International audienceGraph Neural Networks (GNNs) have been studied through the lens of expressive power and generalization. However, their optimization properties are less well understood. We take the first step towards analyzing GNN training by studying the gradient dynamics of GNNs. First, we analyze linearized GNNs and prove that despite the non-convexity of training, convergence to a global minimum at a linear rate is guaranteed under mild assumptions that we validate on real-world graphs. Second, we study what may affect the GNNs' training speed. Our results show that the training of GNNs is implicitly accelerated by skip connections, more depth, and/or a good label distribution. Empirical results confirm that our theoretical results...
Graph neural networks (GNNs) are among the most powerful tools in deep learning. They routinely solv...
Seminal works on graph neural networks have primarily targeted semi-supervised node classification p...
Conventional wisdom in deep learning states that increasing depth improves expressiveness but compli...
The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden lay...
International audienceGraph Neural Networks (GNNs) have succeeded in various computer science applic...
Structures or graphs are pervasive in our lives. Although deep learning has achieved tremendous succ...
International audienceGraph Neural Networks (GNNs) have achieved great successes in many learning ta...
The graph neural network (GNN) has demonstrated its superior performance in various applications. Th...
A graph is a relational data structure suitable for representing non-Euclidean structured data. In r...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
Graph Convolutional Networks (GCNs) have emerged as powerful tools for learning on network structure...
We present Gradient Gating (G2), a novel framework for improving the performance of Graph Neural Net...
In the recent decade, deep neural networks have solved ever more complex tasks across many fronts in...
The success of deep learning has shown impressive empirical breakthroughs, but many theoretical ques...
Graph neural networks (GNNs) are among the most powerful tools in deep learning. They routinely solv...
Seminal works on graph neural networks have primarily targeted semi-supervised node classification p...
Conventional wisdom in deep learning states that increasing depth improves expressiveness but compli...
The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden lay...
International audienceGraph Neural Networks (GNNs) have succeeded in various computer science applic...
Structures or graphs are pervasive in our lives. Although deep learning has achieved tremendous succ...
International audienceGraph Neural Networks (GNNs) have achieved great successes in many learning ta...
The graph neural network (GNN) has demonstrated its superior performance in various applications. Th...
A graph is a relational data structure suitable for representing non-Euclidean structured data. In r...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
Graph Convolutional Networks (GCNs) have emerged as powerful tools for learning on network structure...
We present Gradient Gating (G2), a novel framework for improving the performance of Graph Neural Net...
In the recent decade, deep neural networks have solved ever more complex tasks across many fronts in...
The success of deep learning has shown impressive empirical breakthroughs, but many theoretical ques...
Graph neural networks (GNNs) are among the most powerful tools in deep learning. They routinely solv...
Seminal works on graph neural networks have primarily targeted semi-supervised node classification p...
Conventional wisdom in deep learning states that increasing depth improves expressiveness but compli...
Add to ORKG