Graph pooling for graph neural networks: Progress, challenges, and opportunities
Graph neural networks have emerged as a leading architecture for many graph-level tasks,
such as graph classification and graph generation. As an essential component of the …
such as graph classification and graph generation. As an essential component of the …
Challenges and opportunities in deep reinforcement learning with graph neural networks: A comprehensive review of algorithms and applications
Deep reinforcement learning (DRL) has empowered a variety of artificial intelligence fields,
including pattern recognition, robotics, recommendation systems, and gaming. Similarly …
including pattern recognition, robotics, recommendation systems, and gaming. Similarly …
On over-squashing in message passing neural networks: The impact of width, depth, and topology
Abstract Message Passing Neural Networks (MPNNs) are instances of Graph Neural
Networks that leverage the graph to send messages over the edges. This inductive bias …
Networks that leverage the graph to send messages over the edges. This inductive bias …
Diffusionnet: Discretization agnostic learning on surfaces
We introduce a new general-purpose approach to deep learning on three-dimensional
surfaces based on the insight that a simple diffusion layer is highly effective for spatial …
surfaces based on the insight that a simple diffusion layer is highly effective for spatial …
Shortest path networks for graph property prediction
Most graph neural network models rely on a particular message passing paradigm, where
the idea is to iteratively propagate node representations of a graph to each node in the direct …
the idea is to iteratively propagate node representations of a graph to each node in the direct …
The expressive power of pooling in graph neural networks
FM Bianchi, V Lachi - Advances in neural information …, 2024 - proceedings.neurips.cc
Abstract In Graph Neural Networks (GNNs), hierarchical pooling operators generate local
summaries of the data by coarsening the graph structure and the vertex features …
summaries of the data by coarsening the graph structure and the vertex features …
A survey on graph representation learning methods
S Khoshraftar, A An - ACM Transactions on Intelligent Systems and …, 2024 - dl.acm.org
Graph representation learning has been a very active research area in recent years. The
goal of graph representation learning is to generate graph representation vectors that …
goal of graph representation learning is to generate graph representation vectors that …
On positional and structural node features for graph neural networks on non-attributed graphs
Graph neural networks (GNNs) have been widely used in various graph-related problems
such as node classification and graph classification, where the superior performance is …
such as node classification and graph classification, where the superior performance is …
How framelets enhance graph neural networks
This paper presents a new approach for assembling graph neural networks based on
framelet transforms. The latter provides a multi-scale representation for graph-structured …
framelet transforms. The latter provides a multi-scale representation for graph-structured …
High-level synthesis performance prediction using gnns: Benchmarking, modeling, and advancing
Agile hardware development requires fast and accurate circuit quality evaluation from early
design stages. Existing work of high-level synthesis (HLS) performance prediction usually …
design stages. Existing work of high-level synthesis (HLS) performance prediction usually …