Feature Correlation Aggregation: on the Path to Better Graph Neural
Networks
- URL: http://arxiv.org/abs/2109.09300v1
- Date: Mon, 20 Sep 2021 05:04:26 GMT
- Title: Feature Correlation Aggregation: on the Path to Better Graph Neural
Networks
- Authors: Jieming Zhou, Tong Zhang, Pengfei Fang, Lars Petersson, Mehrtash
Harandi
- Abstract summary: Prior to the introduction of Graph Neural Networks (GNNs), modeling and analyzing irregular data, particularly graphs, was thought to be the Achilles' heel of deep learning.
This paper introduces a central node permutation variant function through a frustratingly simple and innocent-looking modification to the core operation of a GNN.
A tangible boost in performance of the model is observed where the model surpasses previous state-of-the-art results by a significant margin while employing fewer parameters.
- Score: 37.79964911718766
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Prior to the introduction of Graph Neural Networks (GNNs), modeling and
analyzing irregular data, particularly graphs, was thought to be the Achilles'
heel of deep learning. The core concept of GNNs is to find a representation by
recursively aggregating the representations of a central node and those of its
neighbors. The core concept of GNNs is to find a representation by recursively
aggregating the representations of a central node and those of its neighbor,
and its success has been demonstrated by many GNNs' designs. However, most of
them only focus on using the first-order information between a node and its
neighbors. In this paper, we introduce a central node permutation variant
function through a frustratingly simple and innocent-looking modification to
the core operation of a GNN, namely the Feature cOrrelation aGgregation (FOG)
module which learns the second-order information from feature correlation
between a node and its neighbors in the pipeline. By adding FOG into existing
variants of GNNs, we empirically verify this second-order information
complements the features generated by original GNNs across a broad set of
benchmarks. A tangible boost in performance of the model is observed where the
model surpasses previous state-of-the-art results by a significant margin while
employing fewer parameters. (e.g., 33.116% improvement on a real-world
molecular dataset using graph convolutional networks).
Related papers
- Conditional Local Feature Encoding for Graph Neural Networks [14.983942698240293]
Graph neural networks (GNNs) have shown great success in learning from graph-based data.
The key mechanism of current GNNs is message passing, where a node's feature is updated based on the information passing from its local neighbourhood.
We propose conditional local feature encoding (CLFE) to help prevent the problem of node features being dominated by information from local neighbourhood.
arXiv Detail & Related papers (2024-05-08T01:51:19Z) - 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) - Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph [57.2953563124339]
We propose a novel heterogeneous graph neural network with sequential node representation, namely Seq-HGNN.
We conduct extensive experiments on four widely used datasets from Heterogeneous Graph Benchmark (HGB) and Open Graph Benchmark (OGB)
arXiv Detail & Related papers (2023-05-18T07:27:18Z) - A Variational Edge Partition Model for Supervised Graph Representation
Learning [51.30365677476971]
This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities.
We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs.
A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
arXiv Detail & Related papers (2022-02-07T14:37:50Z) - Structure Enhanced Graph Neural Networks for Link Prediction [6.872826041648584]
We propose Structure Enhanced Graph neural network (SEG) for link prediction.
SEG incorporates surrounding topological information of target nodes into an ordinary GNN model.
Experiments on the OGB link prediction datasets demonstrate that SEG achieves state-of-the-art results.
arXiv Detail & Related papers (2022-01-14T03:49:30Z) - Graph Neural Networks with Feature and Structure Aware Random Walk [7.143879014059894]
We show that in typical heterphilous graphs, the edges may be directed, and whether to treat the edges as is or simply make them undirected greatly affects the performance of the GNN models.
We develop a model that adaptively learns the directionality of the graph, and exploits the underlying long-distance correlations between nodes.
arXiv Detail & Related papers (2021-11-19T08:54:21Z) - Identity-aware Graph Neural Networks [63.6952975763946]
We develop a class of message passing Graph Neural Networks (ID-GNNs) with greater expressive power than the 1-WL test.
ID-GNN extends existing GNN architectures by inductively considering nodes' identities during message passing.
We show that transforming existing GNNs to ID-GNNs yields on average 40% accuracy improvement on challenging node, edge, and graph property prediction tasks.
arXiv Detail & Related papers (2021-01-25T18:59:01Z) - GAIN: Graph Attention & Interaction Network for Inductive
Semi-Supervised Learning over Large-scale Graphs [18.23435958000212]
Graph Neural Networks (GNNs) have led to state-of-the-art performance on a variety of machine learning tasks such as recommendation, node classification and link prediction.
Most existing GNN models exploit a single type of aggregator to aggregate neighboring nodes information.
We propose a novel graph neural network architecture, Graph Attention & Interaction Network (GAIN), for inductive learning on graphs.
arXiv Detail & Related papers (2020-11-03T00:20:24Z) - 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) - Generalization and Representational Limits of Graph Neural Networks [46.20253808402385]
We prove that several important graph properties cannot be computed by graph neural networks (GNNs) that rely entirely on local information.
We provide the first data dependent generalization bounds for message passing GNNs.
Our bounds are much tighter than existing VC-dimension based guarantees for GNNs, and are comparable to Rademacher bounds for recurrent neural networks.
arXiv Detail & Related papers (2020-02-14T18:10:14Z) - Bilinear Graph Neural Network with Neighbor Interactions [106.80781016591577]
Graph Neural Network (GNN) is a powerful model to learn representations and make predictions on graph data.
We propose a new graph convolution operator, which augments the weighted sum with pairwise interactions of the representations of neighbor nodes.
We term this framework as Bilinear Graph Neural Network (BGNN), which improves GNN representation ability with bilinear interactions between neighbor nodes.
arXiv Detail & Related papers (2020-02-10T06:43:38Z)
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.