-uniform score (attending) to the features.
Recent works have shown the strengths and weaknesses of the resulting GNN architectures, respectively, GCNs and GATs.
We introduce the graph convolutional attention layer (CAT), which relies on convolutions to compute the attention scores.
Our results demonstrate that L-CAT is able to efficiently combine different GNN layers along the network, outperforming competing methods in a wide
- Score: 7.465923786151107
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing Graph Neural Networks (GNNs) compute the message exchange between
nodes by either aggregating uniformly (convolving) the features of all the
neighboring nodes, or by applying a non-uniform score (attending) to the
features. Recent works have shown the strengths and weaknesses of the resulting
GNN architectures, respectively, GCNs and GATs. In this work, we aim at
exploiting the strengths of both approaches to their full extent. To this end,
we first introduce the graph convolutional attention layer (CAT), which relies
on convolutions to compute the attention scores. Unfortunately, as in the case
of GCNs and GATs, we show that there exists no clear winner between the three
(neither theoretically nor in practice) as their performance directly depends
on the nature of the data (i.e., of the graph and features). This result brings
us to the main contribution of our work, the learnable graph convolutional
attention network (L-CAT): a GNN architecture that automatically interpolates
between GCN, GAT and CAT in each layer, by adding only two scalar parameters.
Our results demonstrate that L-CAT is able to efficiently combine different GNN
layers along the network, outperforming competing methods in a wide range of
datasets, and resulting in a more robust model that reduces the need of
cross-validating.
Related papers
- Scalable Graph Compressed Convolutions [68.85227170390864]
We propose a differentiable method that applies permutations to calibrate input graphs for Euclidean convolution.
Based on the graph calibration, we propose the Compressed Convolution Network (CoCN) for hierarchical graph representation learning.
arXiv Detail & Related papers (2024-07-26T03:14:13Z) - 2-hop Neighbor Class Similarity (2NCS): A graph structural metric
indicative of graph neural network performance [4.051099980410583]
Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data across numerous domains.
On heterophilous graphs, in which different-type nodes are likely connected, GNNs perform less consistently.
We introduce 2-hop Neighbor Class Similarity (2NCS), a new quantitative graph structural property that correlates with GNN performance more strongly and consistently than alternative metrics.
arXiv Detail & Related papers (2022-12-26T16:16:51Z) - Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with
Heterophily [58.76759997223951]
We propose a new metric based on von Neumann entropy to re-examine the heterophily problem of GNNs.
We also propose a Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets.
arXiv Detail & Related papers (2022-03-19T14:26:43Z) - Incorporating Heterophily into Graph Neural Networks for Graph Classification [6.709862924279403]
Graph Neural Networks (GNNs) often assume strong homophily for graph classification, seldom considering heterophily.
We develop a novel GNN architecture called IHGNN (short for Incorporating Heterophily into Graph Neural Networks)
We empirically validate IHGNN on various graph datasets and demonstrate that it outperforms the state-of-the-art GNNs for graph classification.
arXiv Detail & Related papers (2022-03-15T06:48:35Z) - Graph Attention Networks with Positional Embeddings [7.552100672006174]
Graph Neural Networks (GNNs) are deep learning methods which provide the current state of the art performance in node classification tasks.
We propose a framework, termed Graph Attentional Networks with Positional Embeddings (GAT-POS), to enhance GATs with positional embeddings.
We show that GAT-POS reaches remarkable improvement compared to strong GNN baselines and recent structural embedding enhanced GNNs on non-homophilic graphs.
arXiv Detail & Related papers (2021-05-09T22:13:46Z) - A Unified Lottery Ticket Hypothesis for Graph Neural Networks [82.31087406264437]
We present a unified GNN sparsification (UGS) framework that simultaneously prunes the graph adjacency matrix and the model weights.
We further generalize the popular lottery ticket hypothesis to GNNs for the first time, by defining a graph lottery ticket (GLT) as a pair of core sub-dataset and sparse sub-network.
arXiv Detail & Related papers (2021-02-12T21:52:43Z) - 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) - Distance Encoding: Design Provably More Powerful Neural Networks for
Graph Representation Learning [63.97983530843762]
Graph Neural Networks (GNNs) have achieved great success in graph representation learning.
GNNs generate identical representations for graph substructures that may in fact be very different.
More powerful GNNs, proposed recently by mimicking higher-order tests, are inefficient as they cannot sparsity of underlying graph structure.
We propose Distance Depiction (DE) as a new class of graph representation learning.
arXiv Detail & Related papers (2020-08-31T23:15:40Z) - 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) - Graph Highway Networks [77.38665506495553]
Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency.
They suffer from the notorious over-smoothing problem, in which the learned representations converge to alike vectors when many layers are stacked.
We propose Graph Highway Networks (GHNet) which utilize gating units to balance the trade-off between homogeneity and heterogeneity in the GCN learning process.
arXiv Detail & Related papers (2020-04-09T16:26:43Z) - An Uncoupled Training Architecture for Large Graph Learning [20.784230322205232]
We present Node2Grids, a flexible uncoupled training framework for embedding graph data into grid-like data.
By ranking each node's influence through degree, Node2Grids selects the most influential first-order as well as second-order neighbors with central node fusion information.
For further improving the efficiency of downstream tasks, a simple CNN-based neural network is employed to capture the significant information from the mapped grid-like data.
arXiv Detail & Related papers (2020-03-21T11:49:16Z)
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.