Pith. sign in

Graph convolutions that can finally model local structure

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Despite quick progress in the last few years, recent studies have shown that modern graph neural networks can still fail at very simple tasks, like detecting small cycles. This hints at the fact that current networks fail to catch information about the local structure, which is problematic if the downstream task heavily relies on graph substructure analysis, as in the context of chemistry. We propose a very simple correction to the now standard GIN convolution that enables the network to detect small cycles with nearly no cost in terms of computation time and number of parameters. Tested on real life molecule property datasets, our model consistently improves performance on large multi-tasked datasets over all baselines, both globally and on a per-task setting.

citation-role summary

background 1

citation-polarity summary

fields

cs.SI 1

years

2024 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

GNN Applied to Ego-nets for Friend Suggestions

cs.SI · 2024-12-16 · conditional · novelty 6.0

WalkGNN, a pair-state graph neural network run on ego-nets, is reported to outperform baselines for VK friend suggestions offline and lift friend-request CTR by 12 percent online.

citing papers explorer

Showing 1 of 1 citing paper.

  • GNN Applied to Ego-nets for Friend Suggestions cs.SI · 2024-12-16 · conditional · none · ref 42 · internal anchor

    WalkGNN, a pair-state graph neural network run on ego-nets, is reported to outperform baselines for VK friend suggestions offline and lift friend-request CTR by 12 percent online.