The heterophilic graph learning handbook: Benchmarks, models, theoretical analysis, applications and challenges

S Luan, C Hua, Q Lu, L Ma, L Wu, X Wang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Homophily principle,\ie {} nodes with the same labels or similar attributes are more likely to
be connected, has been commonly believed to be the main reason for the superiority of …

A survey on oversmoothing in graph neural networks

TK Rusch, MM Bronstein, S Mishra - arxiv preprint arxiv:2303.10993, 2023‏ - arxiv.org
Node features of graph neural networks (GNNs) tend to become more similar with the
increase of the network depth. This effect is known as over-smoothing, which we …

When do graph neural networks help with node classification? investigating the homophily principle on node distinguishability

S Luan, C Hua, M Xu, Q Lu, J Zhu… - Advances in …, 2023‏ - proceedings.neurips.cc
Homophily principle, ie, nodes with the same labels are more likely to be connected, has
been believed to be the main reason for the performance superiority of Graph Neural …

Difformer: Scalable (graph) transformers induced by energy constrained diffusion

Q Wu, C Yang, W Zhao, Y He, D Wipf, J Yan - arxiv preprint arxiv …, 2023‏ - arxiv.org
Real-world data generation often involves complex inter-dependencies among instances,
violating the IID-data hypothesis of standard learning paradigms and posing a challenge for …

A hitchhiker's guide to geometric gnns for 3d atomic systems

A Duval, SV Mathis, CK Joshi, V Schmidt… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Recent advances in computational modelling of atomic systems, spanning molecules,
proteins, and materials, represent them as geometric graphs with atoms embedded as …

A fractional graph laplacian approach to oversmoothing

S Maskey, R Paolino, A Bacho… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
Graph neural networks (GNNs) have shown state-of-the-art performances in various
applications. However, GNNs often struggle to capture long-range dependencies in graphs …

Gread: Graph neural reaction-diffusion networks

J Choi, S Hong, N Park, SB Cho - … Conference on Machine …, 2023‏ - proceedings.mlr.press
Graph neural networks (GNNs) are one of the most popular research topics for deep
learning. GNN methods typically have been designed on top of the graph signal processing …

Mixtures recomposition by neural nets: a multidisciplinary overview

A Nicolle, S Deng, M Ihme… - Journal of Chemical …, 2024‏ - ACS Publications
Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures,
providing an expressive view of the chemical space and multiscale processes. Their …

Improving graph neural networks with learnable propagation operators

M Eliasof, L Ruthotto, E Treister - … Conference on Machine …, 2023‏ - proceedings.mlr.press
Abstract Graph Neural Networks (GNNs) are limited in their propagation operators. In many
cases, these operators often contain non-negative elements only and are shared across …

Understanding convolution on graphs via energies

F Di Giovanni, J Rowbottom, BP Chamberlain… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Graph Neural Networks (GNNs) typically operate by message-passing, where the state of a
node is updated based on the information received from its neighbours. Most message …