Add to ORKGInternational audienceGraph Neural Networks (GNNs) have achieved great successes in many learning tasks performed on graph structures. Nonetheless, to propagate information GNNs rely on a message passing scheme which can become prohibitively expensive when working with industrial-scale graphs. Inspired by the PPRGo model, we propose the CorePPR model, a scalable solution that utilises a learnable convex combination of the approximate personalised PageRank and the CoreRank to diffuse multi-hop neighbourhood information in GNNs. Additionally, we incorporate a dynamic mechanism to select the most influential neighbours for a particular node which reduces training time while preserving the performance of the model. Overall, we demonstrate that ...
International audienceFinding the seed set that maximizes the influence spread over a network is a w...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
We present Gradient Gating (G2), a novel framework for improving the performance of Graph Neural Net...
International audienceGraph Neural Networks (GNNs) have achieved great successes in many learning ta...
Graph Neural Networks (GNNs) have achieved great successes in many learning tasks performed on graph...
There has been a rising interest in graph neural networks (GNNs) for representation learning over th...
International audienceGraph Neural Networks (GNNs) have been studied through the lens of expressive ...
Recently, many models based on the combination of graph convolutional networks and deep learning hav...
Structures or graphs are pervasive in our lives. Although deep learning has achieved tremendous succ...
Graph neural networks (GNNs) have been widely used to learn vector representation of graph-structure...
International audienceGraph Neural Networks (GNNs) have succeeded in various computer science applic...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large ...
Graph-based recommender systems (GBRSs) have achieved promising performance by incorporating the use...
Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large ...
International audienceFinding the seed set that maximizes the influence spread over a network is a w...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
We present Gradient Gating (G2), a novel framework for improving the performance of Graph Neural Net...
International audienceGraph Neural Networks (GNNs) have achieved great successes in many learning ta...
Graph Neural Networks (GNNs) have achieved great successes in many learning tasks performed on graph...
There has been a rising interest in graph neural networks (GNNs) for representation learning over th...
International audienceGraph Neural Networks (GNNs) have been studied through the lens of expressive ...
Recently, many models based on the combination of graph convolutional networks and deep learning hav...
Structures or graphs are pervasive in our lives. Although deep learning has achieved tremendous succ...
Graph neural networks (GNNs) have been widely used to learn vector representation of graph-structure...
International audienceGraph Neural Networks (GNNs) have succeeded in various computer science applic...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large ...
Graph-based recommender systems (GBRSs) have achieved promising performance by incorporating the use...
Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large ...
International audienceFinding the seed set that maximizes the influence spread over a network is a w...
Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse...
We present Gradient Gating (G2), a novel framework for improving the performance of Graph Neural Net...