Graph pooling for graph neural networks: Progress, challenges, and opportunities

C Liu, Y Zhan, J Wu, C Li, B Du, W Hu, T Liu… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Challenges and opportunities in deep reinforcement learning with graph neural networks: A comprehensive review of algorithms and applications

S Munikoti, D Agarwal, L Das… - IEEE transactions on …, 2023 - ieeexplore.ieee.org
Deep reinforcement learning (DRL) has empowered a variety of artificial intelligence fields,
including pattern recognition, robotics, recommendation systems, and gaming. Similarly …

On over-squashing in message passing neural networks: The impact of width, depth, and topology

F Di Giovanni, L Giusti, F Barbero… - International …, 2023 - proceedings.mlr.press
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 …

Diffusionnet: Discretization agnostic learning on surfaces

N Sharp, S Attaiki, K Crane, M Ovsjanikov - ACM Transactions on …, 2022 - dl.acm.org
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 …

Shortest path networks for graph property prediction

R Abboud, R Dimitrov, II Ceylan - Learning on Graphs …, 2022 - proceedings.mlr.press
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 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 …

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 …

On positional and structural node features for graph neural networks on non-attributed graphs

H Cui, Z Lu, P Li, C Yang - Proceedings of the 31st ACM International …, 2022 - dl.acm.org
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 …

How framelets enhance graph neural networks

X Zheng, B Zhou, J Gao, YG Wang, P Lió, M Li… - arXiv preprint arXiv …, 2021 - arxiv.org
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 …

High-level synthesis performance prediction using gnns: Benchmarking, modeling, and advancing

N Wu, H Yang, Y Xie, P Li, C Hao - Proceedings of the 59th ACM/IEEE …, 2022 - dl.acm.org
Agile hardware development requires fast and accurate circuit quality evaluation from early
design stages. Existing work of high-level synthesis (HLS) performance prediction usually …